How do you load textual inversion checkpoints on this?

[sarmientoj24]

In the UI, I was able to load my checkpoints and use it as main prompt. It works wonders.

Additionally, how do I design it so that it is similar to the A1111 workflow:

1. I generate an image with StableDiffusionPipeline
2. Send the image to adetailer with prompt that uses textual inversion token
3. It outputs a refined image

[JemiloII]

The asdff pipeline inherits everything from the stable diffusion Pipeline.

The only difference is that you use the callback pipe(), pass the usual settings to a dict called custom. No need to pass things around. Load the textual inversions as normal.