<h2 id="flux-cmbsu4912"><strong><span style="color:rgb(253, 126, 20)">Flux</span></strong></h2><p>Hassan Piker 2024.. 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:</p><p></p><ol><li><p>Strength at 0.9-1 with no trigger word</p></li><li><p>Strength at 0.85-.0.95 with trigger word: h4s4n</p></li></ol><p></p><p><span style="color:rgb(193, 194, 197)">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</span></p><h2 id="sdxl-ezmort2vo"><span style="color:rgb(253, 126, 20)">SDXL</span></h2><h2 id="hasan-piker.-9u1e01cny">Hasan Piker.</h2><p><span style="color:rgb(193, 194, 197)">put this in negative prompt: </span><strong><span style="color:rgb(193, 194, 197)">ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8505d917-cb3d-45d5-bf0a-7241715fa455/width=525/8505d917-cb3d-45d5-bf0a-7241715fa455.jpeg" /></span></strong></p>

Files with SHA256: 1c85be6d0d6c9b2168bb1411b70a76188c8519ce9ace4325e589c234601a81ef