xuyang-liu16 / Awesome-Generation-AccelerationLinks
π Collection of awesome generation acceleration resources.
β302Updated last month
Alternatives and similar repositories for Awesome-Generation-Acceleration
Users that are interested in Awesome-Generation-Acceleration are comparing it to the libraries listed below
Sorting:
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Cachingβ168Updated 4 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsityβ393Updated 2 months ago
- (ToCa-v2) A New version of ToCaοΌwith faster speed and better acceleration!β39Updated 4 months ago
- β171Updated 6 months ago
- This is a repo to track the latest autoregressive visual generation papers.β382Updated last month
- An official implementation of DanceGRPO: Unleashing GRPO on Visual Generationβ555Updated this week
- [CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization forβ¦β103Updated 3 weeks ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeersβ245Updated last month
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationβ109Updated 4 months ago
- [TMLR 2025π₯] A survey for the autoregressive models in vision.β665Updated last week
- Adaptive Caching for Faster Video Generation with Diffusion Transformersβ155Updated 9 months ago
- β13Updated last month
- Scaling Diffusion Transformers with Mixture of Expertsβ356Updated 10 months ago
- [ICLR 2025] Autoregressive Video Generation without Vector Quantizationβ556Updated 3 weeks ago
- GenEval: An object-focused framework for evaluating text-to-image alignmentβ333Updated 5 months ago
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"β390Updated last month
- Curated list of methods that focuses on improving the efficiency of diffusion modelsβ45Updated last year
- [CVPR 2025] π₯ Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".β364Updated 2 weeks ago
- The collection of awesome papers on alignment of diffusion models.β304Updated this week
- Awesome Unified Multimodal Modelsβ513Updated last month
- β84Updated 4 months ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.β670Updated last week
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingβ110Updated last year
- [CVPR 2025 Highlight] TinyFusion: Diffusion Transformers Learned Shallowβ132Updated 4 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional varβ¦β136Updated last month
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationβ374Updated 3 months ago
- Official implementation of UnifiedReward & UnifiedReward-Thinkβ493Updated last week
- An official implementation of Flow-GRPO: Training Flow Matching Models via Online RLβ1,002Updated last week
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.β48Updated last year
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformerβ621Updated 9 months ago