thunlp / ACDiT
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
☆31Updated 3 months ago
Alternatives and similar repositories for ACDiT:
Users that are interested in ACDiT are comparing it to the libraries listed below
- HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆54Updated 2 months ago
- [NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective☆66Updated 5 months ago
- TokenBridge: Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation. https://yuqingwang1029.github.io/TokenBridge☆89Updated last week
- The official implementation of OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows☆57Updated last month
- Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]☆79Updated 5 months ago
- ☆157Updated 4 months ago
- ☆30Updated last month
- The official PyTorch implementation for Improving Long-Text Alignment for Text-to-Image Diffusion Models (LongAlign)☆69Updated 6 months ago
- EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.☆90Updated last month
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆86Updated this week
- ☆52Updated 2 weeks ago
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"☆110Updated 2 months ago
- Official Implementation for Diffusion Models Without Classifier-free Guidance☆110Updated 2 months ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆65Updated 2 months ago
- An official pytorch implementation of AAAI 2024 paper "Latent Space Editing in Transformer-based Flow Matching"☆36Updated last year
- Towards training VQ-VAE models robustly!☆68Updated 3 months ago
- [ICLR 2025] Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding☆35Updated last month
- ☆45Updated last month
- Official implementation of HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance☆38Updated this week
- [Interspeech 2024] LiteFocus is a tool designed to accelerate diffusion-based TTA model, now implemented with the base model AudioLDM2.☆33Updated last month
- Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening☆53Updated last month
- Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025)☆66Updated last month
- official code for Diff-Instruct algorithm for one-step diffusion distillation☆71Updated 3 months ago
- FQGAN: Factorized Visual Tokenization and Generation☆47Updated 3 weeks ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆104Updated 3 months ago
- [ICLR 2025] Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching☆43Updated 2 months ago
- Codebase for the paper-Elucidating the design space of language models for image generation☆45Updated 5 months ago
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆108Updated 6 months ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆68Updated last month
- [NeurIPS 2024] Official PyTorch Implementation of "FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner"☆66Updated 6 months ago