#7878th of 79 in Image and videoFor image, video and design, image and design
omnigen
Single model for text-to-image, subject-driven generation and image editing
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.3k
- License
- MIT
- Last commit
- Dec 2025
- Language
- Jupyter Notebook
Missed the latest GitHub check; these facts may be older.
Overview
OmniGen is an image generation model that takes interleaved text and image prompts and handles text-to-image, subject-driven generation, identity-preserving generation and editing without ControlNet or IP-Adapter modules. The repo has a Python inference pipeline (OmniGenPipeline), a Gradio app, and a train.py script for LoRA or full fine-tuning. Weights are Shitao/OmniGen-v1 on Hugging Face; a successor, OmniGen2, lives in a separate repo.
Who it is for: Researchers and developers testing unified image generation and fine-tuning
Strengths
- One model covers text-to-image, editing and reference-image generation without extra plugins
- Includes train.py for LoRA and full fine-tuning, with a toy dataset example
- Usable through Hugging Face Diffusers, a local Gradio app, or Colab
- MIT-licensed code with public weights and a Hugging Face demo
Weaknesses
- Superseded by OmniGen2, which has its own repository
- No release tags; last commit was December 2025
- Python library and notebooks only; no packaged server or Docker image
- Multi-image prompts need manual image placeholders and can be slow
What it needs
- GPU required
- Needs PyTorch, Hugging Face Hub weights, Gradio (optional demo), accelerate (training)
- Models: Shitao/OmniGen-v1
Also in Image and video
See all 79| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 87 out of 100 |
| #4 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 86 out of 100 |
| #5 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 86 out of 100 |