<h2 id="flux-tngr6qdle">Flux</h2>Madison Beer in Dead music video 2017. I havent done much testing so there may be a way to close mouth and i just dont know how but the ne issue I've had with this ahas been closing her mouth, its because this is her in the Dead music video. I could close the mouth in SDXL but don't know how to do it in Flux. I could try negative prompts but i dont want longer image generation so.... 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: m4d1s0n</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/65e1130a-4d37-40bb-b3f9-fc3a242f4cf8/width=525/65e1130a-4d37-40bb-b3f9-fc3a242f4cf8.jpeg" /><h2 id="sdxl-1eumkrdm5">SDXL</h2>Lora of Madison in her Dead music video.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.. This is different from the Baby MV lora because she had more softer features here and stuff. Also I like using this with Lustify. Strength at 0.8-1. Put this in negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth openHere's a photo of her in the music video:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6792233f-52d0-4ef1-842a-abfdfc4c64ed/width=525/6792233f-52d0-4ef1-842a-abfdfc4c64ed.jpeg" />

Files with SHA256: 2e9059c8e0ff987267c01cd3372ccdd472e5f9900147236236168478146b75af