Vchitect / Optix
Memory Efficient Training Framework for Large Video Generation Model
☆24Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for Optix
- CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method☆26Updated 7 months ago
- ☆30Updated 5 months ago
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆20Updated last week
- Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitching"☆96Updated 8 months ago
- 🔥 Aurora Series: A more efficient multimodal large language model series for video.☆47Updated last week
- Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]☆49Updated last week
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆98Updated 2 weeks ago
- Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding☆23Updated 2 weeks ago
- The official repo of continuous speculative decoding☆18Updated this week
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆41Updated 2 months ago
- TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation☆26Updated 2 weeks ago
- Official Repo for Paper "OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision"☆32Updated last week
- ☆23Updated 2 months ago
- [arXiv 2024] I4VGen: Image as Free Stepping Stone for Text-to-Video Generation☆19Updated last month
- ☆59Updated this week
- ☆65Updated last year
- ☆78Updated 10 months ago
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆55Updated last month
- FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax☆18Updated last year
- ☆38Updated 11 months ago
- ☆35Updated last year
- Codebase for the paper-Elucidating the design space of language models for image generation☆31Updated last week
- ☆31Updated 3 weeks ago
- Official implementation of Aurora☆81Updated last year
- Navigate dreamscapes with a click – your chosen point guides the drone’s flight in a thrilling visual journey.☆42Updated 11 months ago
- [ECCV 2024] This is the official implementation of "Stitched ViTs are Flexible Vision Backbones".☆23Updated 10 months ago
- T2VScore: Towards A Better Metric for Text-to-Video Generation☆78Updated 7 months ago
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆26Updated this week
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆84Updated 4 months ago