<h3 id="heading-199"><a target="_blank" rel="ugc" href="https://forms.gle/uSahTwRWuc2YDKe18">Submit your request here</a></h3><h3 id="heading-257">v1.0</h3>Weight: 1.0Trigger + Appearance: <code>shiba kukaku, (amputee, prosthetic arm:1.2), large breasts</code>Default Outfit: <code>japanese clothes, bandages, cleavage</code>Add <code>black hair</code> if necessary.The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler. You'll also notice that my prompt includes <code>&lt;lyco:</code>. Note that all my LoRA files are located within my LyCORIS folder. If the model is labeled as a LoRA, it's a simple LoRA. If it's specified as a LyCORIS, it's a LoHa.<h3 id="heading-258">v0.1</h3>Weight: 1.0Trigger + Appearance: <code>shiba kuukaku, (prosthesis, prosthetic arm:1.2), bandages, large breasts</code>Default Outfit: <code>red dress, cleavage</code>The <code>amputee</code> prompt might work, it might not, same could be said for her <code>prosthetic arm</code>.This is the first LoRA I trained on my laptop, this time using <a target="_blank" rel="ugc" href="https://civarchive.com/models/23900?modelVersionId=28562">Lykon's AnyLoRA checkpoint</a> as a training model. The result is mid, but I'm not disappointed. I realized that I had messed up on one of the settings after checking its metadata, but it's okay because it's all part of the fun experience that is baking a model for ~6 hours. I'll be learning from this to train another character tomorrow.

Kukaku Shiba | Bleach

Retrained on NAI with some of the images in the dataset upscaled.

Files with SHA256: 90f7ba00c1f23dea21a62f56dc8c922832edca8162c786c77efb6267b9b479c4