<h2 id="flux-bi6xbi8ze">Flux</h2>Vinetria. 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 recommend putting "light makeup" some where in your prompt. 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: j0l13</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<h2 id="sdxl-4g5a55wj2">SDXL</h2>An influencerStrength at 0.9-1,I recommend putting "light makeup" at the end of the prompt and seeing if it brings better results, if not just remove it. It depends on the checkpoint.put this in negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open, teethworks great with Acorn is Spinning: <a target="_blank" rel="ugc" href="https://civarchive.com/models/112013?modelVersionId=703094">https://civarchive.com/models/112013?modelVersionId=703094</a>here's a photo of her:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/36f0694a-c489-4bf9-b1c9-3a76f9a20fa2/width=525/36f0694a-c489-4bf9-b1c9-3a76f9a20fa2.jpeg" />

Files with SHA256: e725083c4de12ca3d6b648a8fa56ba20a966a6ec2909d85f8866f3897d4281c3