Popular repositories Loading

1. xDiT xDiT Public

   Forked from xdit-project/xDiT

   xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

   Python

2. onediff onediff Public

   Forked from siliconflow/onediff

   OneDiff: An out-of-the-box acceleration library for diffusion models.

   Jupyter Notebook

3. ParaAttention ParaAttention Public

   Forked from chengzeyi/ParaAttention

   https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

   Python

4. SageAttention SageAttention Public

   Forked from thu-ml/SageAttention

   Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

   Cuda

5. DiffSynth-Studio DiffSynth-Studio Public

   Forked from modelscope/DiffSynth-Studio

   Enjoy the magic of Diffusion models!

   Python

6. ViDiT-Q ViDiT-Q Public

   Forked from FasterProcess/ViDiT-Q

   [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

   Python