Please check out my <a target="_blank" rel="ugc" href="https://ko-fi.com/part_loras">Ko-Fi</a> page if you are interested in supporting me.LoRA commissions open! -&gt; <a target="_blank" rel="ugc" href="https://www.fiverr.com/partai/develop-your-custom-lora-or-loha-model-for-stable-diffusion">Fiverr</a><h3>This is a LoHa LoRA! You need the <a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/a1111-sd-webui-locon">extension</a>! Why? They do a lot better with multi-concepts. This LoHa is probably best used for INPAINTING. Not required tho! You can just prompt for it.</h3>Trigger words for V4.20 (USE NEGATIVES FOR BETTER COLOR CONTROL) - green lips is VERY STRONG, use it with lower tag weight like "green lips:0.8":positive: &lt;lora:ColoredLipstickv420:0.7&gt;(lipstick, green lips, blue dress) and in negative: (green dress:1.5, green hair:1.5, green eyes:1.5)You can try "white lips", "red lips", "pink lips", "orange lips", "purple lips", "green lips", "yellow lips", "gold lips", "brown lips", "blue lips" "black lips", "aqua lips" for colors (white and green aren't that good and orange only appears in high weight like 0.7-0.8). Try to also describe the mouth or use tags that could influence the mouth, if possible, like "smile", "puckered lips", "lips apart", "open mouth" and "closed mouth".<h3>Follow the steps in the Model Version notes to reproduce my images.</h3>Sample images generated with AbyssOrangeMix3A1.All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it. Could use same tags in negatives to control how it generates.You might want to add some negatives, for example: (makeup)It was trained on 81 512x512 images scraped from the internet and 20 epochs using animefull_final.Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific details like "blue lips" or "red lips".The model loves to generate:<ul><li>Everything but "white lips". :(</li></ul>

Colored Lipstick - LoHa

Generate using a weight of 0.4-0.8 like this: &lt;lora:ColoredLipstick220:0.5&gt;. How I archived my generations:<ol><li>txt2img: DPM++ SDE Karras with 20 steps, 512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.4, CFG 7. Then send to img2img!</li><li>img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.</li><li>extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.</li></ol>If anyone is curious about my version names: v{version}.{trainingEpochs}

Files with SHA256: 7ed5406d07015e8d9f70244d4030cc8f098476563da250b231a4fabe5f6b87ea