hustvl / DiG
[CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
☆156Updated 3 weeks ago
Alternatives and similar repositories for DiG:
Users that are interested in DiG are comparing it to the libraries listed below
- This repository includes the official implementation of our paper "Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generat…☆143Updated 3 weeks ago
- Implements VAR+CLIP for text-to-image (T2I) generation☆129Updated 2 months ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆95Updated 3 months ago
- [ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models☆208Updated 2 months ago
- This is the official implementation for ControlVAR.☆101Updated 3 months ago
- [CVPR 2025] Open implementation of "RandAR"☆65Updated this week
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆88Updated 3 weeks ago
- CAR: Controllable AutoRegressive Modeling for Visual Generation☆107Updated 3 months ago
- [AAAI 2025] Linear-complexity Visual Sequence Learning with Gated Linear Attention☆108Updated 9 months ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆86Updated 5 months ago
- [NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"☆192Updated 5 months ago
- Official Implementation for Diffusion Models Without Classifier-free Guidance☆102Updated last month
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆87Updated last week
- High-performance Image Tokenizers for VAR and AR☆226Updated this week
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆61Updated 3 weeks ago
- Towards training VQ-VAE models robustly!☆62Updated 2 months ago
- Scalable Diffusion Models with State Space Backbone☆152Updated last year
- ☆167Updated last month
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆56Updated last month
- [CVPR2025] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project/☆127Updated this week
- ☆146Updated 3 months ago
- Implementation of the paper "MaskBit: Embedding-free Image Generation from Bit Tokens"☆59Updated 3 weeks ago
- The first decoder-only multimodal state space model☆80Updated this week
- [ICLR 2025] Autoregressive Video Generation without Vector Quantization☆419Updated this week
- [CVPR 2025] Official repository of the paper "Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"☆78Updated 3 weeks ago
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆137Updated last month
- [CVPR 2024] Exploiting Diffusion Prior for Generalizable Dense Prediction☆71Updated 11 months ago
- ☆27Updated 2 weeks ago
- Denoising Diffusion Step-aware Models (ICLR2024)☆57Updated last year
- [CVPR 2024] On the Content Bias in Fréchet Video Distance☆103Updated 5 months ago