Note: I did not train these LoRA models myself. Original source: <a target="_blank" rel="ugc" href="https://huggingface.co/stma/lora-dump">https://huggingface.co/stma/lora-dump</a><h2>Recommended settings</h2>Quick start<ul><li>Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/4437/abyssorangemix2-sfw">AbyssOrangeMix2</a></li><li>LoRA weight: 0.6 (UNet: 0.6, TEnc: 0.25)</li><li><code>[realistic], [3d], (3dcg), ((octane render)), [fisheye]</code> in positive prompt for realism</li><li><code>simple background, grey background</code> in negative prompt</li><li>CLIP skip: 2</li><li>Sampler: DPM++ SDE Karras (Euler a recommended for other models)</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/datasets/gsdf/EasyNegative">EasyNegative </a>in negative prompt</li></ul>Usable<ul><li>LoRA weight range: 0.2 - 1.15 (UNet: 0.35 - 1.15 TEnc: 0.2 - 1.0)</li></ul>UNet is required for the style. UNet over 0.65 will look like an anime figure product. Too high UNet weight will melt details.Lower TEnc weight will improve generalization. High TEnc will affect composition to look more like an anime figure product photo. Too high will fry the details.Start with lower weight and increase as necessary. Requires more weight when mixed with TI embeddings and other LoRAs.<h2>Figma</h2>Trained on 5,746 images scraped from GoodSmile's international catalogue, including the discontinued products. All images were tagged with <code>figma</code> first and the product name with <code>figma</code> stripped out second, so an image from a product named "figma Hatsune Miku" would be tagged <code>figma, hatsune miku</code>. All other tags came from the WD1.4 tagger. <code>3d</code> and <code>realistic</code> tags seem to work well with it.The alpha16 version is better at generalizing, while the 7e-5 version is better at capturing the figure-with-transparent-stand look.<h2>Example images</h2><h3>Model</h3><ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/gsdf/Counterfeit-V2.5">Counterfeit-V2.5 </a>(TODO: update example images to <a target="_blank" rel="ugc" href="https://civarchive.com/models/4437/abyssorangemix2-sfw">AbyssOrangeMix2</a>)</li></ul><h3>Textual inversion</h3><ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/4972/roxy-migurdia-ti">Roxy Migurdia</a> (character) <code>roxy-migurdia</code></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/5537/megumin-ti">Megumin</a> (character) <code>megumin_1000</code></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/3036/charturner-character-turnaround-helper">Char Turner </a>(composition) <code>chartuner</code></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/datasets/gsdf/EasyNegative">EasyNegative </a><code>EasyNegative</code></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/datasets/Nerfgun3/bad_prompt">Bad Prompt </a><code>bad_prompt</code></li></ul><h3>Additional LoRA</h3><ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/4831/yelan-lora-collection-of-trauters">Yelan</a> (charater) <code>yelan \(genshin impact\)</code></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/5126/torino-aqua-style-lora">Torino Aqua</a> (style) <code>torino aqua</code></li></ul>

Figma Anime Figures

The 7e-5 version is better at capturing the figure-with-transparent-stand look and has more variety in backgrounds but they look plastic.

Files with SHA256: b16bfab3a6049098e2cb606a925d37e552f460f0064427cdfc147dd84ea25231