Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
| Date | Stars |
|---|---|
| 2026-07-31 | 409 |
| 2026-08-06 | 409 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align=center> # [ICCV 2025] *TaylorSeer*: From Reusing to Forecasting: Accelerating Diffusion Models with *TaylorSeers* <p> <a href='https://arxiv.org/abs/2503.06923'><img src='https://img.shields.io/badge/Paper-arXiv-red'></a> <a href='https://taylorseer.github.io/TaylorSeer/'><img src='https://img.shields.io/badge/Project-Page-blue'></a> </p> </div> ## 🔥 News * `2025/12/06` TaylorSeer is now natively supported in Diffusers. Check out the [doc](https://huggingface.co/docs/diffusers/main/en/optimization/cache#taylorseer-cache). Thanks to @toilaluan for [contributing](https://github.com/huggingface/diffusers/pull/12648) it. * `2025/06/26` 💥💥 TaylorSeer is honored to be accepted by ICCV 2025! * `2025/05/03` 🚀🚀 TaylorSeer for HiDream is released. * `2025/03/30` 🚀🚀 TaylorSeer for Wan2.1 is released. * `2025/03/30` 🚀🚀 The Diffusers inference scripts for TaylorSeers and the xDiT scripts applicable for multi-GPU parallel inference have been officially released. * `2025/03/10` 🚀🚀 Our latest work "From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers" is released! Codes are available at [TaylorSeer](https://github.com/Shenyi-Z/TaylorSeer)! TaylorSeer supports lossless compression at a rate of 4.99x on FLUX.1-dev (with a latency speedup of 3.53x) and high-quality acceleration at a compression rate of 5.00x on HunyuanVideo (with a latency speedup of 4.65x)! We hope *TaylorSeer* can move the paradigm of feature caching methods from reusing to forecasting.For more details, please refer to our latest research paper. * `2025/02/19` 🚀🚀 ToCa solution for **FLUX** has been officially released after adjustments, now achieving up to **3.14× lossless acceleration** (in FLOPs)! * `2025/01/22` 💥💥 ToCa is honored to be accepted by ICLR 2025! * `2024/12/29` 🚀🚀 We release our work [DuCa](https://arxiv.org/abs/2412.18911) about accelerating diffusion transformers for FREE, which achieves nearly lossless acceleration of **2.50×** on [OpenSora](https://github.com/hpcaitech/Open-Sora)! 🎉 **DuCa also overcomes the limitation of ToCa by fully supporting FlashAttention, enabling broader compatibility and efficiency improvements.** * `2024/12/24` 🤗🤗 We release an open-sourse repo "[Awesome-Token-Reduction-for-Model-Compression](https://github.com/xuyang-liu16/Awesome-Token-Reduction-for-Model-Compression)", which collects recent awesome token reduction papers! Feel free to contribute your suggestions! * `2024/12/10` 💥💥 Our team's recent work, **SiTo** (https://github.com/EvelynZhang-epiclab/SiTo), has been accepted to **AAAI 2025**. It accelerates diffusion models through adaptive **Token Pruning**. * `2024/07/15` 🤗🤗 We release an open-sourse repo "[Awesome-Generation-Acceleration](https://github.com/xuyang-liu16/Awesome-Generation-Acceleration)", which collects recent awesome generation accleration papers! Feel free to contribute your suggestions! <details> <summary><strong>Abstract</strong></summary> Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve this problem, feature caching has been proposed to accelerate diffusion models by caching the features in the previous timesteps and then reusing them in the following timesteps. However, at timesteps with significant intervals, the feature similarity in diffusion models decreases substantially, leading to a pronounced increase in errors introduced by feature caching, significantly harming the generation quality. To solve this problem, we propose TaylorSeer, which firstly shows that features of diffusion models at future timesteps can be predicted based on their values at previous timesteps. Based on the fact that features change slowly and continuously across timesteps, TaylorSeer employs a differential method to approximate the higher-order derivatives of features and predict features in future timesteps with Taylor s
Excerpt of 8,986 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bafbaf803750c4d3, llm:Repository title and description: '[ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers' — Python implementation related to accelerating diffusion models (image generation)
matched fp:bafbaf803750c4d3, llm:Repository title and description: '[ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers' — Python implementation related to accelerating diffusion models (image generation)