菜单
Build and orchestrate multi-step AI workflows combining multiple EachLabs models. Create custom pipelines, trigger executions, and manage workflow versions. Use when the user needs to chain multiple AI models or automate multi-step content creation.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/eachlabs/skills --skill eachlabs-workflows命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | eachlabs-workflows |
| description | Build and orchestrate multi-step AI workflows combining multiple EachLabs models. Create custom pipelines, trigger executions, and manage workflow versions. Use when the user needs to chain multiple AI models or automate multi-step content creation. |
| metadata | {"author":"eachlabs","version":"2.0"} |
Build, manage, and execute multi-step AI pipelines that chain multiple models together. each::workflows is completely free to use - you only pay for underlying model costs.
Header: X-API-Key: <your-api-key>
Set the EACHLABS_API_KEY environment variable. Get your key at eachlabs.ai.
https://workflows.eachlabs.run/api/v1
| Method | Path | Description |
|---|---|---|
| GET | /categories | List workflow categories |
| POST | /workflows | Create a workflow |
| GET | /workflows/{id} | Get workflow (UUID or slug) |
| PUT | /workflows/{id} | Update workflow metadata |
| PUT | /workflows/{id}/versions/{versionID} | Create or update version |
| POST |
/{id}/trigger |
| Trigger execution |
| POST | /{id}/bulk-trigger | Bulk trigger (1-10 parallel) |
| GET | /workflows/{id}/executions | List executions |
| GET | /executions/{executionID} | Get execution details |
curl -X POST https://workflows.eachlabs.run/api/v1/workflows \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"name": "Image Enhancement Pipeline",
"description": "Generate and upscale images",
"categories": ["image-generation"],
"definition": {
"version": "v1",
"input_schema": {
"type": "object",
"properties": {
"prompt": {"type": "string", "description": "Image description"}
},
"required": ["prompt"]
},
"steps": [
{
"step_id": "generate",
"type": "model",
"model": "flux-2-pro",
"params": {
"prompt": "{{inputs.prompt}}",
"aspect_ratio": "16:9"
}
},
{
"step_id": "upscale",
"type": "model",
"model": "topaz-upscale-image",
"params": {
"image_url": "{{generate.primary}}",
"scale": 2
}
}
]
}
}'
curl -X POST https://workflows.eachlabs.run/api/v1/{workflowID}/trigger \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"version_id": "v1",
"inputs": {"prompt": "A sunset landscape"},
"webhook_url": "https://your-server.com/webhook"
}'
Response:
{"execution_id": "exec-123", "status": "queued", "started_at": "..."}
curl https://workflows.eachlabs.run/api/v1/executions/{executionID} \
-H "X-API-Key: $EACHLABS_API_KEY"
Response:
{
"execution_id": "exec-123",
"workflow_id": "wf-456",
"status": "completed",
"inputs": {"prompt": "A sunset landscape"},
"step_outputs": {
"generate": {
"step_id": "generate",
"status": "completed",
"output": "https://cdn.example.com/image.png",
"primary": "https://cdn.example.com/image.png",
"metadata": {"model": "flux-2-pro", "version": "1.0.0"}
}
},
"output": ["https://cdn.example.com/upscaled.png"]
}
Execution statuses: running, completed, failed, cancelled
| Type | Purpose |
|---|---|
model | Execute an AI model via each::api |
http | External HTTP request (GET, POST, PUT, DELETE, PATCH) |
python | Execute Python code |
parallel | Execute multiple branches concurrently |
choice | Evaluate condition and route to matching branch |
pass | Pass-through with optional static value injection |
All steps support:
continue_on_error (boolean) - Continue workflow if step failstimeout_seconds (integer) - Step timeoutretry configuration - Automatic retry on failure{
"step_id": "generate",
"type": "model",
"model": "flux-2-max",
"params": {
"prompt": "{{inputs.prompt}}",
"aspect_ratio": "16:9"
}
}
{
"step_id": "call_api",
"type": "http",
"url": "https://api.example.com/process",
"method": "POST",
"headers": {"Content-Type": "application/json"},
"body": {"data": "{{generate.primary}}"},
"auth": {"type": "bearer", "token": "{{inputs.api_token}}"},
"timeout": 30000
}
Auth types: basic (username/password), bearer (token), api_key
{
"step_id": "transform",
"type": "python",
"code": "result = inputs['text'].upper()",
"inputs": {"text": "{{generate.primary}}"}
}
Execute multiple branches simultaneously:
{
"step_id": "step1",
"type": "parallel",
"branches": [
{
"name": "Video Generation",
"steps": [
{
"step_id": "step1_branch_0",
"type": "model",
"model": "kling-3-0",
"params": {"prompt": "{{inputs.prompt}}", "duration": 5}
}
]
},
{
"name": "Image Edit",
"steps": [
{
"step_id": "step1_branch_1",
"type": "model",
"model": "flux-2-edit",
"params": {"prompt": "{{inputs.prompt}}", "image_url": "{{inputs.image}}"}
}
]
}
]
}
{
"step_id": "step2",
"type": "choice",
"condition": {
"expression": "$.step1.primary",
"operator": "string_matches",
"value": ".mp4"
},
"condition_met_branch": {
"name": "condition_met",
"step_id": "step2_condition_met",
"steps": [
{"step_id": "step2_branch_0", "type": "model", "model": "topaz-upscale-video", "params": {"video": "{{step1.primary}}", "scale": 2}}
]
},
"default_branch": {
"name": "default",
"step_id": "step2_default",
"steps": [
{"step_id": "step2_default", "type": "model", "model": "topaz-upscale-image", "params": {"image_url": "{{step1.primary}}", "scale": 2}}
]
}
}
Condition operators:
| Category | Options |
|---|---|
| Comparison | equals, not_equals, greater_than, less_than, greater_than_or_equal, less_than_or_equal |
| String | string_equals, string_matches |
| Array | in, not_in |
| Existence | exists, not_exists, is_null, is_not_null |
Logical operators: and, or, not for complex conditions:
{"and": [
{"expression": "$.step1.primary", "operator": "string_matches", "value": ".png"},
{"expression": "$.inputs.upscale", "operator": "equals", "value": true}
]}
{"step_id": "config", "type": "pass", "result": {"style": "cinematic"}}
Use {{double braces}} to reference inputs and step outputs:
| Reference | Purpose | Example |
|---|---|---|
{{inputs.field}} | Workflow input value | {{inputs.prompt}} |
{{step_id.output}} | Full step output | {{generate.output}} |
{{step_id.primary}} | Primary/first result | {{generate.primary}} |
{{branch_step_id.primary}} | Output from parallel branch | {{step1_branch_0.primary}} |
Templates can be embedded in strings: "A portrait of {{inputs.name}} in {{inputs.style}} style"
Conditions use $ syntax: $.step_id.primary, $.inputs.field
Automatic fallback to secondary model when primary fails:
{
"step_id": "generate",
"type": "model",
"model": "flux-2-max",
"params": {"prompt": "{{inputs.prompt}}"},
"fallback": {
"enabled": true,
"model": "flux-2-pro",
"params": {"prompt": "{{inputs.prompt}}"}
}
}
Steps are defined in versions, not in the workflow itself. This allows iterating while keeping previous versions intact.
Version states: active, archived, deleted
Locking: Set locked: true to prevent modifications (for production stability).
Visibility:
allowed_to_share: false (default) - Private, organization onlyallowed_to_share: true - Unlisted, accessible via direct linkcurl -X PUT https://workflows.eachlabs.run/api/v1/workflows/{workflowID}/versions/{versionID} \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"description": "Added upscaling step",
"definition": {
"version": "v1",
"input_schema": {
"type": "object",
"properties": {
"prompt": {"type": "string"}
},
"required": ["prompt"]
},
"steps": [...]
}
}'
Process multiple inputs (max 10) in a single API call:
curl -X POST https://workflows.eachlabs.run/api/v1/{workflowID}/bulk-trigger \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"version_id": "v1",
"inputs": [
{"prompt": "A sunset landscape"},
{"prompt": "A mountain scene"},
{"prompt": "An ocean view"}
],
"webhook_url": "https://your-server.com/webhook"
}'
Response includes bulk_id for tracking. Partial failures are possible.
Configure a webhook to receive results asynchronously:
curl -X POST https://workflows.eachlabs.run/api/v1/{workflowID}/trigger \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"version_id": "v1",
"inputs": {"prompt": "A sunset landscape"},
"webhook_url": "https://your-server.com/webhook",
"webhook_secret": "your-secret"
}'
Webhook payload (success):
{"execution_id": "...", "workflow_id": "...", "status": "completed", "inputs": {}, "step_outputs": {}, "output": []}
Retry schedule: ~30 seconds, ~2 minutes, ~10 minutes
Verify webhook authenticity using HMAC-SHA256 with webhook_secret.
You can also build workflows using natural language via the each::sense workflow endpoint:
curl -X POST https://eachsense-agent.core.eachlabs.run/workflow \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"message": "Create a workflow that generates an image and then upscales it",
"stream": true,
"session_id": "my-session"
}'
To update an existing workflow, include workflow_id and version_id.
See references/WORKFLOW-EXAMPLES.md for common workflow patterns.
基于 SOC 职业分类
Generate cinematic videos with native synchronized audio using ByteDance Seedance 2.0 (Fast) via EachLabs. Supports text-to-video (bytedance-seedance-2-0-text-to-video-fast) and image-to-video (bytedance-seedance-2-0-image-to-video-fast). Use when the user specifically asks for Seedance 2.0, wants native audio with the video, realistic physics, director-level camera control, or 4–15 second clips up to 720p.
Edit, transform, upscale, and enhance images using EachLabs AI models. Supports image editing, style transfer, background removal, upscaling, inpainting, face swap, virtual try-on, 3D generation, and image analysis. Use when the user wants to edit or transform existing images.
Generate new images from text prompts using EachLabs AI models. Supports text-to-image with multiple model families including Flux, GPT Image, Gemini, Imagen, Seedream, and more. Use when the user wants to create new images from text. For editing existing images, see eachlabs-image-edit.