Replies: 2 comments
-
We are not planning to do such comparison since there are more and more powerful VLMs, such as LLaVA 1.5 or Mini-GPT v2. Maybe directly update the LLaVA-captions to more powerful captioners is a better choice. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi and thanks for the amazing contribution
I am curious to hear if you also tried or compared MplugOwl visual LLM to refine the image captions other than LLaVA and which one you saw is better, pros and cons
thank you
Beta Was this translation helpful? Give feedback.
All reactions