Work in progress

Similar hacking to our opendiffusionai/stablediffusionxl_t5 model

But, with SD1.5 of course.

Why do this? Because coming up with a usable finetuning script for SDXL is turning out to be a pain in the rear. So I thought I might regress to the theoretically easier experiment.

Precision

Note that the unet is only bf16 at this time

Usage

You can use it with the sample code in demo.py

Note that it will give you an image of SOMETHING... however, it is sort of random output at this point. The unet needs to be retrained to get things to match up.

Sample

here's how random the output looks. (its equivalent to putting random strings into an sd1.5 prompt I'd guess)

Prompt: "a misty Tokyo alley at night"