flux-dev 开源项目推荐（35 个）

leejet /stable-diffusion.cpp

纯 C/C++ 实现的扩散模型（SD、Flux、Wan、Qwen Image、Z-Image 等）推理

bghira /SimpleTuner

针对图像/视频/音频扩散模型的通用微调套件。

FurkanGozukara /Stable-Diffusion

FLOX、Stable Distance、SDXL、SD 3、LoRA、微调、DreamBooth、培训、Automatic 1111、Forge WebUI、SwarmUI、DeepFake、TTC、动画、文本转视频、教程、指南、讲座、课程、ComfyUI、Google Colab、RunPod、Kaggle、NoteBooks、Control Net、DTS、语音克隆、AI新闻、ML、ML新闻、科技、科技新闻、Kohya、Midjourney、RunPod

dimtoneff /ComfyUI-PixelArt-Detector

使用 SDXL 生成、缩放、更改调色板并恢复像素艺术图像。比如Astropulse/pixeldetector的节点、Image的调色板加载器、调色板的网格视图等。

HolmesShuan /FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing

[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)

XLabs-AI /deforum-x-flux

Deforum based on flux-dev by XLabs-AI

bytedance /LatentUnfold

Implementation of paper: Flux Already Knows – Activating Subject-Driven Image Generation without Training

codebucks27 /Pictoria-AI-Starter-Code

Transform your photos with the power of AI! Pictoria AI is your ultimate solution for creating/generating professional AI-generated photos, similar to the popular PhotoAI platform. Perfect for LinkedIn headshots and professional portraits. Train AI model on your personal images and generate stunning images.

rubi-du /ComfyUI-Flux-Inpainting

This repository wraps the flux fill model as ComfyUI nodes. Compared to the flux fill dev model, these nodes can use the flux fill model to perform inpainting and outpainting work under lower VRM conditions

GaParmar /group-inference

Scalable group inference for generating high quality and diverse images with diffusion models.

xlite-dev /flux-faster

A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.

GravityVerseYield47 /flux-ai-works

Flux AI Works

Pavansomisetty21 /Text-to-Images-Leveraging-Flux-AI-for-Text-to-Image-Generation

we explores the fascinating domain of text-to-image generation using the powerful capabilities of the Flux API. The objective is to transform textual descriptions into vivid and accurate visual representations, leveraging state-of-the-art artificial intelligence

anthonycorletti /modal-photobooth

An AI powered photobooth for your next profile picture

laurentvv /generator-assets

Headless, modular local AI pipeline: 2D/3D Godot & Blender assets (Flux.1, SDXL, ESRGAN), AI video generation (Wan 2.1/2.2, LTX-2.5, MiniMax-H3) with 4K YouTube masters, and AI music loops (MiniMax-Music3 via audio.cpp) — 100% Vulkan/GGUF, no CUDA, no cloud.

maxron84 /Ollama-OpenWebUi-ComfyUi

Docker service stack for a comprehensive local ai experience, running on a normal home hardware setup with single GPU. Project-Status: Working, Backlog.

kylemclaren /cog-flux

Run Flux on Fly GPUs

iguanesolutions /comfyui-ig1-tools

ComfyUI helpers nodes to work with automated high resolution generation workflows

Tenos-ai /tenos-bot

An image generation bot that uses Comfy's API and Discord's API in a workflow format that focuses on creation over configuration.

wesbiggs /mfluxible

Streaming HTTP API for MLX image generation models on Apple Silicon, built on mflux