Shenyi-Z / TaylorSeerLinks
[ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
☆339Updated 3 months ago
Alternatives and similar repositories for TaylorSeer
Users that are interested in TaylorSeer are comparing it to the libraries listed below
Sorting:
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆195Updated 8 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆590Updated 2 weeks ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆559Updated 3 weeks ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆148Updated 5 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆161Updated last year
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆253Updated 11 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆258Updated 4 months ago
- ☆187Updated 10 months ago
- (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!☆39Updated 8 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆396Updated 5 months ago
- 📚 Collection of awesome generation acceleration resources.☆368Updated 4 months ago
- Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.☆81Updated last month
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆212Updated 2 months ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆296Updated 2 months ago
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆260Updated 2 months ago
- [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation☆592Updated last week
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆52Updated last year
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆208Updated 2 months ago
- Code for Draft Attention☆94Updated 6 months ago
- [ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image…☆337Updated last month
- Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆52Updated last month
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆228Updated 2 weeks ago
- [ICCV 2025][Few-Step Student Surpasses Teacher Diffusion] Learning Few-Step Diffusion Models by Trajectory Distribution Matching☆62Updated last month
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆138Updated 8 months ago
- ☆573Updated 3 weeks ago
- 🤗A PyTorch-native Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs: Z-Image, FLUX2, Qwen-Image, etc.☆676Updated this week
- Unofficial extension implementation of CausVid☆66Updated 7 months ago
- Official code for ICCV 2025 paper, X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distill…☆88Updated 5 months ago
- Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"☆144Updated last month
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆642Updated last year