Execute ComfyUI API-format workflows with parameter injection for image, video, and audio generation.
npx skills add https://github.com/ZardLi1115/zedclaw --skill comfyui-zardli1115
Please help me install this Agent Skill. Skill: comfyui Source: https://github.com/ZardLi1115/zedclaw/tree/main/skills/creative/comfyui Command: npx skills add https://github.com/ZardLi1115/zedclaw --skill comfyui-zardli1115
This Skill removes the friction of setting up ComfyUI and repeatedly running complex image/video generation workflows by providing automated lifecycle management, dependency checking, and parameterized execution.
Run comfyui_generate for a SDXL text-to-image workflow by telling the system: generate an SDXL image from the prompt "a cinematic photograph of a mountain lake at sunrise" and save the result to outputs using the example workflow.
High-intent search queries and answers about installing and using this skill.
Executing ComfyUI workflows automatically involves running API-format workflows while injecting user parameters like prompt text, seed, steps, and dimensions, and uploading input images or masks to generate images, video, and audio.
Yes, ComfyUI supports SD1.5, SDXL, and Flux models for text-to-image, img2img, and inpainting tasks, alongside upscaling and common animation/video pipelines to generate diverse media outputs.
To install and set up ComfyUI, run a hardware check to recommend local or Comfy Cloud environments, then install comfy-cli and ComfyUI with the appropriate GPU flags for optimal execution.
To fix missing nodes, models, or embeddings in ComfyUI, check required dependencies against a running server and apply exact comfy-cli install commands or safe git-based installation hints provided by validation suggestions.
Yes, you can monitor ComfyUI workflow progress using WebSocket progress monitoring, poll job status when needed, and download outputs with path-traversal-safe handling to retrieve generated media.
The best way to validate API-format workflows before execution is to perform safe dependency checks against a running server, verifying required nodes, models, and embeddings to ensure successful workflow execution.
MarbleSodasExecute ComfyUI API-format workflows with parameter injection for image, video, and audio generation.
cabeznoExecute ComfyUI API-format workflows with parameter injection for image, video, and audio generation.
anxiety135790Execute validated Cloudinary workflows for image, video, audio, and 3D generation with parameter injection and monitoring.
skkeoriwAutomate image, video, and audio generation via ComfyUI REST and WebSocket APIs.
