bytedance / USOLinks
🔥🔥 Open-sourced unified customization model
☆1,199Updated 3 months ago
Alternatives and similar repositories for USO
Users that are interested in USO are comparing it to the libraries listed below
Sorting:
- HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning☆1,050Updated last week
- HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation☆665Updated 2 months ago
- [ArXiv 25] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling☆832Updated this week
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆1,105Updated last week
- Official inference repo for FLUX.2 models☆1,289Updated last month
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆2,617Updated 2 months ago
- Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"☆1,206Updated 2 weeks ago
- ComfyUI node for highly expressive speech and realistic zero-shot voice cloning☆354Updated 2 weeks ago
- ☆701Updated last month
- ☆1,485Updated last month
- ☆1,728Updated last week
- [SIGGRAPH Asia 25] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off☆331Updated 2 months ago
- ☆783Updated 5 months ago
- Pusa: Thousands Timesteps Video Diffusion Model☆669Updated 3 months ago
- Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.☆702Updated last week
- Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives☆570Updated last month
- Official GitHub repository for FLUX.1 Krea [dev].☆358Updated 5 months ago
- [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆1,343Updated 3 months ago
- Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.☆785Updated 4 months ago
- ComfyDeployed☆438Updated 3 months ago
- Qwen-Image-Layered: Layered Decomposition for Inherent Editablity☆1,030Updated last week
- ☆1,044Updated 7 months ago
- PersonaLive! : Expressive Portrait Image Animation for Live Streaming☆1,075Updated this week
- In-context subject-driven image generation while preserving foreground fidelity☆350Updated 6 months ago
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation☆1,196Updated 2 months ago
- Lumina-Image 2.0: A Unified and Efficient Image Generative Framework☆844Updated last month
- [Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset☆541Updated 2 months ago
- MoCha: End-to-End Video Character Replacement without Structural Guidance☆525Updated last month
- ObjectClear: Complete Object Removal via Object-Effect Attention☆519Updated last month
- ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio☆547Updated 3 months ago