How to use attention_mask and encoder_attention_mask or apply prompts to specific areas in the image?

Hi, I'm aware of the attention_mask and encoder_attention_mask that exist in the forward function of the UNet2DConditionModel yet there are no examples on how to use this

I would appreciate some help on that, thank you in advance
@patrickvonplaten @Birch-san

Start with the UNet2DConditionModel forward function and inspect the attention_mask and encoder_attention_mask parameters mentioned in the issue. Determine what usage guidance or examples are needed for applying prompts to specific image areas; done means the supported behavior is clearly documented with a usable example.

Scritto dal modello di indicizzazione a partire dal testo della issue.