This is an embedding to provide a loose digital painting style
I highly recommend the new V2 embedding - it is much more flexible, with far fewer odd artifacts. V1 had a heavy leaning toward medieval classical themes and artifacts that required extensive positive and negative prompts to steer properly. V2 (generally) just gives you what you ask for.
One quirk, and I love it so much, is for some reason when I prompt for a skydiver, I routinely get a skydiver on a horse. No horses were included in the training images ... so how that snuck in is a mystery
Interested in generating your own embeddings? My Google doc walkthrough might help
-- -- --
After testing prompts with this embedding a few more days, I've found a fascinating tweak on its style can be to include prompt terms like "anime" and "cel-shading" to flatten some of the rendering down. It won't actually get you a truly anime look. It does get you a more graphic, punchy illustrative feel, but still with really rich coloring. Throwing other aesthetic terms and artist names at this embedding can move it in interesting directions.
Description
FAQ
Comments (4)
Hi, thanks for this model ! I'm a casual user of SD, and I posted your model to just verify it by pickle tensor and share it with the community. I have never claimed it’s mine, and I'm sorry if you felt offended. Anyway, it's already deleted.
no offense taken! Thanks for letting me take ownership ... the whole paradigm of AI-generated art is all borrowed assets anyhow. No doubt these embeddings will only be really useful for a couple months at most before a new incompatible model supersedes SD2.1
Am still very new to this, so i apologize if this is a silly question, but with this work on 2.1_768?
yes - it was trained on SD2.1
Not a silly question - ask whatever you need to know