hustvl / DiG
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
☆118Updated 2 months ago
Alternatives and similar repositories for DiG:
Users that are interested in DiG are comparing it to the libraries listed below
- [AAAI 2025] Linear-complexity Visual Sequence Learning with Gated Linear Attention☆106Updated 8 months ago
- Open implementation of "RandAR"☆54Updated last month
- [arXiv'25] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models☆251Updated last month
- This is the official implementation for ControlVAR.☆95Updated 2 months ago
- Official PyTorch implementation of TrackDiffusion (https://arxiv.org/abs/2312.00651)☆76Updated 7 months ago
- [ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models☆194Updated 3 weeks ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆84Updated 4 months ago
- Denoising Diffusion Step-aware Models (ICLR2024)☆56Updated last year
- CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆75Updated 3 weeks ago
- Implements VAR+CLIP for text-to-image (T2I) generation☆119Updated 3 weeks ago
- [ICLR 2024] Official PyTorch/Diffusers implementation of "Object-aware Inversion and Reassembly for Image Editing"☆84Updated 5 months ago
- Liquid: Language Models are Scalable Multi-modal Generators☆65Updated 2 months ago
- [CVPR 2024] Exploiting Diffusion Prior for Generalizable Dense Prediction☆70Updated 10 months ago
- Official PyTorch implementation of GeoDiffusion in ICLR 2024 (https://arxiv.org/abs/2306.04607)☆74Updated last month
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆83Updated 7 months ago
- Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation (ICCV 2023)☆63Updated last year
- ReNeg: Learning Negative Embedding with Reward Guidance☆28Updated last month
- ☆10Updated 3 months ago
- ☆38Updated last year
- Official repository of the paper "Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"☆44Updated 3 weeks ago
- [Neurips 2024] Video Diffusion Models are Training-free Motion Interpreter and Controller☆33Updated this week
- [ICLR2025]☆137Updated 3 weeks ago
- ☆16Updated last year
- The official implementation of "[MASK] is All You Need"☆106Updated 2 weeks ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆89Updated last month
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆136Updated this week
- CAR: Controllable AutoRegressive Modeling for Visual Generation☆102Updated 2 months ago
- Implementation of the paper "MaskBit: Embedding-free Image Generation from Bit Tokens"☆48Updated 3 weeks ago