Roblox / SmoothCache
Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.
☆41Updated last week
Alternatives and similar repositories for SmoothCache:
Users that are interested in SmoothCache are comparing it to the libraries listed below
- DiT for VAE (and Video Generation)☆32Updated 7 months ago
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆46Updated 6 months ago
- CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method☆26Updated 11 months ago
- TerDiT: Ternary Diffusion Models with Transformers☆69Updated 9 months ago
- Distilling Diversity and Control in Diffusion Models☆33Updated last week
- Official repository for VQDM:Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization paper☆33Updated 6 months ago
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆89Updated 3 weeks ago
- Finetuning and inference tools for the CogView4 and CogVideoX model series.☆29Updated this week
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆43Updated 8 months ago
- [NeurIPS 2024] Official PyTorch Implementation of "FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner"☆66Updated 6 months ago
- [ICLR 2025] Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stit…☆100Updated last year
- ☆83Updated 7 months ago
- [WACV 2025] MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning☆80Updated 4 months ago
- ☆82Updated 4 months ago
- UniCon: A Simple Approach to Unifying Diffusion-based Conditional Generation (ICLR 2025)☆24Updated 3 weeks ago
- Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]☆77Updated 4 months ago
- Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening☆52Updated last month
- The official repo of continuous speculative decoding☆25Updated this week
- An official implementation of SwapAnyone.☆56Updated 2 weeks ago
- The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"☆32Updated 2 weeks ago
- Official Implementation of GrounDiT (NeurIPS 2024)☆49Updated 3 months ago
- code for "TVG: A Training-free Transition Video Generation Method with Diffusion Models"☆41Updated 7 months ago
- faster parallel inference of mochi-1 video generation model☆112Updated last month
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆28Updated 4 months ago
- Official code of "LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer"☆43Updated last month
- Memory Efficient Training Framework for Large Video Generation Model☆25Updated 11 months ago
- TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation☆29Updated 4 months ago
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (arXiv, 2024)☆50Updated 4 months ago
- Official implementation of "VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis"☆19Updated 2 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆144Updated 4 months ago