thu-ml / DiT-ExtrapolationLinks
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) and "UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers"
☆768Updated 3 weeks ago
Alternatives and similar repositories for DiT-Extrapolation
Users that are interested in DiT-Extrapolation are comparing it to the libraries listed below
Sorting:
- ☆416Updated 9 months ago
- Video generation from text&image, 1st-gen☆921Updated 7 months ago
- Unified Multimodal Model for image generation/editing/understanding☆818Updated 3 months ago
- [CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation☆1,223Updated 5 months ago
- Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models☆914Updated 9 months ago
- [ICCV 2025] Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥☆617Updated 2 weeks ago
- HunyuanVideo-1.5: A leading lightweight video generation model☆2,021Updated last week
- Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling☆1,076Updated last month
- ✨ WithAnyone is capable of generating high-quality, controllable, and ID consistent images☆539Updated last week
- An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation☆1,347Updated 2 months ago
- Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple te…☆1,105Updated 10 months ago
- The official implementation of RealisDance☆608Updated 6 months ago
- Echo-4o☆462Updated 2 weeks ago
- [CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition☆792Updated 3 months ago
- MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE☆1,070Updated 2 months ago
- Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model☆916Updated this week
- 🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX☆280Updated 5 months ago
- UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer☆822Updated 7 months ago
- Implementation of paper: Flux Already Knows – Activating Subject-Driven Image Generation without Training☆139Updated 3 months ago
- Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, C…☆316Updated last year
- [ICLR'25] 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation☆364Updated 5 months ago
- [NeurIPS 2025 Spotlight] Towards Understanding Camera Motions in Any Video☆250Updated last month
- [NeurIPS 2025] Official implementation of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulatio…☆616Updated 2 months ago
- Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".☆1,179Updated 8 months ago
- ☆899Updated last year
- Efficient DiT architecture for text2any tasks, ICLR2025☆449Updated 7 months ago
- [CVPR 2025] A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation☆304Updated 9 months ago
- Official implementation for "Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model" (NeurIPS 2024)☆256Updated 8 months ago
- Official implementation of "JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization"☆302Updated 3 weeks ago
- Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning☆168Updated 2 months ago