mit-han-lab / hartLinks
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
☆603Updated 8 months ago
Alternatives and similar repositories for hart
Users that are interested in hart are comparing it to the libraries listed below
Sorting:
- An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆783Updated last week
- [ICLR 2025] Autoregressive Video Generation without Vector Quantization☆535Updated last month
- VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE☆333Updated 5 months ago
- Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraini…☆601Updated 2 months ago
- SEED-Voken: A Series of Powerful Visual Tokenizers☆897Updated 4 months ago
- This is a repo to track the latest autoregressive visual generation papers.☆356Updated this week
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆344Updated 3 weeks ago
- Scaling Diffusion Transformers with Mixture of Experts☆340Updated 9 months ago
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆821Updated 3 months ago
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models☆703Updated 2 months ago
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"☆374Updated last week
- This repo contains the code for 1D tokenizer and generator☆918Updated 3 months ago
- VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning☆251Updated 2 months ago
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆367Updated last month
- MMaDA - Open-Sourced Multimodal Large Diffusion Language Models☆1,136Updated 2 weeks ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆651Updated last month
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆370Updated 5 months ago
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆272Updated 2 months ago
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,341Updated this week
- DDT: Decoupled Diffusion Transformer☆258Updated 2 weeks ago
- Official implementation of Inductive Moment Matching☆488Updated 3 months ago
- [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation☆304Updated 3 weeks ago
- Pixel-Space Generative Models☆252Updated last month
- GenEval: An object-focused framework for evaluating text-to-image alignment☆310Updated 3 months ago
- Scalable and memory-optimized training of diffusion models☆1,195Updated 3 weeks ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆288Updated 3 months ago
- [ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image…☆316Updated 3 weeks ago
- Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆207Updated 2 months ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆402Updated 4 months ago
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆520Updated last year