LinkFoxAI
调用 LinkFox AI 开放平台 AI 作图/视频 API(换模特、抠图、扩图、场景裂变、智能修图、套图、姿势裂变、带货口播、图转视频等)。适用场景:(1) AI 任务创建与结果轮询,(2) 通过 api-call 调用任意开放平台接口,(3) 素材连通性测试。 Skill: LinkFoxAI Owner: linkfox-ai Summary: 调用 LinkFox AI 开放平台 AI 作图/视频 API(换模特、抠图、扩图、场景裂变、智能修图、套图、姿势裂变、带货口播、图转视频等)。适用场景:(1) AI 任务创建与结果轮询,(2) 通过 api-call 调用任意开放平台接口,(3) 素材连通性测试。 Tags: latest:1.5.1 Version history: v1.5.1 | 2026-06-12T06:15:20.181Z | user 新增:视频复刻 video-reclone,支持 SEED、SEED_FAST 两个模型进行视频复刻生成。 调整:商品套图/服装套图支持「无字模式」--no-text,生成纯画面、不带文案排版。 调整:图转视频/带货口播新增支持SEED_FAST模型生成 v1.5.0 | 2026-05-07T12:44:16.506Z | u
Rank
62
Safety
84
Downloads
2.7k
Updated
Oct 9, 2026
Version
1.5.1
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 2.7K downloads reported by the source. Last updated 10/9/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 9, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 9, 2026
- Adoption signal
- 2.7K downloadsadoption · observed Oct 9, 2026
- Latest release
- 1.5.1release · observed Jun 12, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s171g8b6m2khwdy9ye8bxj0wx183vd4z:linkfox-ai- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- 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: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-linkfox-ai-linkfox-ai/snapshot"
Documentation
CLAWHUB
143,565 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
---
name: linkfoxai
description: "调用 LinkFox AI 开放平台 AI 作图/视频 API(换模特、抠图、扩图、场景裂变、智能修图、套图、姿势裂变、带货口播、图转视频等)。适用场景:(1) AI 任务创建与结果轮询,(2) 通过 api-call 调用任意开放平台接口,(3) 素材连通性测试。"
metadata: {"clawdbot":{"emoji":"🦊","requires":{"env":["LINKFOXAI_API_KEY"]}}}
---
# LinkFoxAI - LinkFox AI 开放平台 Skill
LinkFoxAI 让 OpenClaw 调用 LinkFox AI 开放平台 AI 作图/视频能力:换模特、自动抠图、场景裂变、智能扩图、高清放大、消除笔、智能修图、商品套图、服装套图、姿势裂变、带货口播、图转视频等。
## 配置
1. **获取凭证**:注册 [紫鸟开放平台](https://open.ziniao.com),认证开发者并创建 LinkFox 卖家应用,然后在 [linkfox.com/team/api-guide](https://www.linkfox.com/team/api-guide) 将应用绑定到团队,获取 API Key。
2. **环境变量**:`LINKFOXAI_API_KEY`(单一 API Key,配置一个 Key 即可调用全部接口)
3. **自定义 Base URL**(可选):默认 `https://sbappstoreapi.ziniao.com/openapi-router`。若无固定 IP,设置 `LINKFOXAI_BASE_URL=https://sbappstoreapi-proxy.linkfox.com` 并配置白名单。
## 必须使用 sessions_spawn 调度作图任务
AI 作图任务需要排队和生成时间(通常 10 秒 ~ 5 分钟,**极端情况下可能因服务端超时或队列积压导致单个任务耗时超过 30 分钟**)。**务必通过 `sessions_spawn` 将作图任务派发到子会话**,让主会话保持响应。脚本的 `--wait` 参数会自动轮询直到出结果。
### 超时处理策略(AI 自行判断)
当作图任务超时(`--timeout` 耗尽仍未返回结果)时,AI 应根据具体情况自主选择以下策略,无需等待用户指令:
1. **延长轮询时间**:将 `--timeout` 增大到 1800(30 分钟),`--interval` 建议 10~30 秒,适用于重要任务或用户明确愿意等待的场景。
2. **告知用户并继续后台等待**:向用户说明任务仍在生成中,预估剩余时间,并在后台子会话中继续轮询;完成后主动汇报结果。
3. **任务分拆重试**:若任务参数含多图(如 `--output-num 4`),可拆分为多个单图任务并行提交,降低单个任务超时概率。
4. **放弃并报错**:仅当用户明确要求快速返回、或超时时间已大幅超出合理范围(> 40 分钟)时,才终止轮询并告知用户稍后手动查询任务 ID。
> 默认建议:将 `sessions_spawn` 的 `runTimeoutSeconds` 设为 **1800**,`--timeout` 设为 **1700**,以覆盖绝大多数超时场景。仅在明确知道该类型任务通常很快时才缩小超时值。
### 标准调度模板
```
sessions_spawn:
task: |
Run: <skill>/scripts/linkfoxai.py change-model --wait --timeout 1700 \
--image-url "<模特原图>" --head-url "<头部图>" --output-num 4
解析输出 JSON,提取 resultList 中的图片 URL 汇报给用户。
如果 status=4(失败),报告 errorMsg。
如果超时仍未完成,告知用户任务 ID 以便后续手动查询。
label: "LinkFoxAI: AI 换模特"
mode: "run"
runTimeoutSeconds: 1800
cleanup: "keep"
```
### 并行调度多个独立任务
```
# 子任务 1
sessions_spawn:
task: "Run: <skill>/scripts/linkfoxai.py cutout --wait --timeout 1700 --image-url '<url>' --sub-type 1 ..."
label: "LinkFoxAI: 自动抠图"
mode: "run"
runTimeoutSeconds: 1800
# 子任务 2
sessions_spawn:
task: "Run: <skill>/scripts/linkfoxai.py scene-fission --wait --timeout 1700 --image-url '<url>' ..."
label: "LinkFoxAI: 场景裂变"
mode: "run"
runTimeoutSeconds: 1800
```
### 通用接口调用(api-call)
对于脚本没有专属命令的接口(如 AI 穿衣、商品替换、饰品文字等),使用 `api-call` 传入路径和 JSON body:
```
sessions_spawn:
task: |
Run: <skill>/scripts/linkfoxai.py api-call \
--path /linkfox-ai/image/v2/make/fittingRoom \
--body '{"upperOriginUrl":"<上衣图>","modelImageUrl":"<模特图>","outputNum":2}'
获取返回的 data.id,然后运行:
<skill>/scripts/linkfoxai.py poll --id <task_id> --timeout 1700
解析结果汇报给用户。如果超时仍未完成,告知用户任务 ID 以便后续手动查询。
label: "LinkFoxAI: AI 穿衣"
mode: "run"
runTimeoutSeconds: 1800
```
## 脚本命令一览
### 基础命令
| 命令 | 说明 |
|------|------|
| `material-list --type <1-10>` | 作图素材列表(可用于连通性测试) |
| `upload-base64 _meta.json
{
"ownerId": "kn7dmc1t4j28hem1twwyav85p182pb1j",
"slug": "linkfox-ai",
"version": "1.5.1",
"publishedAt": 1781244920181
}references/image-make.md
# AI 作图 / 视频 - 全部接口完整说明
本文档为 LinkFoxAI Skill 内置参考,涵盖开放平台 AI 作图/视频能力、完整参数与注意事项。
所有接口均为 **POST**,请求体 **Content-Type: application/json**,响应体 application/json。
---
## 一、通用作图流程
1. **可选**:调用「作图素材」获取预设素材地址(模特、场景等)。
2. **可选**:本地图片需先调用「图片上传」得到可访问 URL。
3. 调用具体作图接口,得到 **任务 ID**(`data.id`)。
4. 轮询「获取作图结果」直到 `data.status` 为 3(成功) 或 4(失败),取 `data.resultList[].url` 得到结果图。
5. 结果图为**临时地址,有效期约 8 小时**;过期后调用「刷新结果图片地址」传入**图片 ID**(`resultList[].id`,非任务 ID)获取新 URL。
**注意事项:**
- 用户图片需外网可访问、链接稳定,建议使用国内图床(阿里云 OSS、腾讯云 COS 等)。
- 作图素材地址通过「作图素材」接口获得,用作预设资源。
- 本地图片上传支持 base64 编码,无需单独传 OSS。
---
## 二、通用响应结构
所有作图创建任务接口的响应结构一致:
| 参数 | 说明 | 类型 |
|------|------|------|
| traceId | 链路 ID | string |
| code | 状态码,200 为成功 | string |
| msg | 成功/错误描述 | string |
| msgKey | 错误码,code 非 200 时存在 | string |
| data.id | 任务 ID(用于轮询结果) | number |
响应示例:
```json
{"traceId":"f6e0fe4f360f78445c2c5d52f2414dea","code":"200","msg":"成功","data":{"id":123456}}
```
---
## 三、作图素材
**路径**:`/linkfox-ai/image/v2/material/list`
**注意**:此接口可用于连通性测试,无需上传图片。
| 参数 | 说明 | 必填 | 类型 |
|------|------|------|------|
| type | 类型:1=AI换模特-预设模特,2=模特图通用-预设场景,3=AI换模特固定脸-预设模特,4=模特图通用-场景素材,5=AI穿衣姿势-上下装素材,6=AI穿衣姿势-连体衣素材,7=AI穿戴-模特素材,8=手持商品-姿势素材,9=姿势裂变素材,10=套图-排版素材 | 是 | string |
| pageNum | 页数,默认 1 | 否 | number |
| pageSize | 单页条数,默认 10 | 否 | number |
响应 data 含 list(url/name/tagList)、total、hasMore。
```json
{"type":"1"}
```
---
## 四、图片上传
### 4.1 base64 上传
**路径**:`/linkfox-ai/image/v2/uploadByBase64`
**注意**:全局 QPS 100(不分 IP 不分用户)。适用于没有图片存储服务或无法外网访问的场景。
| 参数 | 说明 | 必填 | 类型 |
|------|------|------|------|
| fileName | 文件名(带扩展名),支持 jpeg/jpg/png/webp | 是 | string |
| base64 | 图片 base64 编码,文件不超过 10MB,最长边不超过 4096 | 是 | string |
响应 data 含 viewUrl(上传后图片访问地址)。
### 4.2 生成上传地址(OSS 直传)
**路径**:`/linkfox-ai/image/v1/generateUploadUrl`
**注意**:QPS 由阿里控制,并发能力高于 base64 方式。
| 参数 | 说明 | 必填 | 类型 |
|------|------|------|------|
| fileName | 文件名(主要取后缀) | 是 | string |
响应 data 含 viewUrl(上传成功后可用地址)、policy(url/signature/policy/key/OSSAccessKeyId,用于客户端直传 OSS)。
---
## 五、获取作图结果
**路径**:`/linkfox-ai/image/v2/make/info`
**注意**:需轮询此接口直到 status 变为 3(成功)或 4(失败)。建议轮询间隔 3-5 秒。
| 参数 | 说明 | 必填 | 类型 |
|------|------|------|------|
| id | 作图任务 ID | 是 | number |
| format | 结果格式,目前仅支持 jpg | 否 | string |
响应 data:
| 字段 | 说明 | 类型 |
|------|------|------|
| id | 作图任务 ID | number |
| status | 1=排队中 2=生成中 3=成功 4=失败 | integer |
| errorCode | 错误码 | string |
| errorMsg | 错误描述 | string |
| resultList | 结果图片数组 | array |
| resultList[].id | **图片 ID**(用于刷新地址) | number |
| resultList[].status | 0=生成中 1=成功 2=失败 | integer |
| resultList[].url | 高清图临时地址(有效期 8 小时) | string |
| resultList[].width | 宽 | integer |
| resultList[].height | 高 | integer |
| resultList[].format | 格式 | string |
| resultList[].size | 大小(字节) | integer |
| resultList[].extendField | 扩展参数(如 maskUrl、requestId 等) | object |
---
## 六、刷新结果图片地址
**路径**:`/linkfox-ai/image/v2references/open-platform.md
# LinkFox AI 开放平台 - 接入与错误码
## 接入流程
1. 注册紫鸟开放平台:https://open.ziniao.com
2. 认证开发者,创建 LinkFox 卖家应用:https://open.ziniao.com/docSupport?docId=116
3. 将应用绑定到团队:https://www.linkfox.com/team/api-guide
4. 鉴权方式以官方文档为准:[API 调用指南 - 简单通用模式(推荐)](https://open.ziniao.com/docSupport?docId=233)
## API 基础地址
- 默认:`https://sbappstoreapi.ziniao.com/openapi-router`
- 路径前缀:`/linkfox-ai`
- 无固定 IP 时可使用代理:`https://sbappstoreapi-proxy.linkfox.com`(需配置白名单 IP:120.79.189.15)
## 响应外层结构
所有接口的响应均由开放平台包装了一层外层结构,实际业务数据在 `data` 字段中。
```json
{
"request_id": "abc123",
"code": 0,
"msg": "success",
"data": {
// 此处为业务接口的实际响应体
"traceId": "...",
"code": "200",
"msg": "成功",
"data": { /* 业务数据 */ }
}
}
```
| 字段 | 说明 |
|------|------|
| request_id | 开放平台请求 ID |
| code | 开放平台状态码,0 为成功 |
| msg | 开放平台消息 |
| data | 业务接口实际响应(内部有自己的 traceId/code/msg/data) |
即实际数据嵌套路径为:`响应.data.data`(外层 data 是开放平台包装,内层 data 是业务数据)。
## QPS / 限流说明
- **base64 上传接口** (`/linkfox-ai/image/v2/uploadByBase64`):全局限流 100 QPS。
- **其他接口**:默认无严格 QPS 限制,但建议单应用并发不超过 50 QPS。
- 触发限流时返回 HTTP 429 或开放平台错误码。
- 作图任务提交后需轮询 `make-info` 获取结果,建议轮询间隔 ≥ 3 秒。
## 错误码
| 错误码 | 描述 |
| --- | --- |
| ERR_FILED_VALIDATE | 参数校验异常 |
| ERR_VALIDATE_FAIL | 参数校验异常 |
| ERR_IMAGE_MAKE_AUDIT | 图片审核不通过 |
| ERR_IMAGE_MAKE_WILL_OUT | 作图点数不足 |
| ERR_FORBIDDEN | 没有ID权限,ID取错也有可能 |
| ERR_NOT_HAVE_TEAM_PRIVILEGE | 未绑定团队 |
| TEAM_PERMISSION_DISABLE_USER | 被禁用 |
| ERR_IMAGE_MAKE_COUNT_MAX | 生成中创建上限 |
| TEAM_PERMISSION_EXPIRE | 套餐已过期或者未购买套餐 |
更多说明见开放平台 https://open.ziniao.com 或本 skill 内 `references/image-make.md`。skill-card.md
## Description: LinkFoxAI lets an agent call the LinkFox AI open platform for image and video generation workflows, including model swaps, cutouts, image expansion, scene variation, product image sets, talking sales videos, image-to-video, task polling, generic API calls, and connectivity checks. This skill is ready for commercial/non-commercial use. ## Publisher: [linkfox-ai](https://clawhub.ai/user/linkfox-ai) ### License/Terms of Use: MIT-0 ## Use Case: Developers and external teams use this skill to connect an agent to LinkFox AI media-generation APIs, submit authenticated image or video jobs, poll for results, and return generated media URLs or API responses. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The skill gives an agent broad authenticated access to LinkFox AI APIs and media upload workflows. Mitigation: Use a scoped API key if available, protect LINKFOXAI_API_KEY, and review proposed api-call and upload-base64 commands before execution. Risk: Media, prompts, product data, and account credentials are sent to LinkFoxAI/Ziniao services. Mitigation: Install only when that data sharing is acceptable, and avoid uploading sensitive local files or private/person media without consent. Risk: Changing LINKFOXAI_BASE_URL can route authenticated requests away from the documented official hosts. Mitigation: Keep LINKFOXAI_BASE_URL on the documented official hosts unless the deployment has separately verified the endpoint and allowlist requirements. Risk: Generated media jobs can take a long time, fail audit checks, or return temporary result URLs. Mitigation: Run long jobs in background sessions, poll status, surface task IDs and error messages, and refresh expired result URLs when needed. ## Reference(s): - [LinkFox AI Open Platform](https://open.ziniao.com) - [LinkFox API Guide](https://www.linkfox.com/team/api-guide) - [AI Image and Video API Reference](references/image-make.md) - [Open Platform Access and Error Codes](references/open-platform.md) - [ClawHub Skill Page](https://clawhub.ai/linkfox-ai/skills/linkfox-ai) ## Skill Output: **Output Type(s):** [text, markdown, shell commands, configuration, JSON] **Output Format:** [Markdown guidance with shell commands and JSON API responses or generated media URLs] **Output Parameters:** [1D] **Other Properties Related to Output:** [Outputs may include temporary generated media URLs, task IDs for polling, API error messages, and configuration requirements for LinkFoxAI credentials.] ## Skill Version(s): 1.5.1 (source: server release evidence) ## Ethical Considerations: Users 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.
activepieces
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
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
AionUi
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!
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/linkfox-ai/skills/linkfox-ai",
"sourceUrl": "https://clawhub.ai/linkfox-ai/skills/linkfox-ai",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T12:02:50.605Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-linkfox-ai-linkfox-ai/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-linkfox-ai-linkfox-ai/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-09T12:02:50.605Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "2.7K downloads",
"href": "https://clawhub.ai/linkfox-ai/linkfox-ai",
"sourceUrl": "https://clawhub.ai/linkfox-ai/linkfox-ai",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T12:02:50.605Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.5.1",
"href": "https://clawhub.ai/linkfox-ai/linkfox-ai",
"sourceUrl": "https://clawhub.ai/linkfox-ai/linkfox-ai",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-06-12T06:15:20.181Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-linkfox-ai-linkfox-ai/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-linkfox-ai-linkfox-ai/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.5.1",
"description": "新增:视频复刻 video-reclone,支持 SEED、SEED_FAST 两个模型进行视频复刻生成。 调整:商品套图/服装套图支持「无字模式」--no-text,生成纯画面、不带文案排版。 调整:图转视频/带货口播新增支持SEED_FAST模型生成",
"href": "https://clawhub.ai/linkfox-ai/linkfox-ai",
"sourceUrl": "https://clawhub.ai/linkfox-ai/linkfox-ai",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-06-12T06:15:20.181Z",
"isPublic": true
}
]
}Record generated Oct 9, 2026.
