xuyang-liu16 / Awesome-Generation-Acceleration
π Collection of awesome generation acceleration resources.
β182Updated 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 Cachingβ115Updated 2 weeks ago
- β155Updated 2 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformersβ144Updated 4 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationβ71Updated last week
- β140Updated this week
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingβ98Updated 8 months ago
- [CVPR 2024 Highlight] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Moβ¦β61Updated 8 months ago
- [TMLR 2025π₯] A survey for the autoregressive models in vision.β462Updated last week
- [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationβ262Updated last month
- π Collection of token reduction for model compression resources.β47Updated last week
- This is a repo to track the latest autoregressive visual generation papers.β193Updated this week
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Trainingβ177Updated 2 months ago
- From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeersβ50Updated 2 weeks ago
- (ToCa-v2) A New version of ToCaοΌwith faster speed and better acceleration!β30Updated 3 weeks ago
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationβ255Updated 2 months ago
- The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"β37Updated last month
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional varβ¦β121Updated last month
- This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"β46Updated last week
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.β43Updated 8 months ago
- Scaling Diffusion Transformers with Mixture of Expertsβ304Updated 6 months ago
- Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"β299Updated 3 months ago
- β60Updated last week
- [ICLR 2025] Autoregressive Video Generation without Vector Quantizationβ445Updated this week
- [CVPR 2025] π₯ Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".β296Updated 3 weeks ago
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficientβ93Updated this week
- βοΈ Accelerating Vision Diffusion Transformers with Skip Branches.β64Updated this week
- QuEST: Efficient Finetuning for Low-bit Diffusion Modelsβ41Updated 2 months ago
- Curated list of methods that focuses on improving the efficiency of diffusion modelsβ41Updated 8 months ago
- Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".β83Updated 3 weeks ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.β385Updated 2 weeks ago