Updated: Nov 18, 2024
styleDownload
1 variant available
4280 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
4.6K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
9090 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(61)
Jul 24, 2024
Training: defaults (Prodigy), 412 auto tagged images (20 tags, 0.4 threshold)

1170 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
8240 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
License:
CreativeML Open RAIL++-MTesting loras on civitai. Models might be hit or miss since I can't test before publishing.
I created this model to have a single LoRA that has a style similar to these images: image 1, image 2 (NSFW), image 3 (NSFW).

Model was training using generated images from a combination of the following:
SD model - Pony XL
LoRa (style) - Suoiresnu
LoRa (style) - ExpressiveH
LoRa (concept) - Blackedwear
LoRa (style) - Bartolomeobari
LoRa (style) - Sinfully Stylish
LoRa (style) - fishine
LoRa (slider) - Detail Slider
Changelog:
v1 - the model is workable, but not really what I wanted (see training data)
v2 - added more images and tags, switched to Adafactor
simple images might need
haloin the negative
v3 - added a lot more variation to the images
v3.1 - same as v3, but trained with Prodigy and less repeats/steps - this one is my favourite
v4 (in progress) - will try to reduce overfitting
