Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
-
Updated
May 29, 2024 - Python
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
Using Segment-Anything and CLIP to generate pixel-aligned semantic features.
A goal-oriented planning to lift VLN performance for Closed-Loop Navigation: Simple, Yet Effective
Clipora is a powerful toolkit for fine-tuning OpenCLIP models using Low Rank Adapters (LoRA).
use SAM and OpenCLIP to perform zero-shot object detection using COCO 2017 val split.
A simple open-sourced SigLIP model finetuned on Genshin Impact's image-text pairs.
Text-to-image search with OpenCLIP, Docker, Flask, Faiss, etc. and a basic front-end.
Group images by provided labels using OpenAI/CLIP
Searching Images: From Clip And Beyond
CLIP based Zero Shot Instance Segmentation
Using Docker compose to start up Triton with the OpenClip model, to encode text in to vectors
Add a description, image, and links to the openclip topic page so that developers can more easily learn about it.
To associate your repository with the openclip topic, visit your repo's landing page and select "manage topics."