ComfyUI: Node-based diffusion model interface
Visual graph-based diffusion model workflow builder.
Learn more about ComfyUI
ComfyUI is a Python-based backend and frontend application that provides a node-graph interface for building diffusion model workflows. It implements a modular architecture where individual operations (model loading, sampling, image processing) are represented as nodes that connect to form execution graphs. The system supports multiple diffusion model families including Stable Diffusion variants, SDXL, Flux, and specialized models for video and audio generation, with backend support for NVIDIA, AMD, Intel, and Apple Silicon GPUs. Workflows are constructed visually without requiring code, though the underlying system can be accessed programmatically via API.
Node-Based Workflow Construction
Each operation is a discrete, connectable node forming an execution graph. Complex pipelines are built visually without code, making workflow logic explicit, modular, and reusable across projects.
Multi-Model Family Support
Supports Stable Diffusion 1.x through Flux, SDXL, Hunyuan, plus specialized video, audio, and 3D models. Different model families can be mixed within a single workflow without compatibility barriers.
Abstracted GPU Backends
Unified interface across NVIDIA CUDA, AMD ROCm, Intel Arc, Apple Metal, and Ascend NPUs. Platform-specific optimizations are handled internally, eliminating manual backend configuration.
import requests
import json
workflow = json.load(open('workflow.json'))
response = requests.post(
'http://127.0.0.1:8188/prompt',
json={'prompt': workflow}
)
prompt_id = response.json()['prompt_id']
print(f"Queued: {prompt_id}")Fix crash on safetensors load for some 3rd party Models
- –Fix crash on safetensors load for some 3rd party Models
- –mp: Fix checkpoint saving
- –add File3DAny output to Load3D node; extend SaveGLB to accept File3DAny as input
- –Fix ace step nan issue on some hardware/pytorch configs
- –Try to fix ace text encoder slowness on some configs
Support the 4B ace step 1.5 lm model.
- –Support the 4B ace step 1.5 lm model
- –Dynamicvram: Remove Aimdo exemption for emptycache (fixes VRAM leak)
- –Fix crash with ace step 1.5
Add progress bar to ace step.
- –Add progress bar to ace step
- –Fix some issues with mac
- –llama: cast logits as a comfy-weight
- –Fix mac issue
- –feat(comfy_api): add basic 3D Model file types
See how people are using ComfyUI
Top in AI & ML
Related Repositories
Discover similar tools and frameworks used by developers
DeepFace
Python library wrapping multiple face recognition deep learning models.
Open Notebook
Open source implementation of Google's NotebookLM that runs locally with document processing and podcast generation.
OpenAI.fm
Web demo showcasing OpenAI's Speech API text-to-speech capabilities with an interactive Next.js interface.
AI-Trader
LLM agent benchmarking framework for autonomous market trading.
Open Lovable
AI tool that generates React applications from website clones or user descriptions.
Related Reading
Guides and comparisons from the Greptile content library
The 7 Best AI Coding Tools for Complex Codebases
The best AI coding tools for complex codebases, ranked on accuracy, suggestion quality, and full-codebase context. See which ones you can actually trust.
Best AI Code Review Tools for GitHub
Top-rated AI code review tools for GitHub teams in 2025. Compare features, pricing, and accuracy to find the perfect fit for faster PR reviews and bulletproof code quality.
What is Shift Left Testing? Everything Engineering Leaders Need to Know
The five types of shift-left testing, the benefits and limitations of each, and how the approach changes when agents write and review a growing share of your code.
What is agentic coding? Benefits, risks, and best tools to consider
What engineering leaders need to know about agentic coding: how it differs from AI coding and vibe coding, how it works, the benefits and risks, and the tools worth evaluating.