xuyang-liu16 / Awesome-Generation-Acceleration
π Collection of awesome generation acceleration resources.
β215Updated this week
Alternatives and similar repositories for Awesome-Generation-Acceleration:
Users that are interested in Awesome-Generation-Acceleration are comparing it to the libraries listed below
- Accelerating Diffusion Transformers with Token-wise Feature Cachingβ132Updated last month
- Adaptive Caching for Faster Video Generation with Diffusion Transformersβ145Updated 5 months ago
- β160Updated 3 months ago
- This is a repo to track the latest autoregressive visual generation papers.β272Updated last week
- From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeersβ72Updated 3 weeks ago
- Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsityβ178Updated last week
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationβ77Updated last month
- [TMLR 2025π₯] A survey for the autoregressive models in vision.β508Updated this week
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional varβ¦β125Updated 2 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingβ101Updated 9 months ago
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Trainingβ178Updated 2 months ago
- [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationβ284Updated last month
- [CVPR 2025] π₯ Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".β316Updated last month
- [CVPR 2024 Highlight] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Moβ¦β62Updated 8 months ago
- (ToCa-v2) A New version of ToCaοΌwith faster speed and better acceleration!β31Updated last month
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficientβ98Updated 3 weeks ago
- β69Updated 3 weeks ago
- Official implementation of Unified Reward Model for Multimodal Understanding and Generation.β242Updated this week
- [ICLR 2025] Autoregressive Video Generation without Vector Quantizationβ477Updated this week
- Scaling Diffusion Transformers with Mixture of Expertsβ311Updated 7 months ago
- Implementation of Post-training Quantization on Diffusion Models (CVPR 2023)β136Updated 2 years ago
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationβ299Updated this week
- The collection of awesome papers on alignment of diffusion models.β190Updated this week
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"β240Updated this week
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.β45Updated 9 months ago
- Curated list of methods that focuses on improving the efficiency of diffusion modelsβ44Updated 9 months ago
- π This is a repository for organizing papers, codes, and other resources related to unified multimodal models.β173Updated 2 weeks ago
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representationsβ140Updated 2 months ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.β488Updated this week
- GenEval: An object-focused framework for evaluating text-to-image alignmentβ232Updated last month