
This LoRA is trained on the base SDXL model with 80 images from a great artist, cutesexyrobutts. All images were tagged manually.
For the best results, use realistic models or mixed models. All sample images were generated using Juggernaut XL.
The trigger word best used is "by cutesexyrobutts". It seems that using "pastel colors, thick, curvy" also adds a nice touch to the style.
Lora weight of 0.3 - 0.7 (after testing, this keeps the characters most realistic with adding as much of the style as possible). You can go higher if you are not generating people /characters.
Negative prompt: nsfw, (worst quality, low quality:1.4), (lip, nose, tooth, rouge, lipstick, eyeshadow:1.4), (blush:1.2), (jpeg artifacts:1.4), (depth of field, bokeh, blurry, film grain, chromatic aberration, lens flare:1.0), (1boy, abs, muscular, rib:1.0), greyscale, monochrome, dusty sunbeams, trembling, motion lines, motion blur, emphasis lines, text, title, logo, signature
描述:
训练词语: by cutesexyrobutts
名称: csr_v4_e15.safetensors
大小 (KB): 891185
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success