ComfyUI Skill

This skill enables Claude to interact with ComfyUI for AI image/video generation, workflow management, and distributed GPU compute via Salad Cloud API.

Capabilities

• Generate images using text prompts (text2img)
• Generate images from images (img2img)
• Create and execute node-based workflows
• Deploy to Salad Cloud for distributed GPU compute
• Manage models, LoRAs, and checkpoints
• Video generation (AnimateDiff, CogVideoX, HunyuanVideo)
• Upscaling and post-processing

When to Use This Skill

Use this skill when you need to: