Trained on a selection of images scraped from the X account of artist Henry Daubrez, this Lora creates a painterly style. While not an accurate representation of his style it is still a very nice look. There are FLUX and Z-Image versions available.
Description
This SD3.5L version was trained from the same image caption pairs as the flux version.
FAQ
Comments (10)
6GB! why so huge in 3.5? My 4090 will weep!
560MB < 1 gig
Sorry got my MB and GB mixed up! 560MB is still pretty huge. The Flux version is smaller I wondered why. First tests seem weaker than the Flux version. Is 3.5 harder to train?
@robadams171 Still figuring out the best params for training SD3.5 3.5, will update these as i figure it all out
Awesome model, can allow big range of creativity with strength and other loras
I can't get enough of it, super lora
thanks, glad you like it
Yeah, one of the goats 💞
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.