comfyui
par xtopher86
Image & Video GenerationRésumé
Send a workflow request to ComfyUI and return image results.
Description
Ce que fait ce skill
Sends a JSON workflow to a running ComfyUI server and returns the generated image as a URL or base64 string. Connects over HTTP using configurable host, port, and optional basic auth credentials.
Lets agents drive ComfyUI image generation without manual UI interaction, making it composable with other automated steps.
Quand l'utiliser
- Triggering image generation from an AI agent conversation
- Automating batch image workflows without opening the ComfyUI UI
- Integrating ComfyUI output into a larger multi-step pipeline
- Testing workflow JSON changes programmatically
- Retrieving generated images for downstream processing or storage
Exemple de workflow
User asks: Run this ComfyUI workflow and give me the output image
- 1
Load the workflow JSON object
- 2
POST the workflow to the ComfyUI /run endpoint at the configured host and port
- 3
Receive the JSON response from the server
- 4
Extract the image field containing the URL or base64 string
Image URL or base64 string ready for display or further processing
Prérequis
- ComfyUI server installed and running with the /run endpoint exposed
- COMFYUI_USER and COMFYUI_PASS credentials if the server requires basic auth
Installation
clawhub install xtopher86/comfyui-requestExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.