guandeh17 / Self-ForcingLinks
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
☆3,062Updated 4 months ago
Alternatives and similar repositories for Self-Forcing
Users that are interested in Self-Forcing are comparing it to the libraries listed below
Sorting:
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,172Updated 5 months ago
- A unified inference and post-training framework for accelerated video generation.☆2,962Updated this week
- MAGI-1: Autoregressive Video Generation at Scale☆3,628Updated 7 months ago
- Scalable and memory-optimized training of diffusion models☆1,321Updated 7 months ago
- OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871☆3,999Updated last month
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆2,654Updated 2 months ago
- [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing☆3,578Updated 3 months ago
- HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo☆1,770Updated 8 months ago
- TurboDiffusion: 100–200× Acceleration for Video Diffusion Models☆3,244Updated this week
- Light Image Video Generation Inference Framework☆1,822Updated this week
- Native Multimodal Models are World Learners☆1,399Updated 3 weeks ago
- Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.☆863Updated 4 months ago
- ☆1,921Updated last month
- [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video☆1,711Updated last month
- MMaDA - Open-Sourced Multimodal Large Diffusion Language Models☆1,556Updated 2 months ago
- [ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer☆1,890Updated 6 months ago
- Official inference repo for FLUX.2 models☆1,540Updated this week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,231Updated 7 months ago
- Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model☆2,611Updated last month
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆1,893Updated 2 months ago
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation☆1,200Updated 3 months ago
- [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆1,345Updated 4 months ago
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆650Updated last year
- Open-source unified multimodal model☆5,577Updated 2 months ago
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,539Updated 2 months ago
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆1,181Updated 2 weeks ago
- Lumina-Image 2.0: A Unified and Efficient Image Generative Framework☆852Updated 2 months ago
- Pusa: Thousands Timesteps Video Diffusion Model☆671Updated 4 months ago
- HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning☆1,080Updated 3 weeks ago
- A pipeline parallel training script for diffusion models.☆1,807Updated this week