VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
Supports multi-modal conditioning (text + images) for unified generation across text-to-image, subject-driven, identity-preserving, editing, and image-conditioned tasks without requiring auxiliary modules like ControlNet or IP-Adapter. Uses an end-to-end diffusion architecture that automatically extracts necessary features (objects, poses, depth) from input images based on textual instructions. Integrates with Hugging Face (Diffusers, Model Hub, Spaces) and Replicate, with fine-tuning support for custom tasks.
4,313 stars and 72 monthly downloads. Available on PyPI.
Stars
4,313
Forks
368
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 04, 2025
Monthly downloads
72
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VectorSpaceLab/OmniGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
JIA-Lab-research/DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing...
PKU-YuanGroup/ChronoMagic-Bench
[NeurIPS 2024 D&B Spotlightš„] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of...
SkyworkAI/UniPic
Open-source SOTA multi-image editing model