LeapLabTHU / ImprovedNATLinks
A PyTorch implementation of the paper "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis"
☆46Updated 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 last year
- CODA: Repurposing Continuous VAEs for Discrete Tokenization☆33Updated 4 months ago
- [CVPR 2025] HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation☆56Updated 4 months ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆87Updated last year
- Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"☆155Updated 3 weeks ago
- Autoregressive Image Generation with Randomized Parallel Decoding☆81Updated 3 weeks ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆96Updated 9 months ago
- (ICCV 2025) "Principal Components" Enable A New Language of Images☆72Updated 3 months ago
- [NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective☆72Updated last year
- [NeurIPS 2024] ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis☆24Updated 11 months ago
- Codebase for the paper-Elucidating the design space of language models for image generation☆46Updated last year
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆107Updated last month
- [ECCV 2024] Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators☆45Updated last year
- Denoising Diffusion Step-aware Models (ICLR2024)☆62Updated last year
- The official implementation of "[MASK] is All You Need"☆125Updated 3 months ago
- (SRA) No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves☆94Updated 3 months ago
- [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think☆184Updated last month
- official training and inference code of bitwise tokenizer☆51Updated 6 months ago
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆36Updated 9 months ago
- [NeurIPS 24] Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models☆43Updated last year
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆39Updated 9 months ago
- Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"☆185Updated 5 months ago
- ☆89Updated 7 months ago
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆71Updated 2 months ago
- Implementation of the paper "MaskBit: Embedding-free Image Generation from Bit Tokens"☆88Updated 7 months ago
- Official PyTorch implementation of the paper "Equivariant Image Modeling"(https://arxiv.org/abs/2503.18948)☆34Updated 3 months ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆200Updated 4 months ago
- This is the official implementation for ControlVAR.☆123Updated 11 months ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆160Updated 6 months ago
- Scalable Diffusion Models with State Space Backbone☆156Updated last year