simonw / blip-caption
Generate captions for images with Salesforce BLIP
☆120Updated 8 months ago
Alternatives and similar repositories for blip-caption:
Users that are interested in blip-caption are comparing it to the libraries listed below
- The repository provides code for training the SegmentAnything Model (SAM) for predicting frame polygons in comic books☆50Updated 11 months ago
- ☆27Updated 6 months ago
- Wikidata's QRank as a SQLite DB.☆28Updated last year
- Simple script that reads an image and dumps the text it reads using a vision model and KobolodCPP☆53Updated last week
- Embedding models from Jina AI☆58Updated last year
- Command-line tool for fetching JSON from paginated APIs☆65Updated last year
- Some tough questions to test new models.☆26Updated 10 months ago
- The LLM plugins directory☆40Updated last year
- CLI for running files through AWS Textract☆54Updated 11 months ago
- Using Datasette and CLIP embeddings to find similar faucets.☆22Updated last year
- Convert a Claude.ai export to SQLite☆47Updated 4 months ago
- Bulk image tagging using OpenAI GPT-4 Vision☆70Updated 7 months ago
- LLM plugin for embeddings using sentence-transformers☆52Updated last month
- Convert a web page to markdown☆66Updated 6 months ago
- llm plugin for Cerebras fast inference API☆23Updated this week
- Better Bookmarks Search w/ Transformers☆190Updated last year
- LLM plugin for models hosted by Anyscale Endpoints☆33Updated 10 months ago
- LLM plugin for models hosted on Replicate☆61Updated 10 months ago
- https://verdad.app☆80Updated 2 months ago
- CLI tool for running text through OpenAI Text to speech☆163Updated last year
- Build a RAG dataset for your domain in just a few lines of codes, using your XML sitemap☆45Updated 6 months ago
- Add website scraping abilities to Datasette☆62Updated 2 years ago
- A copy of ONNX models, datasets, and code all in one GitHub repository. Follow the README to learn more.☆104Updated last year
- Visualizing movie frames as art☆121Updated 4 years ago
- Hubcap is an autonomous AI agent in 25 lines of code: a small Autobot that you can't trust. *This is the Python fork/port* from https://g…☆14Updated last year
- High performance human detector☆23Updated 5 months ago
- Use Datasette to explore LAION improved_aesthetics_6plus training data used by Stable DIffusion☆58Updated last year
- Generate embeddings for images and text using CLIP with LLM☆66Updated 10 months ago
- Plugin for LLM adding support for Anthropic's Claude models☆36Updated 3 months ago
- ☆162Updated 8 months ago