lliai / Awesome-Efficient-Diffusion-Models
Paper survey of efficient computation for large scale models.
☆30Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for Awesome-Efficient-Diffusion-Models
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆75Updated 4 months ago
- PyTorch code for Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆34Updated 2 months ago
- [ECCV 2024] Official pytorch implementation of "Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts"☆33Updated 4 months ago
- Adapting LLaMA Decoder to Vision Transformer☆27Updated 6 months ago
- Accelerating Diffusion Transformers with Token-wise Feature Caching☆24Updated 2 weeks ago
- This is a repo to track the latest autoregressive visual generation papers.☆50Updated this week
- [NeurIPS 2024] The official implement of research paper "FreeLong : Training-Free Long Video Generation with SpectralBlend Temporal Atten…☆29Updated last week
- ☆16Updated last year
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆91Updated last year
- 📚 Collection of awesome generation acceleration resources.☆43Updated 2 weeks ago
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆89Updated last year
- The collection of awesome papers on alignment of diffusion models.☆53Updated this week
- ☆41Updated 8 months ago
- The official repository of paper "ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection" (N…☆50Updated last year
- ☆52Updated last year
- Code for paper "Unsegment Anything by Simulating Deformation" (CVPR 2024)☆22Updated 5 months ago
- [CVPR 2023] Zero-shot Generative Model Adaptation via Image-specific Prompt Learning☆82Updated last year
- Official GitHub repository for the Text-Guided Video Editing (TGVE) competition of LOVEU Workshop @ CVPR'23.☆73Updated last year
- torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.☆19Updated 7 months ago
- Official PyTorch Code for "Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?" (https://arxiv.org/abs/2305.12954)☆45Updated 11 months ago
- fixed official code for paper "A Closer Look at Parameter-Efficient Tuning in Diffusion Models".☆40Updated last year
- This repository provides an improved LLamaGen Model, fine-tuned on 500,000 high-quality images, each accompanied by over 300 token prompt…☆27Updated last month
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆20Updated last week
- Curated list of methods that focuses on improving the efficiency of diffusion models☆30Updated 4 months ago
- Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitching"☆96Updated 8 months ago
- Training code for CLIP-FlanT5☆19Updated 3 months ago
- ☆55Updated last year
- Official implementation of "Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization"☆75Updated 7 months ago
- Code and Data for Paper: SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data☆32Updated 8 months ago
- Codebase for the paper-Elucidating the design space of language models for image generation☆31Updated last week