Please check out my Ko-Fi page if you are interested in supporting me.
LoRA commissions open! -> Fiverr
This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.
Trigger words for V3.08 (play with LoRa and tag weights!):
positive: <lora:ColoredSkinv309:0.7>(purple skin, woman)
Colors you can try are "blue skin", "green skin", "gray skin", "orange skin", "pink skin", "purple skin", "red skin", "white skin", "yellow skin", "black skin".
Experiment with adding "very dark" before the skin color tag to get darker shades of that color.
Also, I tested it for a little bit and it seems like it does still recognize colors not present in the dataset for example: "maroon skin" made a very nice red-brown color in a friend model.
Follow the steps in the Model Version notes to reproduce my images.
Sample images generated with AbyssOrangeMix3A1.
All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.
You might want to add some negatives to counter color bleeding if necessary, for example:
(purple background, purple eyes, purple clothes, purple hair)
It was trained on 200 512x512 images(20 for each color) scraped from the internet and 6 epochs using Animefull-final-pruned for the Training Model.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific details like nipples texture, see-through, and impossible shirt or form fitting.
Description
Generate using a weight of 0.4-1.0 like this: <lora:ColoredSkinv308:0.75>.
Using improved dataset and new training settings.
How I archived my generations:
txt2img: DPM++ SDE Karras with 20 steps, 512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.4, CFG 7. Then send to img2img!
img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.
extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.
If anyone is curious about my version names: v{version}.{trainingEpochs}
FAQ
Comments (12)
So is v3.8 a LORA or a LyCORIS? Confused on where to install it.
LyCORIS
Can this work with male images or does it only work with female images?
No sure. Theoretically it doesn't matter if it's a female, a male or a dog, unless I did a poor job at training it.
Use the lora control extension and try this:
<lora:coloredSkin-08: 0@10, 0.5@11 >
If you're using the cutoff extension, you can use that to specify the colors you want and do this instead (set it to a weight of 2 and enable "cutoff strongly." The extension is also bugged and has to be enabled from the first time you generate an image during a session):
<lora:coloredSkin-08:
1@10, 0.5@11, 0.5@20, 0@21>
This will blast the image with the color you want, then taper off, since this lora generates low res images at full strength. You CAN use the lora control extension to smoothly taper off, but when you're adjusting the lora weight each step, it significantly slows down render speeds.
Try using the 1x art clarity model (at 1x of course) in the upscaling tab to fix some blur if wanted: https://openmodeldb.info/models/1x-ArtClarity
edit:
1@10, 0.75@11, 0.75@20, 0.5@21
might be better
XL version pls
I don't have access to hardware capable of training or generating with XL
To anyone finding the effect weaker on the face: Try negative prompting makeup, rouge, that sort of thing.
I've found that very effective at making it just as strong on the face. Apparently SD is putting caucasian-skin makeup on by default, even if the skin color is blue or whatever. And yes, I found this because of SD doing that on african faces.
where do i install it exactly? i got the extension. i tried to put this in the lora folder and the lycoris folder but neither worked. i think i must have misunderstood something.
You don't need the extension anymore. It's been like that for almost a year now. Auto1111 now supports it out of the box.
@Part_LoRAs but still, where am i supposed to place the file? it doesn't seem to work like loras where i just drop it in the folder and it shows up.
@kleocola in the LoRA folder just like any other. It's also for SD 1.5 models.