Tencent-Hunyuan / SRPOLinks
Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
☆1,139Updated last week
Alternatives and similar repositories for SRPO
Users that are interested in SRPO are comparing it to the libraries listed below
Sorting:
- Official repo for CFG-Zero*☆669Updated 5 months ago
- Practice Code for text to image trainer☆489Updated 2 weeks ago
- [CVPR 2025 Highlight🌟] Official ComfyUI implementation of "HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis"☆446Updated 3 months ago
- Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.☆653Updated last month
- ☆527Updated 3 months ago
- ☆1,256Updated last week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,140Updated 4 months ago
- ☆1,316Updated 6 months ago
- High quality training free inpaint for every stable diffusion model. Supports ComfyUI☆629Updated last week
- Training-free Regional Prompting for Diffusion Transformers 🔥☆684Updated 10 months ago
- Start and end frames video generation nodes based on the modified Kijai version Wan2.1 nodes☆375Updated 7 months ago
- Light Video Generation Inference Framework☆676Updated this week
- Nodes for image juxtaposition for Flux in ComfyUI☆1,385Updated 9 months ago
- Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)☆667Updated 3 months ago
- Pusa: Thousands Timesteps Video Diffusion Model☆658Updated last month
- A novel approach to hunyuan image-to-video sampling☆303Updated 8 months ago
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆2,250Updated last week
- ☆637Updated 6 months ago
- An inference and training framework for multiple image input in Flux Kontext dev☆411Updated last month
- Enhance-A-Video: Better Generated Video for Free☆576Updated 7 months ago
- Qwen-Image text to image lora trainer☆493Updated last week
- ☆521Updated 9 months ago
- Illumination Drawing Tools for Text-to-Image Diffusion Models☆778Updated 5 months ago
- [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆1,315Updated last month
- A pipeline parallel training script for diffusion models.☆1,648Updated last month
- ☆441Updated 4 months ago
- ☆779Updated 11 months ago
- HunyuanVideo Keyframe Control Lora is an adapter for HunyuanVideo T2V model for keyframe-based video generation☆163Updated 6 months ago
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆855Updated last week
- ☆429Updated 6 months ago