Prediction mode

[hardikdava]

Search before asking

• I have searched the Multimodal Maestro issues and found no similar feature requests.

Description

Currently, it is only possible to finetune models. But it would be amazing to have predict mode where user can utilize base model functionality without much efforts. Something like florence-2 supports different basic tasks such as image caption, object detection, classification, etc.

Use case

• Image caption mode can easily be used to finetune flux for text2image.

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[SkalskiP]

Hi @hardikdava 👋🏻 long time no see! That's the plan! Due to other tasks, I've been a bit less focused on maestro for the past few weeks, but I'm back and I hope to add this model soon.