<h2 id="flux-w806hpguy">Flux</h2>Mario Perozzi.. All sample images are with no face detailer or hi-res fix, they are 1024x1024 resolution. They are generated on Euler at 20 steps. This lora is trained on 1024x1024 resolution as well. I used flux dev in the sample images. I've done testing and there are 2 ways my loras usually work best:<ol><li>Strength at 0.9-1 with no trigger word</li><li>Strength at 0.85-.0.95 with trigger word: m4r10</li></ol>i use comfy ui and theres a strength_clip option in the lora node and i set it to 0.85. Idk whats best but thats what i do<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/80b0c01a-67e8-4d66-ad18-6e41ac052337/width=525/80b0c01a-67e8-4d66-ad18-6e41ac052337.jpeg" /><h2 id="sdxl-um1fsdqbg">SDXL</h2>strength 0.9-1. put this in negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth openphoto of him:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/de50a378-c1c5-4092-8eaf-9edad1105b15/width=525/de50a378-c1c5-4092-8eaf-9edad1105b15.jpeg" />

Files with SHA256: 8a099cd32423fa50f45f4c01eb4915a76afff2054f2aeb50f210b0849e76fc82