LeapLabTHU / ImprovedNATLinks
A PyTorch implementation of the paper "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis"
☆45Updated last year
Alternatives and similar repositories for ImprovedNAT
Users that are interested in ImprovedNAT are comparing it to the libraries listed below
Sorting:
- [ECCV 2024] AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation☆34Updated 9 months ago
- CODA: Repurposing Continuous VAEs for Discrete Tokenization☆20Updated 3 months ago
- [NeurIPS 2024] ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis☆23Updated 7 months ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆72Updated 4 months ago
- Denoising Diffusion Step-aware Models (ICLR2024)☆61Updated last year
- [NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective☆69Updated 7 months ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆87Updated 8 months ago
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆35Updated 4 months ago
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆33Updated 4 months ago
- Codebase for the paper-Elucidating the design space of language models for image generation☆45Updated 7 months ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆75Updated 3 months ago
- HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆63Updated 4 months ago
- official training and inference code of bitwise tokenizer☆30Updated last month
- FQGAN: Factorized Visual Tokenization and Generation☆49Updated 2 months ago
- Autoregressive Image Generation with Randomized Parallel Decoding☆67Updated 2 months ago
- Code for paper "Principal Components" Enable A New Language of Images☆44Updated 2 weeks ago
- [ECCV 2024] Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators☆44Updated 9 months ago
- [CVPR 25] A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.☆30Updated 2 months ago
- Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"☆80Updated 2 weeks ago
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆102Updated 2 months ago
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆114Updated 8 months ago
- Minimal multi-gpu implementation of EDM2: "Analyzing and Improving the Training Dynamics of Diffusion Models"☆32Updated last year
- Implementation of the paper "MaskBit: Embedding-free Image Generation from Bit Tokens"☆78Updated 2 months ago
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆41Updated 2 weeks ago
- ☆78Updated 3 months ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆175Updated 3 months ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆125Updated last month
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆37Updated 3 months ago
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆90Updated 2 years ago
- Official repository of InLine attention (NeurIPS 2024)☆49Updated 6 months ago