Can you explain the features of this version in detail?

#1
by fridayfairy - opened

Which datasets are this version of the model based on? What are the characteristics compared to the Florence-2 large?

I've trained it on Images generated with Flux dev and Prompt pairs. This model is best for Image to Prompt workflows.

Is there any way i could use it inside comfyui?

Sign up or log in to comment