{"id":"e11d36f0-a8de-453a-ac50-a88f82192cf8","entityType":"agent","slug":"clawhub-cellcog-image-generation-cellcog","name":"Image Generation","canonicalUrl":"https://www.xpersona.co/agent/clawhub-cellcog-image-generation-cellcog","canonicalPath":"/agent/clawhub-cellcog-image-generation-cellcog","generatedAt":"2026-10-09T15:11:57.308Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T01:50:09.587Z","emptyReason":null},"description":"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models. Skill: Image Generation Owner: cellcog Summary: AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models. Tags: latest:1.0.17 Version history: v1.0.17 | 2026-08-24T02:01:22","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 16.4K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s176q1btpn094ats9b4f9hgfwx83knpk:image-generation-cellcog","sourceUrl":"https://clawhub.ai/cellcog/image-generation-cellcog","homepage":"https://clawhub.ai/cellcog/skills/image-generation-cellcog","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/cellcog/image-generation-cellcog","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/cellcog/skills/image-generation-cellcog","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":84,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation,"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T01:50:09.587Z","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":"2026-10-09T01:50:09.587Z","emptyReason":null},"stars":null,"forks":null,"downloads":16365,"packageName":null,"latestVersion":"1.0.17","tractionLabel":"16.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T01:50:09.587Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T01:50:09.587Z","lastCrawledAt":"2026-10-09T01:50:09.587Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T01:50:09.587Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.17","createdAt":"2026-08-24T02:01:22.462Z","changelog":"Content updated.","fileCount":3,"zipByteSize":5258},{"version":"1.0.16","createdAt":"2026-08-24T01:45:42.409Z","changelog":"Content updated.","fileCount":3,"zipByteSize":5190},{"version":"1.0.15","createdAt":"2026-08-03T06:06:04.088Z","changelog":"Content updated.","fileCount":3,"zipByteSize":5472},{"version":"1.0.14","createdAt":"2026-08-02T20:46:59.752Z","changelog":"Display title updated.","fileCount":3,"zipByteSize":5483},{"version":"1.0.13","createdAt":"2026-07-17T03:41:14.456Z","changelog":"- Skill name changed from \"image-cog\" to \"image-generation-cellcog\" - Updated description and documentation to reflect the new skill name and purpose - Removed the skill-card.md file - No changes to usage instructions, model capabilities, or sample prompts","fileCount":3,"zipByteSize":5439},{"version":"1.0.12","createdAt":"2026-04-23T06:18:58.679Z","changelog":"- Added environment and binary requirements to metadata: `python3` and `CELLCOG_API_KEY` are now specified as dependencies. - No functional or user-facing changes; documentation metadata improved for deployment clarity.","fileCount":3,"zipByteSize":5458},{"version":"1.0.11","createdAt":"2026-04-14T17:32:28.816Z","changelog":"- Expanded description to highlight support for brand assets, stickers, comics, and GIFs. - Clarified agent usage instructions: now specifies \"All agents except OpenClaw\" for one code sample. - No changes to code, features, or major usage – documentation and wording improvements only.","fileCount":2,"zipByteSize":4279},{"version":"1.0.10","createdAt":"2026-04-13T01:00:57.111Z","changelog":"- Revised and expanded the skill's description for greater clarity and detail. - Updated SDK usage examples, including new agent provider options. - Improved and clarified image generation features, use cases, and example prompts. - Enhanced documentation for image specifications, styles, and recommended use cases. - Added instructions for both fire-and-forget and blocking agent modes.","fileCount":2,"zipByteSize":4247}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176q1btpn094ats9b4f9hgfwx83knpk:image-generation-cellcog","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-cellcog-image-generation-cellcog/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T15:11:57.304Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-cellcog-image-generation-cellcog/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":"high","updatedAt":"2026-10-09T01:50:09.587Z","emptyReason":null},"readme":"Skill: Image Generation\n\nOwner: cellcog\n\nSummary: AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\n\nTags: latest:1.0.17\n\nVersion history:\n\nv1.0.17 | 2026-08-24T02:01:22.462Z | user\n\nContent updated.\n\nv1.0.16 | 2026-08-24T01:45:42.409Z | user\n\nContent updated.\n\nv1.0.15 | 2026-08-03T06:06:04.088Z | user\n\nContent updated.\n\nv1.0.14 | 2026-08-02T20:46:59.752Z | user\n\nDisplay title updated.\n\nv1.0.13 | 2026-07-17T03:41:14.456Z | auto\n\n- Skill name changed from \"image-cog\" to \"image-generation-cellcog\"\n- Updated description and documentation to reflect the new skill name and purpose\n- Removed the skill-card.md file\n- No changes to usage instructions, model capabilities, or sample prompts\n\nv1.0.12 | 2026-04-23T06:18:58.679Z | auto\n\n- Added environment and binary requirements to metadata: `python3` and `CELLCOG_API_KEY` are now specified as dependencies.\n- No functional or user-facing changes; documentation metadata improved for deployment clarity.\n\nv1.0.11 | 2026-04-14T17:32:28.816Z | auto\n\n- Expanded description to highlight support for brand assets, stickers, comics, and GIFs.\n- Clarified agent usage instructions: now specifies \"All agents except OpenClaw\" for one code sample.\n- No changes to code, features, or major usage – documentation and wording improvements only.\n\nv1.0.10 | 2026-04-13T01:00:57.111Z | auto\n\n- Revised and expanded the skill's description for greater clarity and detail.\n- Updated SDK usage examples, including new agent provider options.\n- Improved and clarified image generation features, use cases, and example prompts.\n- Enhanced documentation for image specifications, styles, and recommended use cases.\n- Added instructions for both fire-and-forget and blocking agent modes.\n\nv1.0.9 | 2026-04-12T23:35:36.714Z | auto\n\n- Shortened and clarified the skill description for improved readability.\n- Streamlined usage instructions, separating OpenClaw and other agents.\n- Removed redundant and verbose onboarding and prerequisite information.\n- Kept all key examples, model details, image types, and prompt tips intact.\n- No changes to core functionality or capabilities; documentation update only.\n\nv1.0.8 | 2026-04-08T05:58:07.920Z | auto\n\n**image-cog v1.0.8 changelog**\n\n- Completely overhauled documentation in SKILL.md for clarity, use cases, and guidance.\n- New sections detailing available models (Gemini 3.1 Flash, GPT Image 1.5, Recraft) and when each is used.\n- Expanded examples for single images, product photography, sets, character consistency, and reference-based generation.\n- Added practical table summaries for aspect ratios, formats, and when to use agent team mode.\n- Improved prompt-writing tips and concrete prompt samples to help users get better results.\n\nv1.0.7 | 2026-04-06T05:07:22.184Z | auto\n\n**Summary: Major documentation and feature list update for broader capabilities.**\n\n- Expanded description and examples for image editing, vector, icon, and transparent background support.\n- Output formats clarified: PNG, JPG, WebP, SVG, with per-model best-use notes.\n- New section on internal model routing and reference image handling.\n- Added chat mode recommendations for single versus batch/multi-image scenarios.\n- Linked to related skills for branding, memes, 3D, GIF, and sticker generation.\n- Broader and clearer language for use cases and feature highlights.\n\nv1.0.6 | 2026-04-03T01:43:37.569Z | auto\n\n- Added guidance on using OpenClaw \"fire-and-forget\" agent sessions for long image tasks\n- Clarified usage of `notify_session_key` and agent differences in code examples\n- Improved SDK usage instructions and removed references to deprecated delivery modes\n- No changes to skill functionality or API, documentation only\n\nv1.0.5 | 2026-04-03T00:07:54.605Z | auto\n\n- Updated documentation to clarify quick start and SDK usage.\n- Shortened and simplified the code example for starting image generation.\n- Added direction to consult the cellcog skill for full API/details.\n- No changes to skill features or logic; documentation only.\n\nv1.0.4 | 2026-03-27T04:17:28.415Z | auto\n\n- Expanded description to highlight image-to-image, photo editing, and social media content generation.\n- Added supported operating systems and a homepage link to metadata.\n- Improved clarity in usage instructions and feature lists.\n- Strengthened emphasis on multi-model capabilities and routing.\n- Updated skill documentation for broader and clearer coverage of features.\n\nv1.0.3 | 2026-03-19T02:55:15.289Z | user\n\n**Now supports multi-model image generation, with automatic provider routing for different image tasks.**\n\n- Added a new section detailing which image generation models are used and their roles: Nano Banana 2 (default), GPT Image 1.5 (for transparent images), and Recraft (vector/icon generation).\n- Clarified that CellCog agents intelligently select the best model for your request, and users can request a specific model in the prompt.\n- No API pattern or usage changes.\n- All other documentation remains unchanged except for new model explanation.\n\nv1.0.2 | 2026-02-11T01:42:50.371Z | user\n\n- Added explicit author (CellCog) and dependencies ([cellcog]) metadata to skill manifest.\n- Clarified prerequisite to require the `cellcog` skill (previously “CellCog mothership skill”).\n- Minor improvements to formatting and dependency instructions for clarity.\n- No changes to feature set or functionality.\n\nv1.0.1 | 2026-02-05T05:51:01.435Z | auto\n\n- Added an emoji to the skill metadata for improved identification.\n- Updated example usage for image generation to show the new fire-and-forget pattern using `create_chat` (v1.0+).\n- Clarified SDK setup instructions and removed references to the deprecated `sessions_spawn` pattern.\n- Small documentation improvements for clarity and accuracy.\n\nv1.0.0 | 2026-02-04T03:40:04.659Z | user\n\n- Initial release of image-cog skill: AI image generation powered by CellCog.\n- Supports creation of single images, editing, style transfer, consistent character sets, and product photography.\n- Enables reference-based images, sets of related images, style matching, and composition-based generation.\n- Integrates with CellCog mothership skill for setup and API calls.\n- Provides detailed documentation on prompt patterns, image specifications (aspect ratios, sizes, styles), and usage tips.\n- Includes example prompts for professional use cases and guidance for both simple and complex image generation workflows.\n\nArchive index:\n\nArchive v1.0.17: 3 files, 5258 bytes\n\nFiles: skill-card.md (1995b), SKILL.md (8117b), _meta.json (144b)\n\nFile v1.0.17:SKILL.md\n\n---\nname: image-generation-cellcog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\n    requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Generation - AI Image Creation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## Choosing Mode & Tier\n\n| Scenario | Recommended |\n|----------|-------------|\n| Single images, edits, small sets | `chat_mode=\"agent\"` (defaults to the `\"flash\"` tier) |\n| Brand-critical campaigns, large coordinated sets | `chat_mode=\"agent\", chat_tier=\"max\"` |\n\n**The flash tier is the default and handles most image generation well** — fast and economical. **Upgrade to `chat_tier=\"max\"`** when quality disappoints or the work is genuinely complex: just re-run the same prompt with `chat_tier=\"max\"`.\n\nAgent Team (`chat_mode=\"team\"`) is reserved for deep research — don't use it for image generation.\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\n**Claude Code, Cursor, Codex + 70 more agents:** `npx skills add cellcog/skills --skill cellcog`\n**OpenClaw:** `openclaw skills install @cellcog/cellcog`\n**CellCog plugin users:** run `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool)\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.17:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.17\",\n  \"publishedAt\": 1787536882462\n}\n\nFile v1.0.17:skill-card.md\n\n## Description:\n\nAI image generation and photo editing powered by CellCog, including text-to-image, image editing, consistent characters, product photography, reference-based generation, style transfer, image sets, social visuals, brand assets, stickers, comics, and GIFs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cellcog](https://clawhub.ai/user/cellcog)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to create and edit professional images through CellCog, including campaign visuals, product photography, consistent characters, reference-based images, and social media assets.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, uploads, reference images, and generated tasks may be processed by CellCog as a third-party service.\n\nMitigation: Avoid sending secrets, private documents, regulated data, or unauthorized reference images unless organizational policy permits CellCog processing.\n\nRisk: Install examples use unpinned package or skill installation commands.\n\nMitigation: Use official CellCog or OpenClaw sources and pin versions for production deployments.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/cellcog/skills/image-generation-cellcog)\n- [CellCog Homepage](https://cellcog.ai)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with Python and shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May produce prompts and instructions that call the CellCog API using CELLCOG_API_KEY.]\n\n## Skill Version(s):\n\n1.0.17 (source: server 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\nArchive v1.0.16: 3 files, 5190 bytes\n\nFiles: skill-card.md (1855b), SKILL.md (8100b), _meta.json (144b)\n\nFile v1.0.16:SKILL.md\n\n---\nname: image-generation-cellcog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\n    requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Generation - AI Image Creation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## Choosing Mode & Tier\n\n| Scenario | Recommended |\n|----------|-------------|\n| Single images, edits, small sets | `chat_mode=\"agent\"` (defaults to the `\"flash\"` tier) |\n| Brand-critical campaigns, large coordinated sets | `chat_mode=\"agent\", chat_tier=\"max\"` |\n\n**The flash tier is the default and handles most image generation well** — fast and economical. **Upgrade to `chat_tier=\"max\"`** when quality disappoints or the work is genuinely complex: just re-run the same prompt with `chat_tier=\"max\"`.\n\nAgent Team (`chat_mode=\"team\"`) is reserved for deep research — don't use it for image generation.\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\n**Claude Code, Cursor, Codex + 70 more agents:** `npx skills add cellcog/skills --skill cellcog`\n**OpenClaw:** `clawhub install cellcog`\n**CellCog plugin users:** run `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool)\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.16:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.16\",\n  \"publishedAt\": 1787535942409\n}\n\nFile v1.0.16:skill-card.md\n\n## Description:\n\nAI image generation and photo editing powered by CellCog for text-to-image creation, image editing, consistent characters, product photography, reference-based generation, style transfer, and campaign image sets.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cellcog](https://clawhub.ai/user/cellcog)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to create or edit images through CellCog, including single images, brand assets, product visuals, social media sets, reference-based generations, and consistent character series.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Referenced or uploaded images may be processed by CellCog during cloud-based generation or editing.\n\nMitigation: Use the skill only when CellCog processing is intended, and avoid uploading confidential, regulated, proprietary, or personal images unless authorized and comfortable with CellCog handling them.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/cellcog/skills/image-generation-cellcog)\n- [CellCog homepage](https://cellcog.ai)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with Python and shell command snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May reference CellCog image-generation requests, uploaded or referenced images, and the CELLCOG_API_KEY environment variable.]\n\n## Skill Version(s):\n\n1.0.16 (source: server release evidence)\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\nArchive v1.0.15: 3 files, 5472 bytes\n\nFiles: skill-card.md (2162b), SKILL.md (8668b), _meta.json (144b)\n\nFile v1.0.15:SKILL.md\n\n---\nname: image-generation-cellcog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\n    requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Generation - AI Image Creation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\n**Claude Code, Cursor, Codex + 70 more agents:** `npx skills add cellcog/skills --skill cellcog`\n**OpenClaw:** `clawhub install cellcog`\n**CellCog plugin users:** run `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool)\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.15:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.15\",\n  \"publishedAt\": 1785737164088\n}\n\nFile v1.0.15:skill-card.md\n\n## Description: <br>\nAI image generation and photo editing powered by CellCog for text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, social media visuals, brand assets, stickers, comics, GIFs, and other professional image creation workflows. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[cellcog](https://clawhub.ai/user/cellcog) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, creators, and agents use this skill to generate and edit images through CellCog, including product photography, consistent character sets, reference-based images, brand assets, and social media visuals. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Image prompts, uploaded images, reference images, and related task data are sent to external services. <br>\nMitigation: Use only data that the organization has approved for CellCog and its model providers; avoid confidential, regulated, personal, or proprietary images unless that data flow is authorized. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill listing](https://clawhub.ai/cellcog/skills/image-generation-cellcog) <br>\n- [CellCog homepage](https://cellcog.ai) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance, files] <br>\n**Output Format:** [Markdown guidance with Python examples, shell commands, configuration details, and generated image files returned through CellCog.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires python3 and CELLCOG_API_KEY. Prompts, uploaded images, reference images, and related task data may be sent to CellCog and its model providers.] <br>\n\n## Skill Version(s): <br>\n1.0.15 (source: server-resolved release evidence) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.0.14: 3 files, 5483 bytes\n\nFiles: skill-card.md (2210b), SKILL.md (8593b), _meta.json (144b)\n\nFile v1.0.14:SKILL.md\n\n---\nname: image-generation-cellcog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\n    requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Generation - AI Image Creation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.14:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.14\",\n  \"publishedAt\": 1785703619752\n}\n\nFile v1.0.14:skill-card.md\n\n## Description: <br>\nAI image generation and photo editing powered by CellCog for text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, social media visuals, brand assets, stickers, comics, GIFs, and professional image creation with multiple AI models. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[cellcog](https://clawhub.ai/user/cellcog) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and external users use this skill to prompt CellCog agents for professional image generation, image editing, character-consistent image sets, product photography, campaign visuals, and reference-based creative work. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Prompts and uploaded reference images may be sent to CellCog and its model providers. <br>\nMitigation: Use the skill only with content approved for that external service path, and avoid sensitive prompts or images unless the user's data policy permits it. <br>\nRisk: The skill requires a CELLCOG_API_KEY. <br>\nMitigation: Store the API key in the agent environment or a secret manager and do not commit it to skill files, prompts, or logs. <br>\n\n\n## Reference(s): <br>\n- [CellCog homepage](https://cellcog.ai) <br>\n- [ClawHub skill page](https://clawhub.ai/cellcog/skills/image-generation-cellcog) <br>\n- [CellCog publisher profile](https://clawhub.ai/user/cellcog) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Code, Shell commands, Configuration instructions] <br>\n**Output Format:** [Markdown with Python and shell code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Guides the agent to use CellCog with CELLCOG_API_KEY and the cellcog Python dependency.] <br>\n\n## Skill Version(s): <br>\n1.0.14 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.0.13: 3 files, 5439 bytes\n\nFiles: skill-card.md (2110b), SKILL.md (8593b), _meta.json (144b)\n\nFile v1.0.13:SKILL.md\n\n---\nname: image-generation-cellcog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\n    requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Generation - AI Image Creation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.13:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.13\",\n  \"publishedAt\": 1784259674456\n}\n\nFile v1.0.13:skill-card.md\n\n## Description: <br>\nAI image generation and photo editing powered by CellCog for text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, social media visuals, brand assets, stickers, comics, and GIFs. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[nitishgargiitd](https://clawhub.ai/user/nitishgargiitd) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and creative teams use this skill to ask an agent to generate or edit images through CellCog, including product visuals, social media assets, reference-based images, and consistent character sets. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Prompts and uploaded or reference images are sent to an external AI service and may be routed to model providers. <br>\nMitigation: Avoid submitting confidential, regulated, or sensitive personal material unless that use is approved for the deployment environment. <br>\nRisk: Generated or edited images may be incorrect, misleading, or unsuitable for a brand or regulated use case. <br>\nMitigation: Review generated image outputs before publication or downstream use. <br>\n\n\n## Reference(s): <br>\n- [CellCog](https://cellcog.ai) <br>\n- [ClawHub skill page](https://clawhub.ai/nitishgargiitd/skills/image-generation-cellcog) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, code, shell commands] <br>\n**Output Format:** [Markdown with Python and shell command examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May produce instructions for image generation prompts, reference-image workflows, SDK calls, and CellCog setup.] <br>\n\n## Skill Version(s): <br>\n1.0.13 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.0.12: 3 files, 5458 bytes\n\nFiles: skill-card.md (2062b), SKILL.md (8573b), _meta.json (144b)\n\nFile v1.0.12:SKILL.md\n\n---\nname: image-cog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\n    requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Cog - AI Image Generation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.12:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.12\",\n  \"publishedAt\": 1776925138679\n}\n\nFile v1.0.12:skill-card.md\n\n## Description: <br>\nAI image generation and photo editing powered by CellCog for text-to-image, image editing, consistent characters, product photography, reference-based generation, style transfer, social media visuals, brand assets, stickers, comics, GIFs, and other professional image creation tasks. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[nitishgargiitd](https://clawhub.ai/user/nitishgargiitd) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, designers, marketers, and other external users use this skill to ask an agent to create or edit images through CellCog, including single images, cohesive image sets, product visuals, character-consistent scenes, and reference-based generations. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Review before execution as proposals could introduce incorrect or misleading guidance into skills. <br>\nMitigation: Review and scan skill before deployment. <br>\n\n## Reference(s): <br>\n- [Image Cog on ClawHub](https://clawhub.ai/nitishgargiitd/skills/image-cog) <br>\n- [CellCog](https://cellcog.ai) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Code, Shell commands, Guidance] <br>\n**Output Format:** [Markdown with Python and shell command examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires python3, the cellcog Python package, and CELLCOG_API_KEY. Security guidance: use a revocable API key and avoid submitting private photos, confidential brand assets, regulated data, or sensitive prompts unless CellCog's provider routing and data-handling terms are acceptable.] <br>\n\n## Skill Version(s): <br>\n1.0.12 (source: server evidence release.version) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.0.11: 2 files, 4279 bytes\n\nFiles: SKILL.md (8508b), _meta.json (144b)\n\nFile v1.0.11:SKILL.md\n\n---\nname: image-cog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Cog - AI Image Generation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\nRun `/cellcog-setup` (or `/cellcog:cellcog-setup` depending on your tool) to install and authenticate.\n**OpenClaw users:** Run `clawhub install cellcog` instead.\n**Manual setup:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.11:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.11\",\n  \"publishedAt\": 1776187948816\n}\n\nArchive v1.0.10: 2 files, 4247 bytes\n\nFiles: SKILL.md (8438b), _meta.json (144b)\n\nFile v1.0.10:SKILL.md\n\n---\nname: image-cog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Cog - AI Image Generation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**Cursor / Claude Code / Other agents (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\n**Cursor:** Run `/cellcog-setup` to install and authenticate.\n**OpenClaw:** Run `clawhub install cellcog` for SDK setup.\n**Other agents:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.10:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.10\",\n  \"publishedAt\": 1776042057111\n}\n\nArchive v1.0.9: 2 files, 4191 bytes\n\nFiles: SKILL.md (8303b), _meta.json (143b)\n\nFile v1.0.9:SKILL.md\n\n---\nname: image-cog\ndescription: \"Powered by CellCog. Image generation and editing. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, and image sets. Multiple aspect ratios, styles, and transparent backgrounds.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Cog - AI Image Generation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**Cursor / Claude Code / Other agents (blocks until done):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\n---\n\n## If CellCog is not installed\n\n**Cursor:** Run `/cellcog-setup` to install and authenticate.\n**OpenClaw:** Run `clawhub install cellcog` for SDK setup.\n**Other agents:** `pip install -U cellcog` and set `CELLCOG_API_KEY`. See the **cellcog** skill for SDK reference.\n\nFile v1.0.9:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.9\",\n  \"publishedAt\": 1776036936714\n}\n\nArchive v1.0.8: 2 files, 4145 bytes\n\nFiles: SKILL.md (8276b), _meta.json (143b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: image-cog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n\n# Image Cog - AI Image Generation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n---\n\n## Prerequisites\n\nThis skill requires the `cellcog` skill for SDK setup and API calls.\n\n```bash\nclawhub install cellcog\n```\n\n**Read the cellcog skill first** for SDK setup. This skill shows you what's possible.\n\n**OpenClaw agents (fire-and-forget — recommended for long tasks):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",  # OpenClaw only\n    task_label=\"my-task\",\n    chat_mode=\"agent\",  # See cellcog skill for all modes\n)\n```\n\n**All other agents (blocks until done):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\nSee the **cellcog** mothership skill for complete SDK API reference — delivery modes, timeouts, file handling, and more.\n\n---\n\n## What Models Do We Use\n\n| Model | Provider | Primary Use |\n|-------|----------|-------------|\n| **Nano Banana 2** (Gemini 3.1 Flash Image) | Google | Default image generation — photorealistic scenes, complex compositions, text rendering, multi-turn character consistency |\n| **GPT Image 1.5** | OpenAI | Transparent background images — logos, stickers, product cutouts, overlay graphics |\n| **Recraft** | Recraft AI | Scalable vector illustrations (SVG) and icon generation |\n\n**Nano Banana 2** is the default model for all image generation. CellCog's agents intelligently route to other models when the task calls for it — for example, transparent PNGs are automatically handled by GPT Image 1.5, and vector/icon requests go to Recraft. If you'd prefer a specific model, just mention it in your prompt (e.g., *\"use ChatGPT/OpenAI image generation\"*).\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur character, then show them: 1) At their desk coding, 2) Presenting to investors, 3) Celebrating a product launch\"\n- **Mascot Variations**: \"Design a friendly robot mascot, then create versions for: welcome page, error page, success message, loading screen\"\n- **Story Sequences**: \"Create a main character, then illustrate them in 5 scenes of a journey\"\n\nThis is powerful for:\n- Comic strips and storyboards\n- Marketing campaigns with consistent characters\n- Video frame generation\n- Brand mascots across contexts\n\n### Product Photography Style\n\nProfessional product visuals:\n\n- **Hero Shots**: \"Product hero shot of a smartwatch on a gradient background\"\n- **Lifestyle Shots**: \"Smartphone being used by a person in a modern living room\"\n- **Flat Lays**: \"Flat lay of skincare products with botanical elements\"\n- **360 Views**: \"Multiple angles of a leather handbag - front, side, back, detail\"\n\n### Sets of Related Images\n\nMultiple cohesive images for campaigns or collections:\n\n- **Social Media Sets**: \"5 Instagram post images for a fitness brand - consistent style, varied content\"\n- **Website Heroes**: \"3 hero images for a SaaS landing page - professional, modern, tech-focused\"\n- **Ad Variations**: \"4 versions of a product ad with different backgrounds and moods\"\n- **Blog Illustrations**: \"Set of 6 illustrations for a blog post about productivity tips\"\n\n### Reference-Based Generation\n\nUse existing images as references for style, character, or composition:\n\n- **Style Matching**: \"Create a new image in the same artistic style as this reference\"\n- **Character Consistency**: \"Using this person as reference, create a new scene with them hiking\"\n- **Brand Alignment**: \"Create product images matching this brand's visual style\"\n- **Composition Reference**: \"Create a similar composition but with different subjects\"\n\n---\n\n## Image Specifications\n\n| Aspect | Options |\n|--------|---------|\n| **Aspect Ratios** | 1:1 (square), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |\n| **Sizes** | 1K (~1024px), 2K (~2048px), 4K (~4096px) |\n| **Styles** | Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector |\n| **Formats** | PNG (default) |\n\n**Size recommendations:**\n- **1K**: Quick iterations, thumbnails, social media posts, drafts\n- **2K**: Standard web content, presentations, marketing materials\n- **4K**: Hero images, print materials, final deliverables where detail matters\n\n---\n\n## When to Use Agent Team Mode\n\nFor image generation, `chat_mode=\"agent team\"` is recommended for:\n- Complex scenes requiring multiple elements\n- Consistent character series\n- Reference-based generation requiring analysis\n- Sets of related images\n\nFor simple single images, `chat_mode=\"agent\"` can work faster.\n\n---\n\n## Example Image Prompts\n\n**Professional headshot:**\n> \"Create a professional headshot of a friendly Asian woman in her 30s, wearing a navy blazer, soft studio lighting, neutral gray background, confident but approachable expression. 1:1 square, 2K quality, photorealistic.\"\n\n**Product photography:**\n> \"Product shot of a premium wireless earbuds case, matte black finish, on a reflective dark surface with subtle blue accent lighting. Minimalist, high-end tech aesthetic. 4:3 landscape, 4K for hero image.\"\n\n**Consistent character set:**\n> \"Create a character: young Black male software developer, casual style with glasses, friendly demeanor. Then create 4 images:\n> 1. Working at a standing desk with multiple monitors\n> 2. In a video call meeting, explaining something\n> 3. At a coffee shop with laptop, thinking\n> 4. Celebrating with team, high-fiving\n> Keep the character exactly consistent across all images.\"\n\n**Social media set:**\n> \"Create 5 Instagram posts for a plant-based meal delivery service:\n> 1. Colorful Buddha bowl from above\n> 2. Happy person unpacking delivery\n> 3. Meal prep containers arranged neatly\n> 4. Close-up of fresh ingredients\n> 5. Before/after showing ingredients to finished dish\n> Style: bright, fresh, appetizing, consistent warm color grading. 1:1 square format.\"\n\n**Style transfer:**\n> \"Transform this uploaded photo of a city street into a Studio Ghibli anime style illustration. Keep the composition and elements but apply the characteristic Ghibli warmth, soft clouds, and whimsical details.\"\n\n---\n\n## Tips for Better Images\n\n1. **Be descriptive**: \"Woman in office\" is vague. \"Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light\" is better.\n\n2. **Specify style**: \"Photorealistic\", \"digital illustration\", \"watercolor\", \"minimalist vector\".\n\n3. **Describe lighting**: \"Soft natural light\", \"dramatic side lighting\", \"golden hour glow\", \"studio lighting\".\n\n4. **Include mood**: \"Professional and confident\", \"warm and inviting\", \"energetic and vibrant\".\n\n5. **Mention composition**: \"Rule of thirds\", \"centered symmetry\", \"close-up\", \"wide establishing shot\".\n\n6. **For consistency**: When creating character series, describe the character in detail first, then reference \"the same character\" in subsequent prompts.\n\nFile v1.0.8:_meta.json\n\n{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.8\",\n  \"publishedAt\": 1775627887920\n}","readmeExcerpt":"Skill: Image Generation Owner: cellcog Summary: AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models. Tags: latest:1.0.17 Version history: v1.0.17 | 2026-08-24T02:01:22","codeSnippets":[],"executableExamples":[{"language":"python","snippet":"result = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)"},{"language":"python","snippet":"from cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])"},{"language":"python","snippet":"result = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)"},{"language":"python","snippet":"from cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])"},{"language":"python","snippet":"result = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)"},{"language":"python","snippet":"from cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: image-generation-cellcog\ndescription: \"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models.\"\nmetadata:\n  openclaw:\n    emoji: \"🎨\"\n    os: [darwin, linux, windows]\n    requires:\n      bins: [python3]\n      env: [CELLCOG_API_KEY]\nauthor: CellCog\nhomepage: https://cellcog.ai\ndependencies: [cellcog]\n---\n# Image Generation - AI Image Creation Powered by CellCog\n\nCreate professional images with AI - from single images to consistent character sets to product photography.\n\n## How to Use\n\nFor your first CellCog task in a session, read the **cellcog** skill for the full SDK reference — file handling, chat modes, timeouts, and more.\n\n**OpenClaw (fire-and-forget):**\n```python\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\n```\n\n**All agents except OpenClaw (blocks until done):**\n```python\nfrom cellcog import CellCogClient\nclient = CellCogClient(agent_provider=\"openclaw|cursor|claude-code|codex|...\")\nresult = client.create_chat(\n    prompt=\"[your task prompt]\",\n    task_label=\"my-task\",\n    chat_mode=\"agent\",\n)\nprint(result[\"message\"])\n```\n\n\n---\n\n## Choosing Mode & Tier\n\n| Scenario | Recommended |\n|----------|-------------|\n| Single images, edits, small sets | `chat_mode=\"agent\"` (defaults to the `\"flash\"` tier) |\n| Brand-critical campaigns, large coordinated sets | `chat_mode=\"agent\", chat_tier=\"max\"` |\n\n**The flash tier is the default and handles most image generation well** — fast and economical. **Upgrade to `chat_tier=\"max\"`** when quality disappoints or the work is genuinely complex: just re-run the same prompt with `chat_tier=\"max\"`.\n\nAgent Team (`chat_mode=\"team\"`) is reserved for deep research — don't use it for image generation.\n\n## What Images You Can Create\n\n### Single Image Creation\n\nGenerate any image from a text description:\n\n- **Scenes**: \"A cozy coffee shop interior with morning light streaming through windows\"\n- **Portraits**: \"Professional headshot of a confident woman in business attire\"\n- **Products**: \"Minimalist product shot of a white sneaker on a marble surface\"\n- **Abstract**: \"Geometric abstract art in navy and gold\"\n- **Nature**: \"Misty mountain landscape at sunrise with a lone hiker\"\n\n### Image Editing\n\nTransform existing images:\n\n- **Style Transfer**: \"Transform this photo into a watercolor painting\"\n- **Background Removal**: \"Remove the background and place on a clean white backdrop\"\n- **Enhancement**: \"Enhance the colors and add dramatic lighting\"\n- **Modification**: \"Change the person's outfit to a red dress\"\n\n### Consistent Characters\n\nCreate multiple images of the same character in different scenarios:\n\n- **Character Series**: \"Create a tech entrepreneur charac"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7a96cj9q65e0bhmzahv790en80ffqm\",\n  \"slug\": \"image-generation-cellcog\",\n  \"version\": \"1.0.17\",\n  \"publishedAt\": 1787536882462\n}"},{"path":"skill-card.md","content":"## Description:\n\nAI image generation and photo editing powered by CellCog, including text-to-image, image editing, consistent characters, product photography, reference-based generation, style transfer, image sets, social visuals, brand assets, stickers, comics, and GIFs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[cellcog](https://clawhub.ai/user/cellcog)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to create and edit professional images through CellCog, including campaign visuals, product photography, consistent characters, reference-based images, and social media assets.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, uploads, reference images, and generated tasks may be processed by CellCog as a third-party service.\n\nMitigation: Avoid sending secrets, private documents, regulated data, or unauthorized reference images unless organizational policy permits CellCog processing.\n\nRisk: Install examples use unpinned package or skill installation commands.\n\nMitigation: Use official CellCog or OpenClaw sources and pin versions for production deployments.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/cellcog/skills/image-generation-cellcog)\n- [CellCog Homepage](https://cellcog.ai)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with Python and shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May produce prompts and instructions that call the CellCog API using CELLCOG_API_KEY.]\n\n## Skill Version(s):\n\n1.0.17 (source: server 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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models. Skill: Image Generation Owner: cellcog Summary: AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs. Professional image creation with multiple AI models. Tags: latest:1.0.17 Version history: v1.0.17 | 2026-08-24T02:01:22","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1170,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T01:50:09.587Z","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":"2026-10-09T01:50:09.587Z","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":"2026-10-09T15:11:57.308Z","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"}]}}}