sayakpaul / diffusers-torchao
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
☆334Updated last month
Alternatives and similar repositories for diffusers-torchao:
Users that are interested in diffusers-torchao are comparing it to the libraries listed below
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆254Updated 5 months ago
- Context parallel attention that accelerates DiT model inference with dynamic caching☆222Updated this week
- Faster generation with text-to-image diffusion models.☆211Updated 5 months ago
- ☆270Updated 2 months ago
- faster parallel inference of mochi-1 video generation model☆112Updated 3 weeks ago
- Enhance-A-Video: Better Generated Video for Free☆474Updated last week
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆388Updated 3 weeks ago
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆447Updated 3 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆191Updated last month
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆537Updated last week
- Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"☆372Updated this week
- ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral)☆566Updated last week
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆202Updated 2 months ago
- Memory-optimized training library for diffusion models☆982Updated this week
- Training-free Regional Prompting for Diffusion Transformers 🔥☆591Updated 3 months ago
- ☆426Updated 11 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆1,000Updated last week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆388Updated last month
- ☆444Updated 3 months ago
- Generate long weighted prompt embeddings for Stable Diffusion☆110Updated 6 months ago
- IP Adapter Instruct☆202Updated 7 months ago
- The code and models for the paper: Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis☆167Updated 2 months ago
- ☆464Updated this week
- Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆199Updated last month
- Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation☆513Updated 6 months ago
- HunyuanVideo GP: Large Video Generation Model - GPU Poor version☆372Updated last week
- A pipeline parallel training script for diffusion models.☆729Updated this week
- ☆124Updated 2 weeks ago
- Rectified Flow Inversion (RF-Inversion) - ICLR 2025☆370Updated this week