This was trained using a dataset of photoreal images from <a target="_blank" rel="ugc" href="http://girlswithmuscle.com">girlswithmuscle.com</a> and various artist to try and give it flexibility in generating photoreal and anime images.The model was trained with traditional tagging + openAI generated image descriptions.While I attempted to train certain trigger words into this model, it seems to work in general but needs to be prompted -&gt; muscle, extremely muscular or even just describing a large body will allow the model to generate larger people.The images were labeled in sizes from 1 -&gt; 9 to give it the ability of generating different sizes though its only limitedly successful.Come visit our discord <a target="_blank" rel="ugc" href="https://discord.gg/aifantasy">https://discord.gg/aifantasy</a> where we post a lot of similar content + video generating AI!

Files with SHA256: 2fccbf5a5dcfb5213f7a77383b1d943daadb7030c9d1f8483c11e83243c60655