Any plan to support the latest DeepFloyd IF?

[kqwyf]

The latest open-source DeepFloyd IF model shows superior results on understanding text prompts and generating images. Do you have a plan to support it?

Ref: https://github.com/deep-floyd/IF

[josephrocca]

Relevant issue: #9920

[halr9000]

Probably too early for most to bother given the steep memory requirements. 16 to 24 gigabytes depending on the model. Or if running it through transformers:

By default diffusers makes use of model cpu offloading to run the whole IF pipeline with as little as 14 GB of VRAM.

Out of my 3060 w/12gb league!