Bagel
ByteDance's open-source unified multimodal model for understanding, generation and image editing.
OmniGen est un projet de image open source, créé par VectorSpaceLab (VectorSpaceLab/OmniGen sur GitHub). Il compte 4 343 étoiles sur GitHub et 364 forks, il est publié sous la licence MIT et a été mis à jour pour la dernière fois sur GitHub le 4 décembre 2025.
OmniGen: one unified model for text-to-image, editing, subject-driven and identity-preserving generation
Create the documented Conda environment (Python 3.10.x) — OmniGen inference expects a CUDA GPU.
Clone the repo and install it in editable mode after installing the pinned PyTorch build.
Load Shitao/OmniGen-v1 weights from Hugging Face through the OmniGen pipeline (or Diffusers).
Write a prompt, pass input images with guidance scales, and save your first edited or subject-driven image.
Text-to-image, editing, subject-driven, identity-preserving, and image-conditioned generation in one model.
Tasks that usually need ControlNet or IP-Adapter are handled natively by the framework.
Reference images inline with <|image_1|>-style placeholders and combine multiple inputs.
Separate guidance_scale and img_guidance_scale parameters balance text and image influence.
Use the model through Hugging Face Diffusers or run the included Gradio demo (app.py).
LoRA and full-parameter training scripts (train.py with accelerate) adapt the model to your data.
Clone the project and enter its directory.
git clone https://github.com/VectorSpaceLab/OmniGen.git
cd OmniGenCreate the Conda env, install the pinned CUDA PyTorch build from the README, then install the package.
conda create -n omnigen python=3.10.13
conda activate omnigen
pip install torch==2.3.1+cu118 torchvision --extra-index-url https://download.pytorch.org/whl/cu118
pip install -e .Load the pretrained model and generate with an image reference, following the README's examples.
from OmniGen import OmniGenPipeline
pipe = OmniGenPipeline.from_pretrained("Shitao/OmniGen-v1")
images = pipe(prompt="Edit <|image_1|>", input_images=["input.png"], guidance_scale=2.5, img_guidance_scale=1.6, seed=0)VectorSpaceLab, the research team behind the OmniGen paper (arXiv 2409.11340).
The code is MIT-licensed and the weights are downloadable from Hugging Face; check the model card for the weights' own terms.
No — it runs locally on your GPU with downloaded weights.
OmniGen folds editing, subject-driven, and conditioned generation into one model with in-prompt image references, instead of a base model plus separate plugin networks.
Create the Python 3.10 Conda env, install the pinned PyTorch build, `pip install -e .`, then run the OmniGenPipeline example from the README.
ByteDance's open-source unified multimodal model for understanding, generation and image editing.
Infinite text-free AI image generator with a searchable multilingual vault
MMagic — OpenMMLab's generative-AI toolbox: diffusion, text-to-image, restoration and a model zoo.
Tencent's HunyuanImage-3.0 — a powerful native multimodal model for image generation.
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Multi-provider AI image generator with OpenAI-compatible API and one-click deploy
Les autres projets de la catégorie Image avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si OmniGen ne vous convient pas.
Stable Diffusion web UI
The node-graph powerhouse for precise, professional AI image and video generation.
High performance self-hosted photo and video management solution
PhotoCraft — a clean-room Photoshop reimplementation in pure Rust: layers, masks, adjustment layers, type, vectors, brushes and real PSD files, offline, MIT / Apache-2.0
Focus on prompting and generating
Projets de la catégorie Image proches dans le catalogue, les plus proches en étoiles de OmniGen — continuez à explorer de part et d'autre.
A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion.
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, a…
A powerful cross-platform raw photo processing program
AI 助手全套开源解决方案,自带运营管理后台,开箱即用。集成了 ChatGPT, Azure, ChatGLM,讯飞星火,文心一言等多个平台的大语言模型。支持 MJ AI 绘画,Stable Diffusion AI 绘画,微博热搜等插件工具。采用 Go + Vue3 + element-plus 实现。
Simple GTK Paint Program
Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.