Caption-Anything icon indicating copy to clipboard operation
Caption-Anything copied to clipboard
verified publisher icon ttengwang

About interaction

Open PilgrimMay opened this issue 2 years ago • 5 comments

Could this work achieve caption everything without any interaction like SAM?

PilgrimMay avatar Apr 18 '23 06:04 PilgrimMay

@PilgrimMay Thank you for your suggestion. Currently, the repository does not support captioning "everything" in a dense caption format. However, we will be adding this feature within the next few days.

ttengwang avatar Apr 18 '23 17:04 ttengwang

Thanks for your continuous upgrading. Note that this job now seems to support caption everything. Is it possible to try this function in the demo?

PilgrimMay avatar May 05 '23 06:05 PilgrimMay

yes, try demo with chatGPT

ttengwang avatar May 06 '23 15:05 ttengwang

OK! Thanks for your excellent work. Would you release the code about training? So that I could train my own datasets.

PilgrimMay avatar May 08 '23 02:05 PilgrimMay

Hi, the model combines pretrained models like SAM, ChatGPT, and BLIP-2 for interactive usage. No additional training is needed. Please refer to the paper at https://arxiv.org/pdf/2305.02677.pdf for more details, and the Acknowledgement Section in the Readme for the official training code of each pretrained model .

ttengwang avatar May 18 '23 15:05 ttengwang