Vchitect / LiteGen
A light-weight and high-efficient training framework for accelerating diffusion tasks.
☆41Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for LiteGen
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆91Updated 2 weeks ago
- minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora☆38Updated 7 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆75Updated 4 months ago
- ☆100Updated last month
- ☆193Updated 4 months ago
- 🔥 Aurora Series: A more efficient multimodal large language model series for video.☆47Updated this week
- Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitching"☆96Updated 8 months ago
- Memory Efficient Training Framework for Large Video Generation Model☆24Updated 6 months ago
- TerDiT: Ternary Diffusion Models with Transformers☆62Updated 5 months ago
- FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆159Updated last week
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆84Updated 4 months ago
- T2VScore: Towards A Better Metric for Text-to-Video Generation☆77Updated 7 months ago
- Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]☆36Updated this week
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆164Updated last month
- VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆137Updated 3 weeks ago
- The official implementation of Latte: Latent Diffusion Transformer for Video Generation.☆32Updated 8 months ago
- Official code for 'Paragraph-to-Image Generation with Information-Enriched Diffusion Model'☆94Updated 6 months ago
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆38Updated 4 months ago
- [NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models☆107Updated last week
- Unified Multi-modal IAA Baseline and Benchmark☆70Updated last month
- 🏞️ Official implementation of "Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition"☆102Updated 6 months ago
- Scaling RWKV-Like Architectures for Diffusion Models☆117Updated 7 months ago
- Video-Infinity generates long videos quickly using multiple GPUs without extra training.☆163Updated 3 months ago
- ☆16Updated last year
- faster parallel inference of mochi-1 video generation model☆73Updated this week
- CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method☆26Updated 6 months ago
- [NeurIPS 2024] Efficient Multi-modal Models via Stage-wise Visual Context Compression☆39Updated 3 months ago
- [Arxiv 2024] Official pytorch implementation of "VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion…☆147Updated 7 months ago
- 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
- Patch convolution to avoid large GPU memory usage of Conv2D☆79Updated 5 months ago