{"id":"96778bd0-831b-4d6e-8352-c5559af13621","entityType":"agent","slug":"clawhub-dlazyai-dlazy-image-generate","name":"图片生成 Image Generate","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dlazyai-dlazy-image-generate","canonicalPath":"/agent/clawhub-dlazyai-dlazy-image-generate","generatedAt":"2026-10-09T18:16:36.403Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:54:53.415Z","emptyReason":null},"description":"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 4.8K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-generate","sourceUrl":"https://clawhub.ai/dlazyai/dlazy-image-generate","homepage":"https://clawhub.ai/dlazyai/skills/dlazy-image-generate","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dlazyai/dlazy-image-generate","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dlazyai/skills/dlazy-image-generate","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":74,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"图片生成 Image Generate technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:54:53.415Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:54:53.415Z","emptyReason":null},"stars":null,"forks":null,"downloads":4752,"packageName":null,"latestVersion":"1.3.27","tractionLabel":"4.8K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:54:53.415Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T04:54:53.415Z","lastCrawledAt":"2026-10-09T04:54:53.415Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T04:54:53.415Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.27","createdAt":"2026-10-08T01:13:59.585Z","changelog":"例行版本更新 2026-10-08","fileCount":4,"zipByteSize":10837},{"version":"1.3.26","createdAt":"2026-10-04T01:12:44.883Z","changelog":"例行版本更新 2026-10-04","fileCount":4,"zipByteSize":10697},{"version":"1.3.25","createdAt":"2026-10-02T04:55:28.709Z","changelog":"例行版本更新 2026-10-02","fileCount":4,"zipByteSize":10818},{"version":"1.3.24","createdAt":"2026-09-30T01:11:56.788Z","changelog":"例行版本更新 2026-09-30","fileCount":4,"zipByteSize":10812},{"version":"1.3.23","createdAt":"2026-09-28T02:10:22.592Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":10691},{"version":"1.3.22","createdAt":"2026-09-28T01:12:44.242Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":10718},{"version":"1.3.21","createdAt":"2026-09-24T01:49:13.603Z","changelog":"例行版本更新 2026-09-24","fileCount":4,"zipByteSize":10974},{"version":"1.3.20","createdAt":"2026-09-22T01:10:32.193Z","changelog":"例行版本更新 2026-09-22","fileCount":4,"zipByteSize":11018}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-generate","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-generate` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/dlazyai/dlazy-image-generate before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T18:16:36.396Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-generate/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:54:53.415Z","emptyReason":null},"readme":"Skill: 图片生成 Image Generate\n\nOwner: dlazyai\n\nSummary: Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\nTags: latest:1.3.27\n\nVersion history:\n\nv1.3.27 | 2026-10-08T01:13:59.585Z | user\n\n例行版本更新 2026-10-08\n\nv1.3.26 | 2026-10-04T01:12:44.883Z | user\n\n例行版本更新 2026-10-04\n\nv1.3.25 | 2026-10-02T04:55:28.709Z | user\n\n例行版本更新 2026-10-02\n\nv1.3.24 | 2026-09-30T01:11:56.788Z | user\n\n例行版本更新 2026-09-30\n\nv1.3.23 | 2026-09-28T02:10:22.592Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.22 | 2026-09-28T01:12:44.242Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.21 | 2026-09-24T01:49:13.603Z | user\n\n例行版本更新 2026-09-24\n\nv1.3.20 | 2026-09-22T01:10:32.193Z | user\n\n例行版本更新 2026-09-22\n\nv1.3.19 | 2026-09-20T01:16:16.040Z | user\n\n例行版本更新 2026-09-20\n\nv1.3.18 | 2026-09-18T01:36:54.182Z | user\n\n例行版本更新 2026-09-18\n\nv1.3.17 | 2026-09-14T01:12:17.467Z | user\n\n例行版本更新 2026-09-14\n\nv1.3.16 | 2026-09-10T01:10:01.133Z | user\n\n例行版本更新 2026-09-10\n\nv1.3.15 | 2026-09-08T01:10:39.031Z | user\n\n例行版本更新 2026-09-08\n\nv1.3.14 | 2026-09-07T01:13:46.278Z | user\n\n例行版本更新 2026-09-07\n\nv1.3.13 | 2026-09-04T01:16:05.571Z | user\n\n例行版本更新 2026-09-04\n\nv1.3.12 | 2026-09-02T01:10:36.789Z | user\n\n例行版本更新 2026-09-02\n\nv1.3.11 | 2026-08-31T02:51:23.498Z | user\n\n源码仓库迁移至 github.com/dlazy-ai/cli\n\nv1.3.10 | 2026-08-24T09:22:15.701Z | user\n\nRestore Chinese display name\n\nv1.3.9 | 2026-08-17T09:04:22.252Z | user\n\nRestore Chinese display name\n\nv1.3.8 | 2026-08-10T05:45:52.769Z | user\n\nRestore Chinese display name\n\nv1.3.7 | 2026-08-10T04:30:58.894Z | user\n\nRestore Chinese display name\n\nv1.3.6 | 2026-08-10T04:00:30.152Z | user\n\nRestore Chinese display name\n\nv1.3.5 | 2026-07-21T02:16:50.926Z | auto\n\n- Bumped the dlazy CLI dependency to version 1.2.3 for installs and usage instructions.\n- Removed the file skill-card.md from the repository.\n- Updated documentation in SKILL.md and SKILL-cn.md to reflect the new CLI version and installation details.\n\nv1.3.4 | 2026-07-17T10:37:11.260Z | auto\n\n- Updated CLI dependency to @dlazy/cli version 1.2.2 (was previously using @latest/1.0.9).\n- Changed installation instructions and metadata to pin the CLI version for more predictable behavior.\n- Clarified authentication steps, explicitly mentioning the login command.\n- Updated and streamlined model descriptions and usage notes.\n- Removed redundant documentation file (skill-card.md).\n\nv1.2.2 | 2026-07-17T08:42:54.598Z | auto\n\n- Removed the file skill-card.md.\n- No changes to core functionality or user experience.\n\nv1.3.3 | 2026-07-09T01:47:09.856Z | user\n\nset Chinese display name for CN search\n\nv1.3.2 | 2026-07-09T01:46:56.916Z | user\n\nset Chinese display name for CN search\n\nv1.3.1 | 2026-07-09T01:28:41.425Z | user\n\nset Chinese display name for CN search\n\nv1.3.0 | 2026-07-07T19:43:12.774Z | auto\n\n- Documentation updates and improvements in both English and Chinese skill descriptions.\n- No code or feature changes; this release focuses on better instructions and clarity.\n\nv1.2.1 | 2026-07-07T18:30:40.538Z | auto\n\n- Added a Chinese translation to the main description field for bilingual support.\n- Removed the redundant skill-card.md file.\n- Minor formatting and metadata updates for clarity and consistency.\n\nv1.2.0 | 2026-06-02T09:54:13.257Z | auto\n\n- Updated CLI install instructions to use the latest version of @dlazy/cli instead of a pinned 1.0.9 version.\n- Metadata now specifies CLI install commands with @latest for npm and npx.\n- Refreshed and simplified the list of available image models, with updated descriptions and new model options (e.g., image-replicate, qwen-image-2-pro).\n- Removed the redundant skill-card.md file.\n- Minor copy and formatting improvements throughout documentation.\n\nv1.1.2 | 2026-06-02T01:38:02.245Z | user\n\nUpdate model skills (names/params refreshed); add search-audio/image/video\n\nv1.1.1 | 2026-05-06T14:05:16.177Z | auto\n\nVersion 1.1.1\n\n- Expanded and updated the list of available image models with detailed descriptions for each, including newly documented models and capabilities.\n- Clarified use cases and feature distinctions for each model to help users select the most suitable option.\n- No changes to the core logic or API usage—documentation updates only.\n\nv1.1.0 | 2026-05-01T07:48:26.469Z | auto\n\n- Added authentication via device-code flow using `dlazy login`, providing a more convenient login method.\n- Clarified alternative manual API key setup options.\n- Added a detailed section on CLI pipe referencing for chaining `dlazy` commands.\n- Updated some example command invocations and references (e.g., changed `mj.imagine` to `mj-imagine`).\n- Improved documentation and organization for easier onboarding.\n\nv1.0.9 | 2026-04-30T10:18:42.141Z | user\n\nSync to CLI 1.0.9 with cliWarning support\n\nv1.0.6 | 2026-04-29T02:34:23.426Z | user\n\nbump @dlazy/cli to 1.0.8\n\nv1.0.5 | 2026-04-27T08:02:34.476Z | user\n\nReduce false-positive scanner alerts: drop 'plaintext' wording from API key storage docs; remove persistsApiKey/network metadata flags in favour of neutral configLocation/apiEndpoints; rewrite Data & Privacy section as factual How-It-Works description without alarming warnings; emphasise that keys can be rotated/revoked at any time from the dLazy dashboard.\n\nv1.0.4 | 2026-04-27T07:41:16.796Z | user\n\nAdd provenance metadata (homepage/source/author/npm), document API key storage location (~/.dlazy/config.json) and DLAZY_API_KEY env var alternative, add Data & Privacy section, recommend 'npx @dlazy/cli@1.0.6' install alternative, normalise Chinese auth-error instruction wording.\n\nv1.0.3 | 2026-04-24T04:02:02.873Z | auto\n\n- Improved agent instructions for handling API key errors: agent should now save the user's key using the CLI and resume the task automatically.\n- Clarified error handling steps in documentation.\n- Updated SKILL.md, SKILL-en.md, and SKILL-cn.md for better guidance and consistency.\n\nv1.0.2 | 2026-04-24T03:27:12.251Z | auto\n\n- Updated required dlazy CLI version to 1.0.6 in installation instructions.\n- No other functional or documentation changes.\n\nv1.0.1 | 2026-04-24T03:21:52.022Z | auto\n\n- Added explicit API key authentication instructions, including CLI setup and key retrieval steps.\n- Updated documentation to clarify all requests require API key configuration.\n- No changes to command usage or available image models.\n\nv1.0.0 | 2026-04-21T05:50:37.271Z | auto\n\nInitial release of dlazy-image-generate skill.\n\n- Adds automated selection of optimal dlazy CLI image model based on prompt.\n- Supports multiple styles: realism, sketch, general text-to-image, minimalist, stylized illustration, SVG/vector, Midjourney, and high-fidelity models.\n- Includes detailed error handling with user guidance for authorization and balance issues.\n- Installation via npm (`@dlazy/cli@1.0.5`) required.\n- Provides usage instructions and model-specific trigger keywords.\n\nArchive index:\n\nArchive v1.3.27: 4 files, 10837 bytes\n\nFiles: skill-card.md (2050b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.27:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\n\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\n\n## Piping Between Commands\n\nEvery `dlazy` invocation prints a JSON envelope on stdout. Any flag value can be a **pipe reference** that pulls from the upstream command's envelope, so you can chain steps without copying URLs by hand.\n\n| Reference          | Resolves to                                                     |\n| ------------------ | --------------------------------------------------------------- |\n| `-`                | Upstream's natural value for this field (scalar or array)       |\n| `@N`               | The N-th output's primary value (e.g. `@0` = first output url)  |\n| `@N.<jsonpath>`    | Drill into the N-th output (`@0.url`, `@1.meta.fps`)            |\n| `@*`               | All outputs' primary values as an array                         |\n| `@stdin`           | The whole upstream JSON envelope                                |\n| `@stdin:<jsonpath>` | Jsonpath into the whole envelope (`@stdin:result.outputs[0].url`) |\n\n### Examples\n\n```bash\n# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> Required flags can be entirely sourced from the pipe — `--field -` satisfies the requirement when an upstream value exists. If stdin is empty, the CLI fails with `code: \"no_stdin\"`.\n\n## Usage\n\nThis skill handles all image generation requests by selecting the best `dlazy` image model.\n\n### Available Image Models\n\n- `dlazy banana-pro`: High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.\n- `dlazy banana2`: General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.\n- `dlazy gpt-image-2`: GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.\n- `dlazy image-replicate`: Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.\n- `dlazy imageseg`: Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.\n- `dlazy jimeng-t2i`: Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.\n- `dlazy kling-image-o1`: Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.\n- `dlazy mj-imagine`: Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.\n- `dlazy qwen-image-2-pro`: Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.\n- `dlazy recraft-v4`: 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.\n- `dlazy recraft-v4-pro`: 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.\n- `dlazy recraft-v4-pro-vector`: High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.\n- `dlazy recraft-v4-vector`: Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.\n- `dlazy seedream-4.5`: High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).\n- `dlazy seedream-5.0`: Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.\n- `dlazy seedream-5.0-lite`: Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.\n- `dlazy seedream-5.0-pro`: Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.\n- `dlazy superres`: Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.\n- `dlazy vectorize`: Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.\n- `dlazy viduq2-t2i`: Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.\n\n**CRITICAL INSTRUCTION FOR AGENT**:\n\n1. Select the most appropriate image model.\n2. Run `dlazy <model_name> -h` to check parameters.\n3. Execute the command.\n\n\n## Error Handling\n\n| Code | Error Type                         | Example Message                                                                                                          |\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\n\n> **AGENT CRITICAL INSTRUCTION**: \n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nFile v1.3.27:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.27\",\n  \"publishedAt\": 1791422039585\n}\n\nFile v1.3.27:skill-card.md\n\n## Description:\n\nSelects a dLazy image model based on the prompt and generates images through the dLazy CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to generate and refine images from text prompts or reference images with dLazy-hosted models.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and generation parameters are sent to dLazy's cloud service.\n\nMitigation: Avoid including sensitive information in prompts or parameters.\n\nRisk: Local media supplied as input can be uploaded to dLazy's media storage.\n\nMitigation: Review and authorize input files before supplying their paths.\n\nRisk: Login stores a dLazy API key locally.\n\nMitigation: Protect the local credential; rotate or revoke the key through the dLazy dashboard if needed.\n\nRisk: A global CLI installation persists on the user's system.\n\nMitigation: Use the pinned npx invocation if a persistent global install is not desired.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-generate)\n- [dLazy CLI package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy CLI repository linked in skill metadata](https://github.com/dlazy-ai/cli)\n- [dLazy API key dashboard](https://dlazy.com/dashboard/organization/api-key)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Image URLs, Guidance]\n\n**Output Format:** [Markdown guidance and CLI JSON responses with hosted image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Generated media is hosted by dLazy.]\n\n## Skill Version(s):\n\n1.3.27 (source: ClawHub release; artifact frontmatter says 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.27:SKILL-cn.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# 文生图 + TTS 配音（拿第一个 output 的 url 作为画面）\ndlazy seedream-4.5 --prompt \"黎明的灯塔\" \\\n  | dlazy qwen-tts --text \"欢迎来到海岸。\" --image @0.url\n\n# 批量分发：把上游所有 output 的 url 一次性传给批处理步骤\ndlazy seedream-4.5 --prompt \"城市天际线\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> 必填参数也可以完全由管道提供 —— 当上游存在对应值时，`--field -` 即可满足必填校验。若 stdin 为空，CLI 会以 `code: \"no_stdin\"` 报错。\n\n## 使用方法\n\n此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。\n\n### 可用的图片模型\n\n- `dlazy banana-pro`: 高质量文生图模型（可选 1 张参考图），适合细节要求更高的主视觉、产品图与品牌风格图生成。\n- `dlazy banana2`: 通用文生图模型（可选 1 张参考图），强调速度与性价比。适合快速视觉草稿、社媒配图与多尺寸比例生成。\n- `dlazy gpt-image-2`: GPT Image 2 文生图及图片编辑模型。支持纯文本生成图片，也支持传入参考图进行图像编辑与合成。\n- `dlazy image-replicate`: 图片复刻工具：分析源图的画面、构图、色彩、光线与风格，生成复刻提示词并交由 Seedream 4.5 生成同风格新图。\n- `dlazy imageseg`: 图像抠图工具：分离前景与背景并返回透明底结果 URL，适合商品图处理、人物抠像与二次合成。\n- `dlazy jimeng-t2i`: 即梦高分辨率文生图模型，支持多比例超清输出与参考图约束，适合商业视觉与精细化出图。\n- `dlazy kling-image-o1`: Kling 图像模型，支持在 prompt 中使用 '<image_1>' 占位符进行参考图绑定。适合多图条件约束与高保真生成。\n- `dlazy mj-imagine`: Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。\n- `dlazy qwen-image-2-pro`: 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型，擅长复杂文本渲染、多行布局、真实质感与语义遵循，支持中英文混排与精细图文设计。\n- `dlazy recraft-v4`: 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。\n- `dlazy recraft-v4-pro`: 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。\n- `dlazy recraft-v4-pro-vector`: 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。\n- `dlazy recraft-v4-vector`: 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。\n- `dlazy seedream-4.5`: 高质量文生图/参考图生图模型，适合海报、写实与创意场景。支持 prompt + 多张参考图，输出单张高分辨率图片（2K/4K）。\n- `dlazy seedream-5.0`: 豆包图像创作模型完整版，支持 2K/3K/4K 高分辨率出图与参考图重绘，适合主视觉、海报以及需要放大印刷的场景。\n- `dlazy seedream-5.0-lite`: 轻量高速图像生成模型，适合批量出图、草图探索与低成本迭代。支持 prompt + 参考图，输出 2K/3K 图片。\n- `dlazy seedream-5.0-pro`: Seedream 5.0 专业版，在画面细节、文字排版与复杂构图上更稳，适合商业级主视觉与高要求的品牌物料。\n- `dlazy superres`: 图像超分工具：提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。\n- `dlazy vectorize`: 图像转 SVG 工具：将位图（PNG/JPG）转换为彩色矢量 SVG 并返回 URL，适合 logo、图标、扁平插画的无损放大与矢量化。\n- `dlazy viduq2-t2i`: Vidu 图像生成模型，支持文本+参考图、比例与分辨率控制。适合角色图、封面图和高分辨率图像生成。\n\n> **智能体关键指令**:\n>\n> 1. 选择最合适的图片模型。\n> 2. 运行 `dlazy <model_name> -h` 查看参数。\n> 3. 执行命令。\n\n\n## 错误处理\n\n| Code | 错误类型                         | 示例信息                                                                                                                 |\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\n\n> **智能体关键指令**: \n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nArchive v1.3.26: 4 files, 10697 bytes\n\nFiles: skill-card.md (1716b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.26:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\n\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\n\n## Piping Between Commands\n\nEvery `dlazy` invocation prints a JSON envelope on stdout. Any flag value can be a **pipe reference** that pulls from the upstream command's envelope, so you can chain steps without copying URLs by hand.\n\n| Reference          | Resolves to                                                     |\n| ------------------ | --------------------------------------------------------------- |\n| `-`                | Upstream's natural value for this field (scalar or array)       |\n| `@N`               | The N-th output's primary value (e.g. `@0` = first output url)  |\n| `@N.<jsonpath>`    | Drill into the N-th output (`@0.url`, `@1.meta.fps`)            |\n| `@*`               | All outputs' primary values as an array                         |\n| `@stdin`           | The whole upstream JSON envelope                                |\n| `@stdin:<jsonpath>` | Jsonpath into the whole envelope (`@stdin:result.outputs[0].url`) |\n\n### Examples\n\n```bash\n# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> Required flags can be entirely sourced from the pipe — `--field -` satisfies the requirement when an upstream value exists. If stdin is empty, the CLI fails with `code: \"no_stdin\"`.\n\n## Usage\n\nThis skill handles all image generation requests by selecting the best `dlazy` image model.\n\n### Available Image Models\n\n- `dlazy banana-pro`: High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.\n- `dlazy banana2`: General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.\n- `dlazy gpt-image-2`: GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.\n- `dlazy image-replicate`: Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.\n- `dlazy imageseg`: Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.\n- `dlazy jimeng-t2i`: Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.\n- `dlazy kling-image-o1`: Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.\n- `dlazy mj-imagine`: Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.\n- `dlazy qwen-image-2-pro`: Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.\n- `dlazy recraft-v4`: 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.\n- `dlazy recraft-v4-pro`: 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.\n- `dlazy recraft-v4-pro-vector`: High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.\n- `dlazy recraft-v4-vector`: Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.\n- `dlazy seedream-4.5`: High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).\n- `dlazy seedream-5.0`: Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.\n- `dlazy seedream-5.0-lite`: Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.\n- `dlazy seedream-5.0-pro`: Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.\n- `dlazy superres`: Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.\n- `dlazy vectorize`: Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.\n- `dlazy viduq2-t2i`: Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.\n\n**CRITICAL INSTRUCTION FOR AGENT**:\n\n1. Select the most appropriate image model.\n2. Run `dlazy <model_name> -h` to check parameters.\n3. Execute the command.\n\n\n## Error Handling\n\n| Code | Error Type                         | Example Message                                                                                                          |\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\n\n> **AGENT CRITICAL INSTRUCTION**: \n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nFile v1.3.26:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.26\",\n  \"publishedAt\": 1791076364883\n}\n\nFile v1.3.26:skill-card.md\n\n## Description:\n\nSelects a dLazy image model for a prompt and helps generate images through the dLazy CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to choose an image-generation model and generate visual assets from prompts or reference images.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and supplied reference media may be sent to the third-party dLazy cloud service.\n\nMitigation: Avoid sharing sensitive prompts or media unless approved for third-party processing.\n\nRisk: Authentication can save an API key in local CLI configuration.\n\nMitigation: Protect the local configuration and rotate or revoke the key if exposed.\n\n## Reference(s):\n\n- [dLazy CLI source (listed in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-generate)\n\n## Skill Output:\n\n**Output Type(s):** [Image links, Shell commands, Guidance]\n\n**Output Format:** [Markdown with image links and inline shell commands]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Generated media may be returned as hosted URLs.]\n\n## Skill Version(s):\n\n1.3.26 (source: ClawHub release metadata; bundled frontmatter: 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.26:SKILL-cn.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# 文生图 + TTS 配音（拿第一个 output 的 url 作为画面）\ndlazy seedream-4.5 --prompt \"黎明的灯塔\" \\\n  | dlazy qwen-tts --text \"欢迎来到海岸。\" --image @0.url\n\n# 批量分发：把上游所有 output 的 url 一次性传给批处理步骤\ndlazy seedream-4.5 --prompt \"城市天际线\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> 必填参数也可以完全由管道提供 —— 当上游存在对应值时，`--field -` 即可满足必填校验。若 stdin 为空，CLI 会以 `code: \"no_stdin\"` 报错。\n\n## 使用方法\n\n此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。\n\n### 可用的图片模型\n\n- `dlazy banana-pro`: 高质量文生图模型（可选 1 张参考图），适合细节要求更高的主视觉、产品图与品牌风格图生成。\n- `dlazy banana2`: 通用文生图模型（可选 1 张参考图），强调速度与性价比。适合快速视觉草稿、社媒配图与多尺寸比例生成。\n- `dlazy gpt-image-2`: GPT Image 2 文生图及图片编辑模型。支持纯文本生成图片，也支持传入参考图进行图像编辑与合成。\n- `dlazy image-replicate`: 图片复刻工具：分析源图的画面、构图、色彩、光线与风格，生成复刻提示词并交由 Seedream 4.5 生成同风格新图。\n- `dlazy imageseg`: 图像抠图工具：分离前景与背景并返回透明底结果 URL，适合商品图处理、人物抠像与二次合成。\n- `dlazy jimeng-t2i`: 即梦高分辨率文生图模型，支持多比例超清输出与参考图约束，适合商业视觉与精细化出图。\n- `dlazy kling-image-o1`: Kling 图像模型，支持在 prompt 中使用 '<image_1>' 占位符进行参考图绑定。适合多图条件约束与高保真生成。\n- `dlazy mj-imagine`: Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。\n- `dlazy qwen-image-2-pro`: 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型，擅长复杂文本渲染、多行布局、真实质感与语义遵循，支持中英文混排与精细图文设计。\n- `dlazy recraft-v4`: 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。\n- `dlazy recraft-v4-pro`: 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。\n- `dlazy recraft-v4-pro-vector`: 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。\n- `dlazy recraft-v4-vector`: 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。\n- `dlazy seedream-4.5`: 高质量文生图/参考图生图模型，适合海报、写实与创意场景。支持 prompt + 多张参考图，输出单张高分辨率图片（2K/4K）。\n- `dlazy seedream-5.0`: 豆包图像创作模型完整版，支持 2K/3K/4K 高分辨率出图与参考图重绘，适合主视觉、海报以及需要放大印刷的场景。\n- `dlazy seedream-5.0-lite`: 轻量高速图像生成模型，适合批量出图、草图探索与低成本迭代。支持 prompt + 参考图，输出 2K/3K 图片。\n- `dlazy seedream-5.0-pro`: Seedream 5.0 专业版，在画面细节、文字排版与复杂构图上更稳，适合商业级主视觉与高要求的品牌物料。\n- `dlazy superres`: 图像超分工具：提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。\n- `dlazy vectorize`: 图像转 SVG 工具：将位图（PNG/JPG）转换为彩色矢量 SVG 并返回 URL，适合 logo、图标、扁平插画的无损放大与矢量化。\n- `dlazy viduq2-t2i`: Vidu 图像生成模型，支持文本+参考图、比例与分辨率控制。适合角色图、封面图和高分辨率图像生成。\n\n> **智能体关键指令**:\n>\n> 1. 选择最合适的图片模型。\n> 2. 运行 `dlazy <model_name> -h` 查看参数。\n> 3. 执行命令。\n\n\n## 错误处理\n\n| Code | 错误类型                         | 示例信息                                                                                                                 |\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\n\n> **智能体关键指令**: \n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nArchive v1.3.25: 4 files, 10818 bytes\n\nFiles: skill-card.md (2004b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.25:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\n\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\n\n## Piping Between Commands\n\nEvery `dlazy` invocation prints a JSON envelope on stdout. Any flag value can be a **pipe reference** that pulls from the upstream command's envelope, so you can chain steps without copying URLs by hand.\n\n| Reference          | Resolves to                                                     |\n| ------------------ | --------------------------------------------------------------- |\n| `-`                | Upstream's natural value for this field (scalar or array)       |\n| `@N`               | The N-th output's primary value (e.g. `@0` = first output url)  |\n| `@N.<jsonpath>`    | Drill into the N-th output (`@0.url`, `@1.meta.fps`)            |\n| `@*`               | All outputs' primary values as an array                         |\n| `@stdin`           | The whole upstream JSON envelope                                |\n| `@stdin:<jsonpath>` | Jsonpath into the whole envelope (`@stdin:result.outputs[0].url`) |\n\n### Examples\n\n```bash\n# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> Required flags can be entirely sourced from the pipe — `--field -` satisfies the requirement when an upstream value exists. If stdin is empty, the CLI fails with `code: \"no_stdin\"`.\n\n## Usage\n\nThis skill handles all image generation requests by selecting the best `dlazy` image model.\n\n### Available Image Models\n\n- `dlazy banana-pro`: High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.\n- `dlazy banana2`: General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.\n- `dlazy gpt-image-2`: GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.\n- `dlazy image-replicate`: Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.\n- `dlazy imageseg`: Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.\n- `dlazy jimeng-t2i`: Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.\n- `dlazy kling-image-o1`: Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.\n- `dlazy mj-imagine`: Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.\n- `dlazy qwen-image-2-pro`: Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.\n- `dlazy recraft-v4`: 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.\n- `dlazy recraft-v4-pro`: 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.\n- `dlazy recraft-v4-pro-vector`: High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.\n- `dlazy recraft-v4-vector`: Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.\n- `dlazy seedream-4.5`: High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).\n- `dlazy seedream-5.0`: Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.\n- `dlazy seedream-5.0-lite`: Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.\n- `dlazy seedream-5.0-pro`: Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.\n- `dlazy superres`: Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.\n- `dlazy vectorize`: Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.\n- `dlazy viduq2-t2i`: Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.\n\n**CRITICAL INSTRUCTION FOR AGENT**:\n\n1. Select the most appropriate image model.\n2. Run `dlazy <model_name> -h` to check parameters.\n3. Execute the command.\n\n\n## Error Handling\n\n| Code | Error Type                         | Example Message                                                                                                          |\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\n\n> **AGENT CRITICAL INSTRUCTION**: \n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nFile v1.3.25:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.25\",\n  \"publishedAt\": 1790916928709\n}\n\nFile v1.3.25:skill-card.md\n\n## Description:\n\nSelects a dLazy image model for a prompt and guides image generation through the dLazy CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to choose an image-generation model and generate or edit images from text prompts and optional reference media via dLazy.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and supplied media may be sent to dLazy's hosted service.\n\nMitigation: Share only prompts and files approved for upload to that service.\n\nRisk: An API key may be saved locally, and requests may consume credits.\n\nMitigation: Use a per-invocation key when persistent storage is unsuitable, protect credentials, and review available credits before large runs.\n\nRisk: Installing the CLI introduces an external npm package.\n\nMitigation: Review the pinned package and its source before global installation in sensitive environments.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-generate)\n- [dLazy CLI repository (declared in skill metadata; import provenance unavailable)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Shell commands, Guidance]\n\n**Output Format:** [Markdown guidance and generated image URLs returned in JSON]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May link to images hosted by dLazy.]\n\n## Skill Version(s):\n\n1.3.25 (source: ClawHub release metadata; artifact frontmatter lists 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.25:SKILL-cn.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# 文生图 + TTS 配音（拿第一个 output 的 url 作为画面）\ndlazy seedream-4.5 --prompt \"黎明的灯塔\" \\\n  | dlazy qwen-tts --text \"欢迎来到海岸。\" --image @0.url\n\n# 批量分发：把上游所有 output 的 url 一次性传给批处理步骤\ndlazy seedream-4.5 --prompt \"城市天际线\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> 必填参数也可以完全由管道提供 —— 当上游存在对应值时，`--field -` 即可满足必填校验。若 stdin 为空，CLI 会以 `code: \"no_stdin\"` 报错。\n\n## 使用方法\n\n此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。\n\n### 可用的图片模型\n\n- `dlazy banana-pro`: 高质量文生图模型（可选 1 张参考图），适合细节要求更高的主视觉、产品图与品牌风格图生成。\n- `dlazy banana2`: 通用文生图模型（可选 1 张参考图），强调速度与性价比。适合快速视觉草稿、社媒配图与多尺寸比例生成。\n- `dlazy gpt-image-2`: GPT Image 2 文生图及图片编辑模型。支持纯文本生成图片，也支持传入参考图进行图像编辑与合成。\n- `dlazy image-replicate`: 图片复刻工具：分析源图的画面、构图、色彩、光线与风格，生成复刻提示词并交由 Seedream 4.5 生成同风格新图。\n- `dlazy imageseg`: 图像抠图工具：分离前景与背景并返回透明底结果 URL，适合商品图处理、人物抠像与二次合成。\n- `dlazy jimeng-t2i`: 即梦高分辨率文生图模型，支持多比例超清输出与参考图约束，适合商业视觉与精细化出图。\n- `dlazy kling-image-o1`: Kling 图像模型，支持在 prompt 中使用 '<image_1>' 占位符进行参考图绑定。适合多图条件约束与高保真生成。\n- `dlazy mj-imagine`: Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。\n- `dlazy qwen-image-2-pro`: 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型，擅长复杂文本渲染、多行布局、真实质感与语义遵循，支持中英文混排与精细图文设计。\n- `dlazy recraft-v4`: 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。\n- `dlazy recraft-v4-pro`: 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。\n- `dlazy recraft-v4-pro-vector`: 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。\n- `dlazy recraft-v4-vector`: 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。\n- `dlazy seedream-4.5`: 高质量文生图/参考图生图模型，适合海报、写实与创意场景。支持 prompt + 多张参考图，输出单张高分辨率图片（2K/4K）。\n- `dlazy seedream-5.0`: 豆包图像创作模型完整版，支持 2K/3K/4K 高分辨率出图与参考图重绘，适合主视觉、海报以及需要放大印刷的场景。\n- `dlazy seedream-5.0-lite`: 轻量高速图像生成模型，适合批量出图、草图探索与低成本迭代。支持 prompt + 参考图，输出 2K/3K 图片。\n- `dlazy seedream-5.0-pro`: Seedream 5.0 专业版，在画面细节、文字排版与复杂构图上更稳，适合商业级主视觉与高要求的品牌物料。\n- `dlazy superres`: 图像超分工具：提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。\n- `dlazy vectorize`: 图像转 SVG 工具：将位图（PNG/JPG）转换为彩色矢量 SVG 并返回 URL，适合 logo、图标、扁平插画的无损放大与矢量化。\n- `dlazy viduq2-t2i`: Vidu 图像生成模型，支持文本+参考图、比例与分辨率控制。适合角色图、封面图和高分辨率图像生成。\n\n> **智能体关键指令**:\n>\n> 1. 选择最合适的图片模型。\n> 2. 运行 `dlazy <model_name> -h` 查看参数。\n> 3. 执行命令。\n\n\n## 错误处理\n\n| Code | 错误类型                         | 示例信息                                                                                                                 |\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\n\n> **智能体关键指令**: \n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nArchive v1.3.24: 4 files, 10812 bytes\n\nFiles: skill-card.md (2005b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.24:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\n\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\n\n## Piping Between Commands\n\nEvery `dlazy` invocation prints a JSON envelope on stdout. Any flag value can be a **pipe reference** that pulls from the upstream command's envelope, so you can chain steps without copying URLs by hand.\n\n| Reference          | Resolves to                                                     |\n| ------------------ | --------------------------------------------------------------- |\n| `-`                | Upstream's natural value for this field (scalar or array)       |\n| `@N`               | The N-th output's primary value (e.g. `@0` = first output url)  |\n| `@N.<jsonpath>`    | Drill into the N-th output (`@0.url`, `@1.meta.fps`)            |\n| `@*`               | All outputs' primary values as an array                         |\n| `@stdin`           | The whole upstream JSON envelope                                |\n| `@stdin:<jsonpath>` | Jsonpath into the whole envelope (`@stdin:result.outputs[0].url`) |\n\n### Examples\n\n```bash\n# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> Required flags can be entirely sourced from the pipe — `--field -` satisfies the requirement when an upstream value exists. If stdin is empty, the CLI fails with `code: \"no_stdin\"`.\n\n## Usage\n\nThis skill handles all image generation requests by selecting the best `dlazy` image model.\n\n### Available Image Models\n\n- `dlazy banana-pro`: High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.\n- `dlazy banana2`: General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.\n- `dlazy gpt-image-2`: GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.\n- `dlazy image-replicate`: Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.\n- `dlazy imageseg`: Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.\n- `dlazy jimeng-t2i`: Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.\n- `dlazy kling-image-o1`: Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.\n- `dlazy mj-imagine`: Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.\n- `dlazy qwen-image-2-pro`: Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.\n- `dlazy recraft-v4`: 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.\n- `dlazy recraft-v4-pro`: 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.\n- `dlazy recraft-v4-pro-vector`: High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.\n- `dlazy recraft-v4-vector`: Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.\n- `dlazy seedream-4.5`: High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).\n- `dlazy seedream-5.0`: Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.\n- `dlazy seedream-5.0-lite`: Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.\n- `dlazy seedream-5.0-pro`: Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.\n- `dlazy superres`: Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.\n- `dlazy vectorize`: Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.\n- `dlazy viduq2-t2i`: Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.\n\n**CRITICAL INSTRUCTION FOR AGENT**:\n\n1. Select the most appropriate image model.\n2. Run `dlazy <model_name> -h` to check parameters.\n3. Execute the command.\n\n\n## Error Handling\n\n| Code | Error Type                         | Example Message                                                                                                          |\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\n\n> **AGENT CRITICAL INSTRUCTION**: \n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nFile v1.3.24:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.24\",\n  \"publishedAt\": 1790730716788\n}\n\nFile v1.3.24:skill-card.md\n\n## Description:\n\nSelects a dLazy CLI image model for generating or editing images from user prompts.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to select and run dLazy image-generation, editing, or enhancement models for visual assets.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and supplied local media may be sent to dLazy, and generated files are hosted there.\n\nMitigation: Avoid private prompts or media unless you intend to share them with dLazy.\n\nRisk: Logging in may save an API key in the user's local CLI configuration.\n\nMitigation: Protect the user configuration and rotate or revoke the key if exposed.\n\nRisk: Hosted generation may consume paid credits; installing the external CLI globally persists a local binary.\n\nMitigation: Check credit usage and use the documented pinned npx invocation if a global install is unwanted.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-generate)\n- [dLazy CLI repository (skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy website](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Guidance, Configuration instructions]\n\n**Output Format:** [Text and shell commands; CLI responses are JSON with generated-media URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Generated images are hosted by dLazy; model selection depends on the requested task.]\n\n## Skill Version(s):\n\n1.3.24 (source: ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.24:SKILL-cn.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# 文生图 + TTS 配音（拿第一个 output 的 url 作为画面）\ndlazy seedream-4.5 --prompt \"黎明的灯塔\" \\\n  | dlazy qwen-tts --text \"欢迎来到海岸。\" --image @0.url\n\n# 批量分发：把上游所有 output 的 url 一次性传给批处理步骤\ndlazy seedream-4.5 --prompt \"城市天际线\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> 必填参数也可以完全由管道提供 —— 当上游存在对应值时，`--field -` 即可满足必填校验。若 stdin 为空，CLI 会以 `code: \"no_stdin\"` 报错。\n\n## 使用方法\n\n此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。\n\n### 可用的图片模型\n\n- `dlazy banana-pro`: 高质量文生图模型（可选 1 张参考图），适合细节要求更高的主视觉、产品图与品牌风格图生成。\n- `dlazy banana2`: 通用文生图模型（可选 1 张参考图），强调速度与性价比。适合快速视觉草稿、社媒配图与多尺寸比例生成。\n- `dlazy gpt-image-2`: GPT Image 2 文生图及图片编辑模型。支持纯文本生成图片，也支持传入参考图进行图像编辑与合成。\n- `dlazy image-replicate`: 图片复刻工具：分析源图的画面、构图、色彩、光线与风格，生成复刻提示词并交由 Seedream 4.5 生成同风格新图。\n- `dlazy imageseg`: 图像抠图工具：分离前景与背景并返回透明底结果 URL，适合商品图处理、人物抠像与二次合成。\n- `dlazy jimeng-t2i`: 即梦高分辨率文生图模型，支持多比例超清输出与参考图约束，适合商业视觉与精细化出图。\n- `dlazy kling-image-o1`: Kling 图像模型，支持在 prompt 中使用 '<image_1>' 占位符进行参考图绑定。适合多图条件约束与高保真生成。\n- `dlazy mj-imagine`: Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。\n- `dlazy qwen-image-2-pro`: 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型，擅长复杂文本渲染、多行布局、真实质感与语义遵循，支持中英文混排与精细图文设计。\n- `dlazy recraft-v4`: 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。\n- `dlazy recraft-v4-pro`: 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。\n- `dlazy recraft-v4-pro-vector`: 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。\n- `dlazy recraft-v4-vector`: 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。\n- `dlazy seedream-4.5`: 高质量文生图/参考图生图模型，适合海报、写实与创意场景。支持 prompt + 多张参考图，输出单张高分辨率图片（2K/4K）。\n- `dlazy seedream-5.0`: 豆包图像创作模型完整版，支持 2K/3K/4K 高分辨率出图与参考图重绘，适合主视觉、海报以及需要放大印刷的场景。\n- `dlazy seedream-5.0-lite`: 轻量高速图像生成模型，适合批量出图、草图探索与低成本迭代。支持 prompt + 参考图，输出 2K/3K 图片。\n- `dlazy seedream-5.0-pro`: Seedream 5.0 专业版，在画面细节、文字排版与复杂构图上更稳，适合商业级主视觉与高要求的品牌物料。\n- `dlazy superres`: 图像超分工具：提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。\n- `dlazy vectorize`: 图像转 SVG 工具：将位图（PNG/JPG）转换为彩色矢量 SVG 并返回 URL，适合 logo、图标、扁平插画的无损放大与矢量化。\n- `dlazy viduq2-t2i`: Vidu 图像生成模型，支持文本+参考图、比例与分辨率控制。适合角色图、封面图和高分辨率图像生成。\n\n> **智能体关键指令**:\n>\n> 1. 选择最合适的图片模型。\n> 2. 运行 `dlazy <model_name> -h` 查看参数。\n> 3. 执行命令。\n\n\n## 错误处理\n\n| Code | 错误类型                         | 示例信息                                                                                                                 |\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\n\n> **智能体关键指令**: \n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nArchive v1.3.23: 4 files, 10691 bytes\n\nFiles: skill-card.md (1731b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.23:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\n\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\n\n## Piping Between Commands\n\nEvery `dlazy` invocation prints a JSON envelope on stdout. Any flag value can be a **pipe reference** that pulls from the upstream command's envelope, so you can chain steps without copying URLs by hand.\n\n| Reference          | Resolves to                                                     |\n| ------------------ | --------------------------------------------------------------- |\n| `-`                | Upstream's natural value for this field (scalar or array)       |\n| `@N`               | The N-th output's primary value (e.g. `@0` = first output url)  |\n| `@N.<jsonpath>`    | Drill into the N-th output (`@0.url`, `@1.meta.fps`)            |\n| `@*`               | All outputs' primary values as an array                         |\n| `@stdin`           | The whole upstream JSON envelope                                |\n| `@stdin:<jsonpath>` | Jsonpath into the whole envelope (`@stdin:result.outputs[0].url`) |\n\n### Examples\n\n```bash\n# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> Required flags can be entirely sourced from the pipe — `--field -` satisfies the requirement when an upstream value exists. If stdin is empty, the CLI fails with `code: \"no_stdin\"`.\n\n## Usage\n\nThis skill handles all image generation requests by selecting the best `dlazy` image model.\n\n### Available Image Models\n\n- `dlazy banana-pro`: High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.\n- `dlazy banana2`: General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.\n- `dlazy gpt-image-2`: GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.\n- `dlazy image-replicate`: Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.\n- `dlazy imageseg`: Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.\n- `dlazy jimeng-t2i`: Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.\n- `dlazy kling-image-o1`: Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.\n- `dlazy mj-imagine`: Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.\n- `dlazy qwen-image-2-pro`: Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.\n- `dlazy recraft-v4`: 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.\n- `dlazy recraft-v4-pro`: 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.\n- `dlazy recraft-v4-pro-vector`: High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.\n- `dlazy recraft-v4-vector`: Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.\n- `dlazy seedream-4.5`: High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).\n- `dlazy seedream-5.0`: Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.\n- `dlazy seedream-5.0-lite`: Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.\n- `dlazy seedream-5.0-pro`: Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.\n- `dlazy superres`: Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.\n- `dlazy vectorize`: Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.\n- `dlazy viduq2-t2i`: Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.\n\n**CRITICAL INSTRUCTION FOR AGENT**:\n\n1. Select the most appropriate image model.\n2. Run `dlazy <model_name> -h` to check parameters.\n3. Execute the command.\n\n\n## Error Handling\n\n| Code | Error Type                         | Example Message                                                                                                          |\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\n\n> **AGENT CRITICAL INSTRUCTION**: \n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nFile v1.3.23:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.23\",\n  \"publishedAt\": 1790561422592\n}\n\nFile v1.3.23:skill-card.md\n\n## Description:\n\nSelects a dLazy image model to generate or edit images from prompts and optional reference media.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to generate, edit, upscale, or vectorize images through dLazy's hosted service.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, parameters, and referenced local media are sent to dLazy's hosted service.\n\nMitigation: Send only content approved for third-party processing and review referenced files before use.\n\nRisk: The skill depends on a third-party CLI package and an API key.\n\nMitigation: Review the pinned package before installation; rotate or revoke the API key when no longer needed.\n\n## Reference(s):\n\n- [dLazy CLI repository (listed in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-generate)\n\n## Skill Output:\n\n**Output Type(s):** [Images, Text]\n\n**Output Format:** [JSON CLI response with hosted image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Image generation and editing results may include hosted URLs; reference media may be uploaded.]\n\n## Skill Version(s):\n\n1.3.23 (source: server-resolved ClawHub release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.23:SKILL-cn.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# 文生图 + TTS 配音（拿第一个 output 的 url 作为画面）\ndlazy seedream-4.5 --prompt \"黎明的灯塔\" \\\n  | dlazy qwen-tts --text \"欢迎来到海岸。\" --image @0.url\n\n# 批量分发：把上游所有 output 的 url 一次性传给批处理步骤\ndlazy seedream-4.5 --prompt \"城市天际线\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> 必填参数也可以完全由管道提供 —— 当上游存在对应值时，`--field -` 即可满足必填校验。若 stdin 为空，CLI 会以 `code: \"no_stdin\"` 报错。\n\n## 使用方法\n\n此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。\n\n### 可用的图片模型\n\n- `dlazy banana-pro`: 高质量文生图模型（可选 1 张参考图），适合细节要求更高的主视觉、产品图与品牌风格图生成。\n- `dlazy banana2`: 通用文生图模型（可选 1 张参考图），强调速度与性价比。适合快速视觉草稿、社媒配图与多尺寸比例生成。\n- `dlazy gpt-image-2`: GPT Image 2 文生图及图片编辑模型。支持纯文本生成图片，也支持传入参考图进行图像编辑与合成。\n- `dlazy image-replicate`: 图片复刻工具：分析源图的画面、构图、色彩、光线与风格，生成复刻提示词并交由 Seedream 4.5 生成同风格新图。\n- `dlazy imageseg`: 图像抠图工具：分离前景与背景并返回透明底结果 URL，适合商品图处理、人物抠像与二次合成。\n- `dlazy jimeng-t2i`: 即梦高分辨率文生图模型，支持多比例超清输出与参考图约束，适合商业视觉与精细化出图。\n- `dlazy kling-image-o1`: Kling 图像模型，支持在 prompt 中使用 '<image_1>' 占位符进行参考图绑定。适合多图条件约束与高保真生成。\n- `dlazy mj-imagine`: Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。\n- `dlazy qwen-image-2-pro`: 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型，擅长复杂文本渲染、多行布局、真实质感与语义遵循，支持中英文混排与精细图文设计。\n- `dlazy recraft-v4`: 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。\n- `dlazy recraft-v4-pro`: 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。\n- `dlazy recraft-v4-pro-vector`: 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。\n- `dlazy recraft-v4-vector`: 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。\n- `dlazy seedream-4.5`: 高质量文生图/参考图生图模型，适合海报、写实与创意场景。支持 prompt + 多张参考图，输出单张高分辨率图片（2K/4K）。\n- `dlazy seedream-5.0`: 豆包图像创作模型完整版，支持 2K/3K/4K 高分辨率出图与参考图重绘，适合主视觉、海报以及需要放大印刷的场景。\n- `dlazy seedream-5.0-lite`: 轻量高速图像生成模型，适合批量出图、草图探索与低成本迭代。支持 prompt + 参考图，输出 2K/3K 图片。\n- `dlazy seedream-5.0-pro`: Seedream 5.0 专业版，在画面细节、文字排版与复杂构图上更稳，适合商业级主视觉与高要求的品牌物料。\n- `dlazy superres`: 图像超分工具：提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。\n- `dlazy vectorize`: 图像转 SVG 工具：将位图（PNG/JPG）转换为彩色矢量 SVG 并返回 URL，适合 logo、图标、扁平插画的无损放大与矢量化。\n- `dlazy viduq2-t2i`: Vidu 图像生成模型，支持文本+参考图、比例与分辨率控制。适合角色图、封面图和高分辨率图像生成。\n\n> **智能体关键指令**:\n>\n> 1. 选择最合适的图片模型。\n> 2. 运行 `dlazy <model_name> -h` 查看参数。\n> 3. 执行命令。\n\n\n## 错误处理\n\n| Code | 错误类型                         | 示例信息                                                                                                                 |\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\n\n> **智能体关键指令**: \n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nArchive v1.3.22: 4 files, 10718 bytes\n\nFiles: skill-card.md (1808b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.22:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\n\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\n\n## Piping Between Commands\n\nEvery `dlazy` invocation prints a JSON envelope on stdout. Any flag value can be a **pipe reference** that pulls from the upstream command's envelope, so you can chain steps without copying URLs by hand.\n\n| Reference          | Resolves to                                                     |\n| ------------------ | --------------------------------------------------------------- |\n| `-`                | Upstream's natural value for this field (scalar or array)       |\n| `@N`               | The N-th output's primary value (e.g. `@0` = first output url)  |\n| `@N.<jsonpath>`    | Drill into the N-th output (`@0.url`, `@1.meta.fps`)            |\n| `@*`               | All outputs' primary values as an array                         |\n| `@stdin`           | The whole upstream JSON envelope                                |\n| `@stdin:<jsonpath>` | Jsonpath into the whole envelope (`@stdin:result.outputs[0].url`) |\n\n### Examples\n\n```bash\n# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> Required flags can be entirely sourced from the pipe — `--field -` satisfies the requirement when an upstream value exists. If stdin is empty, the CLI fails with `code: \"no_stdin\"`.\n\n## Usage\n\nThis skill handles all image generation requests by selecting the best `dlazy` image model.\n\n### Available Image Models\n\n- `dlazy banana-pro`: High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.\n- `dlazy banana2`: General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.\n- `dlazy gpt-image-2`: GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.\n- `dlazy image-replicate`: Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.\n- `dlazy imageseg`: Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.\n- `dlazy jimeng-t2i`: Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.\n- `dlazy kling-image-o1`: Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.\n- `dlazy mj-imagine`: Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.\n- `dlazy qwen-image-2-pro`: Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.\n- `dlazy recraft-v4`: 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.\n- `dlazy recraft-v4-pro`: 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.\n- `dlazy recraft-v4-pro-vector`: High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.\n- `dlazy recraft-v4-vector`: Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.\n- `dlazy seedream-4.5`: High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).\n- `dlazy seedream-5.0`: Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.\n- `dlazy seedream-5.0-lite`: Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.\n- `dlazy seedream-5.0-pro`: Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.\n- `dlazy superres`: Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.\n- `dlazy vectorize`: Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.\n- `dlazy viduq2-t2i`: Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.\n\n**CRITICAL INSTRUCTION FOR AGENT**:\n\n1. Select the most appropriate image model.\n2. Run `dlazy <model_name> -h` to check parameters.\n3. Execute the command.\n\n\n## Error Handling\n\n| Code | Error Type                         | Example Message                                                                                                          |\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\n\n> **AGENT CRITICAL INSTRUCTION**: \n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nFile v1.3.22:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.22\",\n  \"publishedAt\": 1790557964242\n}\n\nFile v1.3.22:skill-card.md\n\n## Description:\n\nSelects a dLazy image model for a prompt and guides image generation through the dLazy CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to select a dLazy image model and generate or edit images from prompts and optional reference media.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected local media may be sent to dLazy-hosted services.\n\nMitigation: Share only prompts and files you are comfortable sending to dLazy.\n\nRisk: Image generation may incur API usage costs.\n\nMitigation: Request dLazy generation explicitly and check available credits before running commands.\n\nRisk: Login saves an API key locally, and global installation persists the CLI.\n\nMitigation: Protect or rotate the API key and use the pinned npx invocation if a global install is unwanted.\n\n## Reference(s):\n\n- [dLazy CLI homepage (skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package (skill metadata)](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, Image URLs]\n\n**Output Format:** [Text guidance and CLI JSON containing hosted image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Generated media is hosted by dLazy.]\n\n## Skill Version(s):\n\n1.3.22 (source: server-resolved ClawHub release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.22:SKILL-cn.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# 文生图 + TTS 配音（拿第一个 output 的 url 作为画面）\ndlazy seedream-4.5 --prompt \"黎明的灯塔\" \\\n  | dlazy qwen-tts --text \"欢迎来到海岸。\" --image @0.url\n\n# 批量分发：把上游所有 output 的 url 一次性传给批处理步骤\ndlazy seedream-4.5 --prompt \"城市天际线\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> 必填参数也可以完全由管道提供 —— 当上游存在对应值时，`--field -` 即可满足必填校验。若 stdin 为空，CLI 会以 `code: \"no_stdin\"` 报错。\n\n## 使用方法\n\n此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。\n\n### 可用的图片模型\n\n- `dlazy banana-pro`: 高质量文生图模型（可选 1 张参考图），适合细节要求更高的主视觉、产品图与品牌风格图生成。\n- `dlazy banana2`: 通用文生图模型（可选 1 张参考图），强调速度与性价比。适合快速视觉草稿、社媒配图与多尺寸比例生成。\n- `dlazy gpt-image-2`: GPT Image 2 文生图及图片编辑模型。支持纯文本生成图片，也支持传入参考图进行图像编辑与合成。\n- `dlazy image-replicate`: 图片复刻工具：分析源图的画面、构图、色彩、光线与风格，生成复刻提示词并交由 Seedream 4.5 生成同风格新图。\n- `dlazy imageseg`: 图像抠图工具：分离前景与背景并返回透明底结果 URL，适合商品图处理、人物抠像与二次合成。\n- `dlazy jimeng-t2i`: 即梦高分辨率文生图模型，支持多比例超清输出与参考图约束，适合商业视觉与精细化出图。\n- `dlazy kling-image-o1`: Kling 图像模型，支持在 prompt 中使用 '<image_1>' 占位符进行参考图绑定。适合多图条件约束与高保真生成。\n- `dlazy mj-imagine`: Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。\n- `dlazy qwen-image-2-pro`: 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型，擅长复杂文本渲染、多行布局、真实质感与语义遵循，支持中英文混排与精细图文设计。\n- `dlazy recraft-v4`: 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。\n- `dlazy recraft-v4-pro`: 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。\n- `dlazy recraft-v4-pro-vector`: 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。\n- `dlazy recraft-v4-vector`: 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。\n- `dlazy seedream-4.5`: 高质量文生图/参考图生图模型，适合海报、写实与创意场景。支持 prompt + 多张参考图，输出单张高分辨率图片（2K/4K）。\n- `dlazy seedream-5.0`: 豆包图像创作模型完整版，支持 2K/3K/4K 高分辨率出图与参考图重绘，适合主视觉、海报以及需要放大印刷的场景。\n- `dlazy seedream-5.0-lite`: 轻量高速图像生成模型，适合批量出图、草图探索与低成本迭代。支持 prompt + 参考图，输出 2K/3K 图片。\n- `dlazy seedream-5.0-pro`: Seedream 5.0 专业版，在画面细节、文字排版与复杂构图上更稳，适合商业级主视觉与高要求的品牌物料。\n- `dlazy superres`: 图像超分工具：提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。\n- `dlazy vectorize`: 图像转 SVG 工具：将位图（PNG/JPG）转换为彩色矢量 SVG 并返回 URL，适合 logo、图标、扁平插画的无损放大与矢量化。\n- `dlazy viduq2-t2i`: Vidu 图像生成模型，支持文本+参考图、比例与分辨率控制。适合角色图、封面图和高分辨率图像生成。\n\n> **智能体关键指令**:\n>\n> 1. 选择最合适的图片模型。\n> 2. 运行 `dlazy <model_name> -h` 查看参数。\n> 3. 执行命令。\n\n\n## 错误处理\n\n| Code | 错误类型                         | 示例信息                                                                                                                 |\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\n\n> **智能体关键指令**: \n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nArchive v1.3.21: 4 files, 10974 bytes\n\nFiles: skill-card.md (2366b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.21:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\n\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\n\n## Piping Between Commands\n\nEvery `dlazy` invocation prints a JSON envelope on stdout. Any flag value can be a **pipe reference** that pulls from the upstream command's envelope, so you can chain steps without copying URLs by hand.\n\n| Reference          | Resolves to                                                     |\n| ------------------ | --------------------------------------------------------------- |\n| `-`                | Upstream's natural value for this field (scalar or array)       |\n| `@N`               | The N-th output's primary value (e.g. `@0` = first output url)  |\n| `@N.<jsonpath>`    | Drill into the N-th output (`@0.url`, `@1.meta.fps`)            |\n| `@*`               | All outputs' primary values as an array                         |\n| `@stdin`           | The whole upstream JSON envelope                                |\n| `@stdin:<jsonpath>` | Jsonpath into the whole envelope (`@stdin:result.outputs[0].url`) |\n\n### Examples\n\n```bash\n# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> Required flags can be entirely sourced from the pipe — `--field -` satisfies the requirement when an upstream value exists. If stdin is empty, the CLI fails with `code: \"no_stdin\"`.\n\n## Usage\n\nThis skill handles all image generation requests by selecting the best `dlazy` image model.\n\n### Available Image Models\n\n- `dlazy banana-pro`: High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.\n- `dlazy banana2`: General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.\n- `dlazy gpt-image-2`: GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.\n- `dlazy image-replicate`: Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.\n- `dlazy imageseg`: Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.\n- `dlazy jimeng-t2i`: Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.\n- `dlazy kling-image-o1`: Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.\n- `dlazy mj-imagine`: Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.\n- `dlazy qwen-image-2-pro`: Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.\n- `dlazy recraft-v4`: 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.\n- `dlazy recraft-v4-pro`: 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.\n- `dlazy recraft-v4-pro-vector`: High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.\n- `dlazy recraft-v4-vector`: Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.\n- `dlazy seedream-4.5`: High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).\n- `dlazy seedream-5.0`: Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.\n- `dlazy seedream-5.0-lite`: Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.\n- `dlazy seedream-5.0-pro`: Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.\n- `dlazy superres`: Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.\n- `dlazy vectorize`: Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.\n- `dlazy viduq2-t2i`: Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.\n\n**CRITICAL INSTRUCTION FOR AGENT**:\n\n1. Select the most appropriate image model.\n2. Run `dlazy <model_name> -h` to check parameters.\n3. Execute the command.\n\n\n## Error Handling\n\n| Code | Error Type                         | Example Message                                                                                                          |\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\n\n> **AGENT CRITICAL INSTRUCTION**: \n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nFile v1.3.21:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.21\",\n  \"publishedAt\": 1790214553603\n}\n\nFile v1.3.21:skill-card.md\n\n## Description:\n\nImage generation skill that automatically selects an appropriate dLazy CLI image model based on the prompt.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to generate, edit, upscale, segment, vectorize, or replicate images through dLazy's hosted image models from natural-language prompts and optional reference media.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, parameters, and local media files explicitly passed to the CLI may be sent to dLazy's hosted service, and generated outputs may be hosted by dLazy.\n\nMitigation: Do not send private or sensitive reference files unless that data sharing is acceptable for the use case.\n\nRisk: The dLazy CLI may store a paid-account API key in local configuration.\n\nMitigation: Use per-invocation environment authentication for temporary credentials when appropriate, and rotate or revoke keys from the dLazy dashboard if exposure is suspected.\n\nRisk: The skill installs or runs a third-party npm CLI before contacting the hosted API.\n\nMitigation: Review the pinned package or listed source before trusting the CLI with credentials or private media.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-image-generate)\n- [dLazy CLI source listed in skill metadata](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy homepage](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, Configuration instructions, Files]\n\n**Output Format:** [Markdown with inline bash commands and JSON result URLs from the dLazy CLI]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Generated media is returned as hosted URLs; authentication uses a dLazy API key stored by the CLI or supplied per invocation.]\n\n## Skill Version(s):\n\n1.3.21 (source: server release evidence; artifact frontmatter reports 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.21:SKILL-cn.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# 文生图 + TTS 配音（拿第一个 output 的 url 作为画面）\ndlazy seedream-4.5 --prompt \"黎明的灯塔\" \\\n  | dlazy qwen-tts --text \"欢迎来到海岸。\" --image @0.url\n\n# 批量分发：把上游所有 output 的 url 一次性传给批处理步骤\ndlazy seedream-4.5 --prompt \"城市天际线\" --n 4 \\\n  | dlazy superres --images @*\n```\n\n> 必填参数也可以完全由管道提供 —— 当上游存在对应值时，`--field -` 即可满足必填校验。若 stdin 为空，CLI 会以 `code: \"no_stdin\"` 报错。\n\n## 使用方法\n\n此技能处理所有图片生成请求，通过选择最佳的 `dlazy` 图片模型。\n\n### 可用的图片模型\n\n- `dlazy banana-pro`: 高质量文生图模型（可选 1 张参考图），适合细节要求更高的主视觉、产品图与品牌风格图生成。\n- `dlazy banana2`: 通用文生图模型（可选 1 张参考图），强调速度与性价比。适合快速视觉草稿、社媒配图与多尺寸比例生成。\n- `dlazy gpt-image-2`: GPT Image 2 文生图及图片编辑模型。支持纯文本生成图片，也支持传入参考图进行图像编辑与合成。\n- `dlazy image-replicate`: 图片复刻工具：分析源图的画面、构图、色彩、光线与风格，生成复刻提示词并交由 Seedream 4.5 生成同风格新图。\n- `dlazy imageseg`: 图像抠图工具：分离前景与背景并返回透明底结果 URL，适合商品图处理、人物抠像与二次合成。\n- `dlazy jimeng-t2i`: 即梦高分辨率文生图模型，支持多比例超清输出与参考图约束，适合商业视觉与精细化出图。\n- `dlazy kling-image-o1`: Kling 图像模型，支持在 prompt 中使用 '<image_1>' 占位符进行参考图绑定。适合多图条件约束与高保真生成。\n- `dlazy mj-imagine`: Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。\n- `dlazy qwen-image-2-pro`: 阿里云百炼 qwen-image-2.0-pro 千问通用图像生成模型，擅长复杂文本渲染、多行布局、真实质感与语义遵循，支持中英文混排与精细图文设计。\n- `dlazy recraft-v4`: 1MP 栅格图像生成，具备更精炼的设计判断力。适合日常创意工作和快速迭代场景。\n- `dlazy recraft-v4-pro`: 4MP 高分辨率栅格图像生成。适合可印刷级素材与大幅面应用场景。\n- `dlazy recraft-v4-pro-vector`: 高保真文本到矢量模型，4MP 级品质。适合生产级 SVG 素材与精细插画。\n- `dlazy recraft-v4-vector`: 文本到矢量图模型，输出 SVG 结果。适合 Logo、图标与可无损缩放的设计素材。\n- `dlazy seedream-4.5`: 高质量文生图/参考图生图模型，适合海报、写实与创意场景。支持 prompt + 多张参考图，输出单张高分辨率图片（2K/4K）。\n- `dlazy seedream-5.0`: 豆包图像创作模型完整版，支持 2K/3K/4K 高分辨率出图与参考图重绘，适合主视觉、海报以及需要放大印刷的场景。\n- `dlazy seedream-5.0-lite`: 轻量高速图像生成模型，适合批量出图、草图探索与低成本迭代。支持 prompt + 参考图，输出 2K/3K 图片。\n- `dlazy seedream-5.0-pro`: Seedream 5.0 专业版，在画面细节、文字排版与复杂构图上更稳，适合商业级主视觉与高要求的品牌物料。\n- `dlazy superres`: 图像超分工具：提升图片清晰度与细节并返回增强后 URL，适合低清素材修复与二次放大输出。\n- `dlazy vectorize`: 图像转 SVG 工具：将位图（PNG/JPG）转换为彩色矢量 SVG 并返回 URL，适合 logo、图标、扁平插画的无损放大与矢量化。\n- `dlazy viduq2-t2i`: Vidu 图像生成模型，支持文本+参考图、比例与分辨率控制。适合角色图、封面图和高分辨率图像生成。\n\n> **智能体关键指令**:\n>\n> 1. 选择最合适的图片模型。\n> 2. 运行 `dlazy <model_name> -h` 查看参数。\n> 3. 执行命令。\n\n\n## 错误处理\n\n| Code | 错误类型                         | 示例信息                                                                                                                 |\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\n\n> **智能体关键指令**: \n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\n\n## Tips\n\nVisit https://dlazy.com for more information.\n\nArchive v1.3.20: 4 files, 11018 bytes\n\nFiles: skill-card.md (2490b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nFile v1.3.20:SKILL.md\n\n---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\n- Generated output UR\n\nArchive v1.3.19: 4 files, 10889 bytes\n\nFiles: skill-card.md (2149b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)\n\nArchive v1.3.18: 4 files, 10839 bytes\n\nFiles: skill-card.md (2045b), SKILL-cn.md (10417b), SKILL.md (10791b), _meta.json (140b)","readmeExcerpt":"Skill: 图片生成 Image Generate Owner: dlazyai Summary: Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。 Tags: latest:1.3.27 Version history: v1.3.27 | 2026-10-08T01:13:59.585Z | user 例行版本更新 2026-10-08 v1.3.26 | 2026-10-04T01:12:44.883Z | user 例行版本更新 2026-10-04 v1.3.25 | 2026-10-02T04:55:28.709Z | user 例行版本更新 2026-10-02 v1.3.24 | 2026-0","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"},{"language":"bash","snippet":"npx @dlazy/cli@1.2.3 <command>"},{"language":"bash","snippet":"# Generate an image and feed its url straight into image-to-video\ndlazy seedream-4.5 --prompt \"a red fox in snow\" \\\n  | dlazy kling-v3 --image - --prompt \"fox starts running\"\n\n# Generate an image, then add TTS narration over a still\ndlazy seedream-4.5 --prompt \"lighthouse at dawn\" \\\n  | dlazy qwen-tts --text \"Welcome to the coast.\" --image @0.url\n\n# Fan-out: pass every upstream output url into a batch step\ndlazy seedream-4.5 --prompt \"city skyline\" --n 4 \\\n  | dlazy superres --images @*"},{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When this skill is called, use dlazy <subcommand>.\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\nImage generation skill. Automatically selects the best dlazy CLI image model based on the prompt.\n\n## Trigger Keywords\n\n- generate image\n- draw picture\n- text to image\n\n## Authentication\n\nAll requests require a dLazy API key. The recommended way to authenticate is `dlazy login`:\n\n```bash\ndlazy login\n```\n\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\n\n### Alternative: Set the Key Manually\n\nIf you already have an API key, you can save it directly:\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\n\n### Getting Your API Key Manually\n\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. Copy the key shown in the API Key section\n\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\n\n\n\n\n## About & Provenance\n\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **Maintainer**: dlazyai\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\n- **Homepage**: [dlazy.com](https://dlazy.com)\n\nYou can install on demand without persisting a global binary by running:\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\n\n## How It Works\n\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\n\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-generate\",\n  \"version\": \"1.3.27\",\n  \"publishedAt\": 1791422039585\n}"},{"path":"skill-card.md","content":"## Description:\n\nSelects a dLazy image model based on the prompt and generates images through the dLazy CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to generate and refine images from text prompts or reference images with dLazy-hosted models.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and generation parameters are sent to dLazy's cloud service.\n\nMitigation: Avoid including sensitive information in prompts or parameters.\n\nRisk: Local media supplied as input can be uploaded to dLazy's media storage.\n\nMitigation: Review and authorize input files before supplying their paths.\n\nRisk: Login stores a dLazy API key locally.\n\nMitigation: Protect the local credential; rotate or revoke the key through the dLazy dashboard if needed.\n\nRisk: A global CLI installation persists on the user's system.\n\nMitigation: Use the pinned npx invocation if a persistent global install is not desired.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-generate)\n- [dLazy CLI package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy CLI repository linked in skill metadata](https://github.com/dlazy-ai/cli)\n- [dLazy API key dashboard](https://dlazy.com/dashboard/organization/api-key)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Image URLs, Guidance]\n\n**Output Format:** [Markdown guidance and CLI JSON responses with hosted image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Generated media is hosted by dLazy.]\n\n## Skill Version(s):\n\n1.3.27 (source: ClawHub release; artifact frontmatter says 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"SKILL-cn.md","content":"---\nname: dlazy-image-generate\nversion: 1.3.5\ndescription: \"图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，请自动选择对应的 dlazy 子命令执行。\"}}\n---\n\n# 图片生成 Image Generate\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\n\n\n\n\n\n\n\n\n图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。\n\n## Trigger Keywords /## 触发关键词\n\n- 生成图片\n- 画图\n- 文生图\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n\n\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\n\n## 命令间管道 (Piping)\n\n每次 `dlazy` 调用都会向 stdout 输出一个 JSON 信封。任意参数都可以使用 **管道引用** 直接从上游命令的信封里取值，避免手工复制 URL。\n\n| 引用语法              | 含义                                                            |\n| --------------------- | --------------------------------------------------------------- |\n| `-`                   | 上游为该字段提供的自然值（标量或数组按字段类型自动选取）        |\n| `@N`                  | 第 N 个 output 的主值（如 `@0` 为第一个 output 的 url）         |\n| `@N.<jsonpath>`       | 进入第 N 个 output 的字段（`@0.url`, `@1.meta.fps`）            |\n| `@*`                  | 所有 output 的主值组成的数组                                    |\n| `@stdin`              | 上游完整的 JSON 信封                                            |\n| `@stdin:<jsonpath>`   | 在完整信封上做 jsonpath（`@stdin:result.outputs[0].url`）       |\n\n### 示例\n\n```bash\n# 文生图后直接把图喂给图生视频\ndlazy seedream-4.5 --prompt \"雪地里的红狐\" \\\n  | dlazy kling-v3 --image - --prompt \"狐狸开始奔跑\"\n\n# "}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1278,"uniquenessScore":42,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T04:54:53.415Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T04:54:53.415Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:16:36.403Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}