Red velvet, overstuffed furniture, and cleavage. An aesthetic gradient trained mostly on pictures of Victorian interiors that is brighter than Dark Victorian. It also tends to produce nudity if clothing is not specified in the prompt. The first sample is with the gradient at a reasonable level (.5 and 5 steps) the second is much higher (1.0 and 10 steps).
Description
Base model
FAQ
Comments (6)
Is it capable of producing "hardcore" images? It seems like the sample pictures display scenes that will end up going that way. :P
Not as such. Aesthetic embeddings shift the "mood" of a piece by tweaking color, lighting, and details. Actual hardcore content requires a model trained on that subject.
The fingers are in trouble again. Stable Diffusion generates amazing faces, but I still haven't learned how to make fingers :(
Try to download bad_prompt embedding and use watermark, text, error, blurry, jpeg artifacts, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name, (worst quality, low quality:1.4), bad anatomy, (worst quality, low quality:1.4)
It helps me in 1 of 3 arts
hi, what the difference between the 2 embedding ?
You should really make more. Aesthetic gradients are a lot better than people kmow.