ComfyUI Quick Start
A collection of quick-start tutorials for ComfyUI
Translated by AI
Lecture 1: Getting started with AI creation and text-to-image generation
- Basic concepts of AI generation and a comparison of mainstream AI tools
- Prompt engineering for text-to-image
- Installing and using ComfyUI
- Installing custom models in ComfyUI
- Basics of image generation parameters
- Installing ComfyUI extensions
- Choosing a base model in ComfyUI
Lecture 2: Image-to-image generation, precise control and post-processing
* (Most of what this section covers can now be done by “editing images by talking” with multimodal models such as GPT-4o or Doubao. Decide for yourself whether you need to learn it.)
- Image generation from an input image
- Precise control of image generation with ControlNet
- Style transfer with IPAdapter
- Image post-processing: upscaling, retouching, outpainting
Lecture 3: Building AI agents in ComfyUI
↓ (The tutorials below need a local ComfyUI setup; decide for yourself whether to try them.)
- Your first AI agent in ComfyUI
- 3D bio-architect: an AI agent with multimodal input and output
- Building multi-agent AI interaction
- Further study: running AI agents with external tools and resources
Lecture 4: AI generation and editing of 3D models and video
- AI generation of 3D models
- Fine-tuning 3D model textures with AI
- Video generation with AI models (online platforms)