This is a simple micro-LoRA for POV Paizuri.
I suggest using this LoRA at 0.9-1.0 weight for best results.
Always add this to the prompt with the LoRA to activate it: 1boy, penis, breasts, paizuri
After that you can add other descriptive tags - If you remove penis from the prompt - It will naturally hide the penis under her breasts.
USE CLIP SKIP 2.
This was trained on NAI model - I have no idea if it works on realistic models. Images were generated on AOM3_A1 using the Orange Mix VAE.
Embeds and LoRAs used - Bad Prompt
Be sure to leave a review, comment and check out my other LoRAs - You might see something you like here.
Everything I'm making will always be free but if you want to show a little bit more support, you can buy me a coffee - https://ko-fi.com/ekune
Description
FAQ
Comments (11)
love this but do you think you could make a lora that just has the hands pressing the breasts together, (I cant get the breasts to look and shape this good without this lora, but I also dont want POV and well... pazuri). Again love this!
Yeah, if I get a chance I'll do it.
What class did you use for this? and how many images?
https://rentry.org/lora_train
I followed this guide - and I'm not sure about class. It was 40 Images.
Is anyone interested in making a negative embedding of impasto (Orange series models), too many models are mixed with them, resulting in a very large degradation of the results used at the same time.
It works good and useful in other models, many thanks!
how to use Lora not for this in general
hello i realy apreciate your lora's , but i have a little problems here "NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
Time taken: 2.51s
Torch active/reserved: 2617/2648 MiB, Sys VRAM: 4449/6144 MiB (72.41%)" can you help me?
i have the same issue, not an issue with the lora afaik
marvelous work
Details
Files
POVPaizuri.safetensors
Mirrors
povPaizuriLora1MB_povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
POVPaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
POVPaizuri_ekune.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
POVPaizuri.safetensors
POVPaizuri_ekune.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
POVPaizuri.safetensors
p_pair_v1.safetensors
POVPaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
POVPaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
POVPaizuri.safetensors
povPaizuriLora1MB_povpaizuri.safetensors
POVPaizuri (1).safetensors
POVPaizuri.safetensors
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.






