drbh/capcap

📸 AI image captions. Built on 🤗 candle and poem

Rust

1

4 commits

updated Nov 8, 2023

README

capcap

https://github.com/drbh/capcap/assets/9896130/28947bec-efe7-49d9-99d2-9a294f0de5b2

Description

Ever wished for your computer to describe a picture's caption? AI makes it possible now!

Stack

blip vision model
candle to run the model
poem as http server
vanilla js for frontend
deployed without GPU (single shared-1x-cpu@1024MB)

Try it out at capcap.drbh.xyz

Contributors

4 commits

Similar repos

radames/Candle-BLIP-Image-Captioning

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

32

Etto48/CVProject

An LLM for captioning images

0

sherlcok314159/ImageCaption

This repository provides the code used for image caption which combines the CLIP and current LLMs.

0

m87-labs/moondream

tiny vision language model

10,048

Salesforce/blip-image-captioning-base

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and…

889

zeinhasan/Vision-Language-Model-Image-to-Text-Generation

Vision Language Model - Image to Text Generation

0

Agent-Eval-Refine/Captioner

A Dense Captioner optimized for Graphical User Interface

2

AdamShuo/joycaption_webui

Joy Caption WebUI 是一个基于 LLaVA 模型的图像标注工具，可以为图像生成详细的描述性标注。

21

Languages

Rust

56.0%

HTML

34.2%

Makefile

4.4%

Dockerfile

4.1%

Shell

1.3%

drbh/capcap

📸 AI image captions. Built on 🤗 candle and poem

Rust

1

4 commits

updated Nov 8, 2023

README

capcap

https://github.com/drbh/capcap/assets/9896130/28947bec-efe7-49d9-99d2-9a294f0de5b2

Description

Ever wished for your computer to describe a picture's caption? AI makes it possible now!

Stack

blip vision model
candle to run the model
poem as http server
vanilla js for frontend
deployed without GPU (single shared-1x-cpu@1024MB)

Try it out at capcap.drbh.xyz

Similar repos

radames/Candle-BLIP-Image-Captioning

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

32

Etto48/CVProject

An LLM for captioning images

0

sherlcok314159/ImageCaption

This repository provides the code used for image caption which combines the CLIP and current LLMs.

0

m87-labs/moondream

tiny vision language model

10,048

Salesforce/blip-image-captioning-base

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and…

889

zeinhasan/Vision-Language-Model-Image-to-Text-Generation

Vision Language Model - Image to Text Generation

0

Agent-Eval-Refine/Captioner

A Dense Captioner optimized for Graphical User Interface

2

AdamShuo/joycaption_webui

Joy Caption WebUI 是一个基于 LLaVA 模型的图像标注工具，可以为图像生成详细的描述性标注。

21

Contributors

4 commits

Languages

Rust

56.0%

HTML

34.2%

Makefile

4.4%

Dockerfile

4.1%

Shell

1.3%