Trained this model using V-Pred, which makes it much better at keeping characters looking consistent. For fixing up the details,i used Kontext—and it's a total game-changer. It can handle tricky things like correcting hands with multiple fingers or even making an ice cream cone disappear. To top it all off, integrated the Nunchaku inference engine, and the processing speed has absolutely skyrocketed<h3 id="recommended-weight:-0.9~1-fuzrhqq5s">Recommended weight: 0.9~1</h3><ul><li>CFG: 5 ~ 7</li><li>Steps: 28 ~ 35</li><li>Sampling Method: Euler</li><li>using Hires.fix and ADetialer</li></ul><h2 id="prompts-jocsug5yi">Prompts</h2><ul><li>Prompt Prefix:</li></ul><pre><code>kidgk, 1boy, solo, black hair </code></pre><ul><li>Negative Prompt:</li></ul><pre><code> nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, (((bad hands))), mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro,bad legs,multiple legs,multiplayer,</code></pre>

Files with SHA256: e4094af31cbd9df79e46cfdd6af21396464ece68d7df9df2c52dbf679cbf3dd3