Style model trained on various images from the artist Louis Le Breton, most famous for his drawings in the Dictionnaire Infernal. Is as equally capable of producing colored images as it is of black and white ones. Version 1.0 was trained on 20 images of his work, not just from the Dictionnaire, but also his landscape and portraits. Version 2.0 was trained on 26 images of a similarly wide variety of subject matter. As a result it should be able to generate a decent range of subject matter. Please read the "about this version" section for each model for more information on what it does.
Description
I was attempting to train SD 1.5 on the expanded dataset I used for V2, but something went wrong and the model fried itself. Its pretty unusable at weights higher than 0.5, but me my guest if you want to try generating something weird. At weights of 0.5 and lower the style is pretty weak but it still works to some degree. Either way, youll probably want to upscale it.
I will try uploading V2 of the 1.5 model later but I'll be putting this here if anyone wants to use it in the meantime.
FAQ
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.