Type | |
Stats | 96 |
Reviews | (5) |
Published | Mar 31, 2024 |
Base Model | |
Training | Steps: 8,750 Epochs: 70 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Trigger Words | Mad1B2024 |
Hash | AutoV2 2895230772 |
This is, I'm quite certain, the only Madison Beer Lora for SD 1.5 trained exclusively on well-varied (in terms of pose, angle, etc) images that were significantly higher than 1024x1024 to begin with, properly cropped to the following resolutions (all 1024 on at least one dimension):
512x1024
768x1024
1024x1024
1024x768
1024x512
Checkpoints I've personally found this to work well with include PicX Real, I Can't Believe It's Not Photography, Babes, and RealCartoon3D. "PsychomergeRealistic" as used in (some of) the example pictures is a personal checkpoint merge that I plan to also release on CivitAI at some point relatively soon.
This Lora may be updated in the future with a larger data set, although I'm very pleased with how it turned out for this release in any case, to say the least.