<h2 id="flux-3452t8t9u">Flux</h2>Bradley Martyn 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:<ol><li>Strength at 0.9-1 with no trigger word</li><li>Strength at 0.85-.0.95 with trigger word: br4dl3y</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/f9890a65-3572-40f7-a830-9a5429c5a907/width=525/f9890a65-3572-40f7-a830-9a5429c5a907.jpeg" /><h2 id="v2-w922kohbt">V2</h2>Should be better, based more on what he looks like now. Putting beard in positive prompt may help.negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open, teeth<h2 id="v1-5kapy3qqq">V1</h2>An influencer, strength 0.9-1, put this in negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open, teethphoto of him:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0f497a8b-80fe-4956-9f8d-ea2f48d7b1b6/width=525/0f497a8b-80fe-4956-9f8d-ea2f48d7b1b6.jpeg" />

Files with SHA256: aa206519d3612f030dcadad86206de6b261a5c0db86adf954cc2405e2c6affbb