A lora for retro sci-fi and fantasy images, like Frank Frazetta and other famous artists of the genre. It was also fed a lot of vintage sci-fi book illustrations and artworks.
Description
A much smaller sized model. I hope it actually learned the style and not regurgitates the dataset.
FAQ
Comments (3)
Thanks for including prompts. But you should really talk a little about the LORA too. All the data you include on this page builds engagement with those of us likely to try the LORA. Mentioning the number and types of image used in the training process is a good start!
Anyone try this on Forge with Q4_0 GGUF? At 0.8 strength at 20 steps I see massive image damage. 0.6 gives a much better result, but with a 'pixelated' image.
Does this respond to specific artists? If so which ones work best? Looks cool
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.