Textual inversion model trained on pictures of Daniel Bruhl on the red carpet.
Much better than the 1st version (since I fixed the training prompts), doesnt come off as deep fried.
Needs work: Likes to clone himself, go out of frame and not be realistic. All can be fixed with proper prompting.
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.