# Ai-Comfyui

**Repository Path**: ai-learning_3/ai-comfyui

## Basic Information

- **Project Name**: Ai-Comfyui
- **Description**: 形成一个完整的闭环执行流程。实现无需用户进行额外操作，仅需依次点击六次界面按钮即可完成全部流程并生成目标图片或展示最终效果的自动化执行机制。确保每个步骤之间实现无缝衔接，前一步骤的输出自动作为后一步骤的输入，消除用户手动干预的需求。
- **Primary Language**: Unknown
- **License**: GPL-3.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-03-31
- **Last Updated**: 2026-04-03

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

<div align="center">

# ComfyUI
**The most powerful and modular visual AI engine and application.**

## Latest Updates

### 🔧 Bug Fixes (2026-04-02)
- **Fixed GUI one-click generation 400 error issue**
  - Corrected API client model list endpoint error
  - Rewrote workflow construction logic using correct node IDs and connection methods
  - Fixed seed value validation issue
  - GUI can now properly submit generation tasks to ComfyUI server

- **Smoke test passed**
  - ✅ Server connection normal
  - ✅ Model list correctly loaded
  - ✅ Workflow format validation passed
  - ✅ API call successfully returned prompt_id
  - ✅ Task queue execution normal

### 🎯 GUI Feature Status
- **One-click generation of cute kittens**: ✅ Fully fixed and usable
- **Model management**: ✅ Supports main model, VAE, LoRA loading
- **Prompt management**: ✅ Supports positive/negative prompt input
- **Generation progress monitoring**: ✅ Real-time display of execution status

## Language / 语言

Choose your preferred language to view the documentation:

<a href="docs/zh-CN/README.md" style="display: inline-block; padding: 10px 20px; margin: 10px; background-color: #4285F4; color: white; text-decoration: none; border-radius: 4px; font-weight: bold;">中文文档 / Chinese Documentation</a>

<a href="docs/en-US/README.md" style="display: inline-block; padding: 10px 20px; margin: 10px; background-color: #34A853; color: white; text-decoration: none; border-radius: 4px; font-weight: bold;">English Documentation / 英文文档</a>

## Quick Start

### [Desktop Application](https://www.comfy.org/download)
- The easiest way to get started.
- Available on Windows & macOS.

### [Windows Portable Package](docs/en-US/README.md#installing)
- Get the latest commits and completely portable.
- Available on Windows.

### [Manual Install](docs/en-US/README.md#manual-install-windows-linux)
Supports all operating systems and GPU types (NVIDIA, AMD, Intel, Apple Silicon, Ascend).

## Key Features

- Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything.
- Support for multiple models including SD1.x, SD2.x, SDXL, Stable Cascade, SD3, Pixart, AuraFlow, HunyuanDiT, Flux, and more.
- Asynchronous Queue system
- Smart memory management: can automatically run large models on GPUs with as low as 1GB vram with smart offloading.
- Works even if you don't have a GPU with: ```--cpu``` (slow)
- Can load ckpt and safetensors: All in one checkpoints or standalone diffusion models, VAEs and CLIP models.
- Safe loading of ckpt, pt, pth, etc.. files.
- Embeddings/Textual inversion
- [Loras (regular, locon and loha)](https://comfyanonymous.github.io/ComfyUI_examples/lora/)
- [Hypernetworks](https://comfyanonymous.github.io/ComfyUI_examples/hypernetworks/)
- Loading full workflows (with seeds) from generated PNG, WebP and FLAC files.
- Saving/Loading workflows as Json files.
- Nodes interface can be used to create complex workflows like one for [Hires fix](https://comfyanonymous.github.io/ComfyUI_examples/2_pass_txt2img/) or much more advanced ones.
- [Area Composition](https://comfyanonymous.github.io/ComfyUI_examples/area_composition/)
- [Inpainting](https://comfyanonymous.github.io/ComfyUI_examples/inpaint/) with both regular and inpainting models.
- [ControlNet and T2I-Adapter](https://comfyanonymous.github.io/ComfyUI_examples/controlnet/)
- [Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)](https://comfyanonymous.github.io/ComfyUI_examples/upscale_models/)
- [GLIGEN](https://comfyanonymous.github.io/ComfyUI_examples/gligen/)
- [Model Merging](https://comfyanonymous.github.io/ComfyUI_examples/model_merging/)
- [LCM models and Loras](https://comfyanonymous.github.io/ComfyUI_examples/lcm/)
- Latent previews with [TAESD](docs/en-US/README.md#how-to-show-high-quality-previews)
- Works fully offline: core will never download anything unless you want to.
- Optional API nodes to use paid models from external providers through the online [Comfy API](https://docs.comfy.org/tutorials/api-nodes/overview).
- [Config file](extra_model_paths.yaml.example) to set the search paths for models.
- **Visualization Panel Application**: Provides an intuitive interface to manage models, prompts, and resources.
- **Workflow Management System**: Supports creating, saving, loading, and managing multiple workflows.
- **Permission Control**: Supports role-based permission management with admin, user, and guest roles.
- **State Management**: Supports hierarchical state structure with state listeners for reactive updates.
- **Error Handling**: Supports categorized error messages with detailed error feedback.

## Examples

Check out the [Examples page](https://comfyanonymous.github.io/ComfyUI_examples/) to see what ComfyUI can do with various workflows.

## Support and Development Channels

[Discord](https://comfyanonymous.github.io/ComfyUI_examples/area_composition/): Try #help or #feedback channels.

[Matrix space: #comfyui_space:matrix.org](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) (it's like discord but open source).

Also see: [https://www.comfy.org/](https://www.comfy.org/)

</div>