A lora based on the style of blue-senpai
Image info
Model used based64
Notes
The feet wont come out perfectly as expected of ai,use the example images prompts as reference
Training settings?
The most important part of training is getting a good dataset!
I've included the dataset along with the captions, feel free to use them to make a better lora!
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 parameters
Description
FAQ
Comments (7)
ayyo did you use a mirko lora for the mirko photo?
Nope just pure prompts. The only lora I used was the blue-senpai one
Thank you so much!!
Actually tho, is there any chance we could get tags to activate the poses at all?
That seems to be the only issue so far imo, the feet is understandable due to A1111 so patience and inpainting should fix that. Other than that it's great!
Ill try and retrain it for the specific poses but due to the low amount of images present in the dataset I doubt I can get the specific poses without the lora being overtrained
@mnemosynekotorin Ahhh I see. Maybe releasing it as a separate version is an option? But either way tho, I appreciate your efforts
Can we get lora for abc.@123 please?
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.