image-edit 开源项目推荐（44 个）

VectorSpaceLab /OmniGen

OmniGen：统一图像生成。https://arxiv.org/pdf/2409.11340

tamarott /SinGAN

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

wangkai930418 /awesome-diffusion-categorized

按子领域分类的扩散模型论文集

sled-group /InfEdit

[CVPR 2024] Official implementation, Inversion-Free Image Editing with Natural Language"

Amshaker /Mobile-O

[CVPR'26 Demo] Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

light-and-ray /Minimalistic-Comfy-Wrapper-WebUI

MCWW: Additional non-node based UI for ComfyUI focused on inference. Stable UI states; presets; and advanced queue. Based on Gradio

tamlhp /awesome-instructional-editing

Awesome Instruction Editing. Image and Media Editing with Human Instructions. Instruction-Guided Image and Media Editing.

sled-group /CycleNet

[NeurIPS 2023]CycleNet官方代码：重新思考图像处理中文本引导扩散中的周期一致性

weichow23 /EditMGT

Official Repo for Paper <EditMGT Unleashing the Potential of Masked Generative Transformer in Image Editing>

KingGyuSuh /codex-image-in-cc

Claude Code plugin that exposes Codex CLI's built-in imagegen skill as /codex-image:* user-invoked slash commands.

yingchen001 /CF-CLIP

[ACM MM 2022] Towards Counterfactual Image Manipulation via CLIP

weichow23 /AnySD

Official model implementation and benchmark evaluation repository of <AnyEdit: Unified High-Quality Image Edit with Any Idea>

zhuochen02 /SynPS

[CVPR 2026] The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy

Anu3ev /image-editor

TypeScript image editor library built on FabricJS, allowing you to create instances with an integrated montage area and providing an API to modify and manage state.

tensorslab /skills

TensorLab Skills are AI task definitions for Claude Code, focusing on multimedia generation and processing using TensorsLab's AI models. It provides comprehensive capabilities including text-to-image and image-to-image generation, advanced image editing (avatar generation, watermark removal, object erasure, face replacement), as well as text-to-vid

zilongzheng /PatchGenCN

CVPR 2021 Oral Paper PatchGenCN

XZXY-AI /awesome-gpt-image-2-playground

The only GPT Image 2 prompt library you can run for free in your browser. 32 ready-to-run prompts, 12 languages.

neoneo-ai /neo-studio

Neo Studio：AI 驱动的绘图，导演工作台，Windows 桌面端 +ComfyUI插件双形态，支持手机连接， MCP 服务（20 工具）。LLM 提示词增强/生成/反推、Krea2 / Qwen Image 生图与参考编辑、H3 多段视频导演、素材库与配方一键发送、工作流修复。Prompt, image gen, video director, asset/recipe library, workflow repair, MCP for agents.

EricRollei /Emu35-Comfyui-Nodes

custom comfyui nodes and quantization for Emu3.5 Image and Emu 3.5 base

easygoing0114 /ComfyUI-uit-hidream-o1

用于 HiDream-O1-Image 的单一采样节点（UIT Sampler）。