GPT4V Image Captioner image marking processing tool

This project by Jiaye, LEOSAM is a rabbit, sleeePyZhou, Co-developed by Fok

.

Please click this Github link on the project homepage, future Major iterations will be carried out on libLibai, and quick improvements to small versions will be made on Github.

For detailed instructions on how to use the software, please refer to the one I just posted Station B video.

This is also the first video on my Station B AI channel. Everyone is welcome to play 3 times with 1 click~ The special features of this software include: • One-click installation and use • Single

Image inversion and batch marking functions

• Cloud GPT4 & local CogVLM dual models optional • Visual label analysis and processing •

Image bucket pre-compression

• Keyword screening and watermark

image recognition If you think this project is helpful to you, you are welcome to give this project a small Star on GitHub. Thank you all!

V1.1 update content:

1. A bunch of minor bugs have been fixed. Currently, features such as adding new tags and running cogvlm under Linux can be used normally

.

2. Added a free Chinese translation option

.