thu-ml / TurboDiffusionLinks
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
☆3,298Updated last week
Alternatives and similar repositories for TurboDiffusion
Users that are interested in TurboDiffusion are comparing it to the libraries listed below
Sorting:
- Light Image Video Generation Inference Framework☆1,897Updated this week
- Official inference repo for FLUX.2 models☆1,721Updated 3 weeks ago
- A unified inference and post-training framework for accelerated video generation.☆3,059Updated this week
- ☆2,053Updated last month
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation☆1,204Updated 3 months ago
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆2,827Updated this week
- Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.☆3,485Updated last week
- Qwen-Image-Layered: Layered Decomposition for Inherent Editablity☆1,540Updated last month
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆1,211Updated last month
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,254Updated 8 months ago
- Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"☆1,750Updated last week
- HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo☆1,777Updated 8 months ago
- CogView4, CogView3-Plus and CogView3(ECCV 2024)☆1,104Updated 10 months ago
- MAGI-1: Autoregressive Video Generation at Scale☆3,639Updated 7 months ago
- 🤗 A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.☆945Updated this week
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,202Updated 6 months ago
- [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆1,350Updated 4 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~ …☆2,074Updated last month
- Open-source unified multimodal model☆5,631Updated 3 months ago
- SkyReels V1: The first and most advanced open-source human-centric video foundation model☆2,645Updated 10 months ago
- ☆1,046Updated 8 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…☆3,399Updated last month
- HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency☆1,089Updated 3 weeks ago
- [NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation☆2,794Updated last month
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆1,873Updated this week
- GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning☆2,162Updated last week
- [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing☆3,625Updated 3 months ago
- Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving stat…☆1,539Updated 7 months ago
- Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)☆1,715Updated 6 months ago
- HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning☆1,127Updated 2 weeks ago