LargeWorldModel / ElasticTok
ElasticTok: Adaptive Tokenization for Image and Video
☆54Updated 3 months ago
Alternatives and similar repositories for ElasticTok:
Users that are interested in ElasticTok are comparing it to the libraries listed below
- Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?☆103Updated last week
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆50Updated last week
- Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models☆82Updated last year
- ☆116Updated last year
- ☆23Updated 2 weeks ago
- [CVPR 2024] On the Content Bias in Fréchet Video Distance☆103Updated 4 months ago
- A Video Tokenizer Evaluation Dataset☆101Updated last month
- ☆138Updated 2 months ago
- Minimal multi-gpu implementation of EDM2: "Analyzing and Improving the Training Dynamics of Diffusion Models"☆28Updated 11 months ago
- ☆43Updated 5 months ago
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆35Updated 9 months ago
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆95Updated 4 months ago
- ☆51Updated 4 months ago
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆78Updated 2 weeks ago
- [ICML 2024] Compositional Image Decomposition with Diffusion Models☆47Updated 7 months ago
- Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos☆49Updated 6 months ago
- [ICLR 2025][arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization☆127Updated 8 months ago
- Official implementation of "Self-Improving Video Generation"☆60Updated last month
- Collaborative Score Distillation for Consistent Visual Synthesis (NeurIPS 2023)☆113Updated last year
- Official Release of NeurIPS 2023 Spotlight paper "Object-Centric Slot Diffusion"☆63Updated 11 months ago
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆111Updated last year
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆25Updated last week
- [ICCV 2023] Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models☆80Updated last year
- ☆71Updated 4 months ago
- [NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective☆59Updated 3 months ago