blip2 开源项目推荐（61 个）

DAMO-NLP-SG /Video-LLaMA

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

zli12321 /Vision-Language-Models-Overview

一个最前端的视觉语言模型论文集和模型汇总，GitHub 仓库。持续更新。

sled-group /chat-with-nerf

[ICRA 2024] Chat with NeRF enables users to interact with a NeRF model by typing in natural language.

mlpc-ucsd /BLIVA

(AAAI 2024) BLIVA: A Simple Multimodal LLM for Better Handling of Text-rich Visual Questions

gongzix /NeuroClips

[NeurIPS 2024] Official code base for NeuroClips

arashsajjadi /ai-powered-video-analyzer

一款离线AI驱动的视频分析工具，具备对象检测（YOLO）、图片字幕（BLIP）、语音转录（Whisper）、音频事件检测（PANNs）和AI生成摘要（通过Ollama的LLMs）。它通过用户友好的图形界面确保隐私和离线使用。

SmithaUpadhyaya /fashion_image_caption

Automate Fashion Image Captioning using BLIP-2. Automatic generating descriptions of clothes on shopping websites, which can help customers without fashion knowledge to better understand the features (attributes, style, functionality etc.) of the items and increase online sales by enticing more customers.

kyegomez /qformer

Implementation of Qformer from BLIP2 in Zeta Lego blocks.

152334H /MiniGPT-4-discord-bot

A true multimodal LLaMA derivative -- on Discord!

BUAADreamer /SPN4CIR

[ACM MM 2024] Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives

UCSB-AI /ComCLIP

NAACL 2024 论文《ComCLIP：无训练合成图像与文本匹配》的官方实现和数据集

nngocson2002 /ViVQA

The Multimodal Model for Vietnamese Visual Question Answering (ViVQA)

zer0int /CLIP-Interrogator-LongCLIP-hallucinwords

CLIP Interrogator, fully in HuggingFace Transformers 🤗, with LongCLIP & CLIP's own words and / or *your* own words!

ZhaoPeiduo /BLIP2-Japanese

Modifying LAVIS' BLIP2 Q-former with models pretrained on Japanese datasets.

jacobmarks /fiftyone-image-captioning-plugin

Caption images across your datasets with state of the art models from Hugging Face and Replicate!

matlok-ai /bampe-weights

This repository is for profiling, extracting, visualizing and reusing generative AI weights to hopefully build more accurate AI models and audit/scan weights at rest to identify knowledge domains for risk(s).

aws-samples /visual-question-answering-finetuning

Finetuning Large Visual Models on Visual Question Answering

MichiganNLP /visual_diversity_budget

Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost

CogitoNTNU /RizzAI

A Rizz bot that uses AI to help you make good opening lines.

Pavansomisetty21 /Visual-Question-Answering-using-Gemini-LLM

In this we explore into visual Question Answering Using Gemini LLM and image was in URL or any other extension