开放源码的无App推送服务，iOS14+扫码即用。亦支持快应用/iOS和Mac客户端、Android客户端、自制设备

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

OpenMMLab Pre-training Toolbox and Benchmark

Image to prompt with BLIP and CLIP

Effortless data labeling with AI support from Segment Anything and other awesome models.

中文nlp解决方案(大模型、数据、模型、训练、推理)

Easily compute clip embeddings and build a clip retrieval system with them

Android UI 快速开发，专治原生控件各种不服

Collection of AWESOME vision-language models for vision tasks

Must-have resource for anyone who wants to experiment with and build on the OpenAI vision API 🔥

🥂 Gracefully face hCaptcha challenge with MoE(ONNX) embedded solution.

Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).

Stable Diffusion in NCNN with c++, supported txt2img and img2img

Search photos on Unsplash using natural language

"Video-ChatGPT" is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

Search inside YouTube videos using natural language

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"