->NoobAI V-Pred | PonyDiffusion | SD 1.5
Please, check the description, there is a little bit of useful information.
Inеtroduction:
This LoRA is supposed to represent Jadf's artstyle.
Please, be sure to use the same positive and negative quality prompt for better result.
Compatibility:
Humans: great
Anthros: great
Ponies: great
Multiple characters: great
Character LoRAs; great
Unique characters: great
Recommendations:
Trigger word - jadf (v4+)
Trigger word - jdf (v3)
1.0 emphasis
Clip Skip 1
CFG 5
NoobAI 1.0 V-Pred for generations (Main)
NoobAI 1.0 Eps for generations (Alternative)
masterpiece, best quality, highres, absurdresin positivesworst aesthetic, worst quality, low quality, bad quality, lowres, flat colorin negatives+
colorful, saturated, red theme, blue themefor CIvitAI generationsCFG Rescale 0.3 - 0.4 (if you're using v-pred version)
Use anything else in negatives only if you want to avoid or remove something from the image. For example, you don't want to see doors - "door" in negative. Style will look much better without garbage in negative prompt. Just try it.
Characters (v4+):
Jadf-tan
black hair, very long hair, blunt bangs, hime cut, red hairband, yellow eyes
There is still not so much images of her, but character is now working, at least. I hope you'll like this change, and of course, i hope there will be more art of her in the future.
Credits:
Trained on NoobAI 1.0 V-Pred. Dataset of 200 pictures (v1), 30 epochs, Clip Skip - 1
Trained on NoobAI 1.0 V-Pred. Dataset of 300 pictures (v2), 40 epochs, Clip Skip - 1
Trained on NoobAI 1.0 V-Pred. Dataset of 260 pictures (v3), 40 epochs, Clip Skip - 1
Trained on NoobAI 1.0 V-Pred. Dataset of 550 pictures (v4). 30 epochs. Clip Skip - 1
Trained on NoobAI 1.0 V-Pred. Dataset of 600 pictures (v5). 30 epochs. Clip Skip - 1
Trained on NoobAI 1.0 V-Pred. Dataset of 600 pictures (v5). 30 epochs. Clip Skip - 1
Really big thanks to:
Jadf for beautiful artwork
Some good folks from Discord server
You, for reading, downloading, liking and reviewing this LoRA
Description
What's new?
Added "old artstyle" tag as a regularization tag for negative, now you may use it to avoid flat and simple-styled images from appearing. You'll still get better style even without it.
Expanded dataset up to 600 images
Drastically improved overall style stability
FAQ
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.