SDXL has two text encoders. I see the latest training config on patreon is training both of them. H
SDXL has two text encoders. I see the latest training config on patreon is training both of them. How does this work when prompting? Particularly when using the
sdxl_gen_img script from kohya? I see in diffusers people leverage both of the text encoders by actually sending in two prompts (and optionally two negative prompts). I'm guessing that using just a single prompt will only leverage one of the text encoders?
