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 V3.20:
<lora:CumOnTonguev320:0.75>(cum on tongue, open mouth, tongue out, cumdrip)
You can try "cum string", "facial", "bukkake"(cum EVERYWHERE), "cum on hair", "cum on hair", "cum on breasts", "cum in mouth", "after fellatio", "hands up", "cum on hands" and "cupping hands".
For camera angle try "from side", "profile", "form above", "from below" and "pov".
I suggest using negatives: "blurry", "vapor", "steam" and "steaming body".
Side view not 100% so keep that in mind!
Follow the steps in the Model Version notes to reproduce my images.
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, for example:
(simple background, white background)
Sample images generated with Grapefruit using <lora:CumOnTongueV220:1> and some simple positive prompts.
It was trained on 150 512x512 images scraped from the internet and 8 epochs using Animefull-final-pruned for the Training Model.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger Extension and fine tuned for specific details like cum on tongue and cumdrip.
Model loves to generate:
Fucking "vapor", "steam" and "steaming body". :(
Likes to draw a penis randomly. lol
Description
Generate using a weight of 0.5-1 like this: <lora:CumOnTongev320:0.7>.
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 0.5, 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 (7)
Can loha be used with lora? I collected many lora character, but loha models are too little.
Yes! Just needs the extension and use it as any other LoRA
It's just a different training Algorithm for a LoRA that have the capability of it learning more stuff.
can you use it with comfyUI
I have no idea :(
https://github.com/comfyanonymous/ComfyUI#features
"Loras (regular, locon and loha)" listed there so it should work.
@Part_LoRAs thank you i try it