A test for generating wetlook images
Description
FAQ
Comments (4)
you should train this more using these negative prompts:
(((close-to-any-water, bathing, standing-in-water)))
A lot of the training images have the woman standing in water so SD will naturally want to reproduce that even though it isn't specifically mentioned in the image captions.
You can't actually "train" with negative prompts so I guess you mean negative prompting in SD. The ones you mention would probably help quite a bit. Cheers.
@FrozenGunner thanks for that. i never trained a model, so i don't know that you can't use negative prompts.
i once made a style with just prompting it 1:1 to this model here and i used those negative prompts. that's why i was simply posting it.
For some reason, this won't load in ComfyUI - I get lots of "lora key not loaded" messages, followed by ones about a shape being invalid for input of a given size. Any idea what's with that?
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.