2023/7/5 update
Update dataset. Retrain the model using new craft.
Introduction
A LoRA model trained with ~500 images by Nanoless. No trigger tag. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.6 version (original) YesMix.
Cautions (Must Read)
Some preview images are generated using 'Hires Fix' and upscaled using 'SD Upscale'. Thus, if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.
The maximum of generating resolution should not exceed 1024 theoretically, otherwise extra/deformed head/limbs will be waiting for you :). Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.
For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, make sure add '--no-half-vae' in command line of webui to prevent generating black images. See voldy's log for the details of edit method. For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.
Description
FAQ
Comments (6)
Oh niceee, I like this!
This is amazing! Could you make LorA with Tofuubear and Rosuuri?
Ok, I'll check and try it after I recover from the sickness.
Hi, always liked his style but as you see from the picture I posted it doesn't work. I put your image on PNG info and tried to generate with your same quality but nothing.
How should I use this lora?
I saw that you don't use it in the prompts either
you can install 'additional network' extension by kohya to use this LoRA model during generating or you can use the following syntax to use this LoRA model during generating: <lora:name of lora model:weights of lora model>
For anyone using this Lora, after testing I could conclude that it's best to use weights between 0.5 - 0.8, (personally the sweet spot is 0.7)
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.