Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
ovi054 
posted an update 28 days ago
Post
5191
Image-to-Prompt⚡

ovi054/image-to-prompt

Extract text prompt from image. And you can reuse the prompt to generate similar images!

Useful for prompt engineering, studying image-to-text alignment, making training datasets, or recreating similar outputs.

Powered by: Gradio, Florence 2

👉 Try it now: ovi054/image-to-prompt
inflatebot

This, being charitable, is just prompt-oriented image captioning. It doesn't "extract" anything from anything. It provides decent descriptions, but only as good as Florence 2 can do.
There's nothing wrong with any of that inherently, it can still be useful, but claiming it to be a "prompt extractor" is misleading IMO.

Also most of these reactions are from... yourself?

AI-Joe-git

First of all, it is not a prompt extractor at all, and secondly, you could have used Qwen2.5 VL instead of Florence 2, which is clearly outdated, and you'll have much better results

Yi3852
•
edited 26 days ago

i made a similar demo for text2music which extracts some tags and lyrics for a song
gradio: http://47.121.209.64/mufun_demo_acestep
finetuned model weights: https://huggingface.co/Yi3852/MuFun-ACEStep
https://github.com/ace-step/ACE-Step/issues/313

In this post