thu-ml / TurboDiffusionLinks
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
☆3,087Updated this 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☆1,718Updated this week
- A unified inference and post-training framework for accelerated video generation.☆2,898Updated last week
- ☆1,874Updated 3 weeks ago
- Official inference repo for FLUX.2 models☆1,319Updated last month
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆2,634Updated 2 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,218Updated 7 months ago
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation☆1,198Updated 2 months ago
- MAGI-1: Autoregressive Video Generation at Scale☆3,622Updated 6 months ago
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆1,138Updated last week
- Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"☆1,359Updated last week
- [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆1,343Updated 4 months ago
- Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.☆937Updated this week
- [NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ …☆2,058Updated 3 weeks ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,025Updated 3 weeks ago
- 🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.☆861Updated this week
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,134Updated 5 months ago
- Qwen-Image-Layered: Layered Decomposition for Inherent Editablity☆1,375Updated last week
- CogView4, CogView3-Plus and CogView3(ECCV 2024)☆1,103Updated 9 months ago
- HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo☆1,762Updated 7 months ago
- Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.☆6,875Updated last week
- ☆1,045Updated 7 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,569Updated last week
- Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment☆1,472Updated 4 months ago
- ☆1,981Updated 3 weeks ago
- A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gem…☆2,107Updated 2 weeks ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆883Updated last week
- Native Multimodal Models are World Learners☆1,394Updated last week
- HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning☆1,061Updated 2 weeks ago
- Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving stat…☆1,515Updated 6 months ago
- [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing☆3,550Updated 2 months ago