lucasjinreal / ImageTokenizerLinks
imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video.
☆37Updated last year
Alternatives and similar repositories for ImageTokenizer
Users that are interested in ImageTokenizer are comparing it to the libraries listed below
Sorting:
- LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.☆37Updated last year
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆43Updated last year
- The official repo of continuous speculative decoding☆30Updated 7 months ago
- Triton implement of bi-directional (non-causal) linear attention☆56Updated 9 months ago
- Implementation of the proposed MaskBit from Bytedance AI☆82Updated last year
- Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"☆54Updated 9 months ago
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆50Updated last year
- Train vector quantized CLIP models using pytorch lightning☆20Updated last year
- 😊 TPTT: Transforming Pretrained Transformers into Titans☆29Updated last month
- ☆90Updated last year
- Official repository for ICML 2024 paper "MoRe Fine-Tuning with 10x Fewer Parameters"☆21Updated last month
- Code for paper "Patch-Level Training for Large Language Models"☆93Updated last week
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆34Updated last year
- The official implementation of the paper "Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation"☆20Updated 11 months ago
- Pytorch implementation of HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models☆28Updated last year
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆45Updated 4 months ago
- [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…☆104Updated last year
- ☆71Updated 11 months ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆181Updated last year
- TerDiT: Ternary Diffusion Models with Transformers☆71Updated last year
- Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]☆93Updated 3 months ago
- Scaling RWKV-Like Architectures for Diffusion Models☆138Updated last year
- minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora☆40Updated last year
- ☆75Updated last year
- Video dataset dedicated to portrait-mode video recognition.☆53Updated last month
- [ICML 2025] Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆103Updated 5 months ago
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆53Updated 8 months ago
- Official code for infimm-hd☆16Updated last year
- [EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner☆143Updated 5 months ago
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆40Updated 8 months ago