Z-Image Turbo Info:
Sampler Settings:
Use Beta Scheduler for best results, I've also been using Euler for the Sampler with good results.
PROMPTING:
Based on my tests with Z-Image, please use the word "vagina" instead of "pussy" to show a vagina.
There will be some oddities with some anatomy as I continue learning about training this model, so any feedback would be great!
Flux Dev Info:
This model excels at nude female anatomy. Its not perfect in this first version, so several generations might be needed for certain things. Some things to note, this REALLY wants to make nude women, so if you're trying to add clothes, I suggest lowering the strength a bit to lower the models tendency to make nude women. Second, I think there weren't enough asian women in the training data, so it struggles to make asian women. It will do it, but in the second version I will add more asians.
SD 1.5 Info:
This is a model to give your subjects an oiled/wet skin look. This is meant for photo real images, but I'm sure it will work on anime as well. No keyword is needed, you can just keep the weight at 1, or lower it if needed. It's very easy to use. The only thing I will suggest is to use Watermark as part of your negative prompt. The images I used had some watermarks, but I will release a v2 soon with these watermarks removed. This model is also fairly nsfw, so if you don't want nude images, you will likely have to negative prompt for your liking.
Share your images! I'd love to see what you make!
Description
Here's the Z-Image Turbo Version of my OiledSkin Lora! A few notes VERY IMPORTANT
Sampler Settings:
Use Beta Scheduler for best results, I've also been using Euler for the Sampler with good results.
PROMPTING:
Based on my tests with Z-Image, please use the word "vagina" instead of "pussy" to show a vagina.
There will be some oddities with some anatomy as I continue learning about training this model, so any feedback would be great!
FAQ
Comments (3)
I experimented with this LoRA across several prompts, comparing results both with and without it activated. I found that, for my use case, the prompts generally yielded better results without the LoRA applied. While trying different strengths, I noticed a tendency towards softer definition, occasional issues with hand generation, and some slight distortions in character features. It seemed to subtly shift away from the intended prompt. The 'oiled skin' effect does appear to work well, but there were enough other visual changes that it felt like the overall impact wasn’t quite as strong as I hoped.
welcome to the world of ZIT Loras! you can download all you want, you'll probably only find a few that actually help you do anything. assuming your vocabulary is bigger than danbooru tags, just use the model bareback.
It's so slippery that it's dangerous!