A lora for creating coat flashing scenes
Although this can be created through only the use prompts I found it not that consistent especially when using other loras
Trained with 100 images
Image info
Model used based64
Training settings?
The most important part of training is getting a good dataset (Dataset is included in the downloads section)
Training settings can be found by installing the additional networks extension in auto1111
Extensions -> available -> load from -> additional networks
Restart webui
place lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora
To view the training settings
Go to additional network tab -> choose model -> training paramters
Description
FAQ
Comments (4)
I mean, the sales-pitch is hot, but I think a shady trench-coat street dealer, should have more items in stock ...
I ran an ultra simple prompt just to test this Lora. With an X/Y/Z Plot using tons of different (3D, 2D, 2.5D) models, and 3 different prompts : 348 images generated and not even ONE with anything related to actual public indecency or exhibitionism.
Adding words to the prompt, such as: coat, flashing, exhibitionism. Sure I get results, same results I'd get without your "Lora" that literally does nothing at all.
a few things to check
1-were you on clipskip 2?
2-was the lora being called?
3-were you using the correct trigger words
4-are you using a photorealistic model? (if so it might not work)
5-did you take a look at the many examples that show it worked along with their prompt
6-did you try it out using the same models I showcased before moving to a different model?
bo sinn reference
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.