VectorSpaceLab / OmniGen2Links
OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871
☆3,979Updated 3 weeks ago
Alternatives and similar repositories for OmniGen2
Users that are interested in OmniGen2 are comparing it to the libraries listed below
Sorting:
- Open-source unified multimodal model☆5,505Updated 2 months ago
- [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing☆3,537Updated 2 months ago
- MAGI-1: Autoregressive Video Generation at Scale☆3,620Updated 6 months ago
- Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.☆6,525Updated last week
- ☆2,488Updated 5 months ago
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation☆1,196Updated 2 months ago
- ☆1,968Updated 2 weeks ago
- HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo☆1,758Updated 7 months ago
- ☆1,728Updated last week
- [NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation☆2,752Updated last week
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆2,617Updated 2 months ago
- Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment☆1,469Updated 3 months ago
- Official PyTorch implementation of One-Minute Video Generation with Test-Time Training☆2,328Updated 6 months ago
- SkyReels-V2: Infinite-length Film Generative model☆5,375Updated 4 months ago
- The best OSS video generation models, created by Genmo☆3,540Updated last month
- 🔥🔥 Open-sourced unified customization model☆1,196Updated 3 months ago
- Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model☆2,581Updated last week
- [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆1,343Updated 3 months ago
- SkyReels V1: The first and most advanced open-source human-centric video foundation model☆2,613Updated 9 months ago
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,008Updated 3 months ago
- Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, im…☆3,185Updated 2 months ago
- [NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ …☆2,051Updated last week
- SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer☆4,847Updated last week
- MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.☆3,022Updated 5 months ago
- [ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis☆1,608Updated 4 months ago
- TurboDiffusion: 100–200× Acceleration for Video Diffusion Models☆1,749Updated this week
- A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.☆3,598Updated this week
- ☆3,143Updated 9 months ago
- Official inference repo for FLUX.2 models☆1,268Updated 3 weeks ago
- A unified inference and post-training framework for accelerated video generation.☆2,878Updated this week