A simple trained model a muscular male photos, the image is labeled using Joy Captioning so it was trained on a somewhat long text. This model might generated bad anatomy sometime, but the text capability is still preserved (well, mostly)This model aim to add concept of male genitalia that seems to be missing from the base model completely. But I am not sure if they works with a thinner manCFG scale range between is 2.5 - 4.0, with 20-25 diffusion step is okay, but more seems to give plastic skin. Tested using ComfyUI with non-quantized flux, fp16 t5_xxl, and "Flux (C64 Lora)" from <a target="_blank" rel="ugc" href="http://openart.ai">openart.ai</a><hr /><h3 id="experimentation-notes-i7cbog9xl">Experimentation Notes</h3><ul><li>Using ComfyUI Inpire Pack &gt; Lora Loader (Block Weight) with only last layer mask <code>0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1</code>, is the only real layer that encode the concept of penis. This will preserve almost all the flux capability, and decouple the muscle-bear body type</li></ul>Sample Image(s)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6ef4de3d-2b1b-4c56-8d7e-d5d08b833229/width=525/6ef4de3d-2b1b-4c56-8d7e-d5d08b833229.jpeg" />

Musclebear Flux1.D

Sample trained model, so don't expect much. The trained image mostly has only one subject, so if there is more, the generated image going to get wonky

Files with SHA256: 9ca9860ea9e3d91a87a97003bd15b91067415ee835135aebec7e93f1258b0693