kyegomez / NaViT
My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"
☆185Updated last week
Related projects ⓘ
Alternatives and complementary repositories for NaViT
- [CVPR 2024] CapsFusion: Rethinking Image-Text Data at Scale☆194Updated 8 months ago
- VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks☆367Updated 4 months ago
- [NeurIPS'24 Spotlight] EVE: Encoder-Free Vision-Language Models☆231Updated last month
- ☆127Updated 2 weeks ago
- [CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"☆175Updated 5 months ago
- MoVQGAN - model for the image encoding and reconstruction☆197Updated last year
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆389Updated last week
- Explore the Limits of Omni-modal Pretraining at Scale☆89Updated 2 months ago
- When do we not need larger vision models?☆336Updated this week
- The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A su…☆178Updated 3 weeks ago
- Densely Captioned Images (DCI) dataset repository.☆159Updated 4 months ago
- [ICLR2024] The official implementation of paper "VDT: General-purpose Video Diffusion Transformers via Mask Modeling", by Haoyu Lu, Guoxi…☆209Updated 6 months ago
- MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer☆197Updated 7 months ago
- [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"☆213Updated 3 weeks ago
- ☆131Updated 10 months ago
- Diffusion Feedback Helps CLIP See Better☆215Updated 2 months ago
- Harnessing 1.4M GPT4V-synthesized Data for A Lite Vision-Language Model☆246Updated 4 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆207Updated 2 months ago
- ☆193Updated 4 months ago
- ☆289Updated 9 months ago
- ☆105Updated 3 months ago
- This repo contains the code for 1D tokenizer and generator☆548Updated this week
- OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text☆274Updated this week
- LaVIT: Empower the Large Language Model to Understand and Generate Visual Content☆532Updated last month
- [CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers☆526Updated 3 weeks ago
- Official implementation of the Law of Vision Representation in MLLMs☆131Updated this week
- LLaVA-HR: High-Resolution Large Language-Vision Assistant☆212Updated 3 months ago
- Implementation of PALI3 from the paper PALI-3 VISION LANGUAGE MODELS: SMALLER, FASTER, STRONGER"☆142Updated last week
- ✨✨Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models☆137Updated last week
- LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images☆318Updated last month