<h2 id="mint-with-3-outfits-support">Mint with 3 Outfits Support</h2>Trained on a curated mix of 28 images—blending official 2D illustrations and 3D game models.This model is designed to put Mint in different outfits.<h3 id="key-features">Key Features</h3><ul><li>3 Built-in Outfits: Supports Default, Loungewear, and Bikini out of the box.</li><li>High Versatility: Clean outfit tagging allows custom clothing using <code>(alternate costume:1.3)</code>.</li><li>Anima Research Included: Features detailed comparison notes and training benchmarks below.</li></ul>Downside: At Dim 16, it ended up learning the art style too.Another LoRA (Outfit 1 only)⇩<a target="_blank" rel="ugc" href="https://civarchive.com/models/2996345/mintnteoutfit1">https://civarchive.com/models/2996345/mintnteoutfit1</a><hr /><h3 id="quick-reference">Quick Reference</h3>LoRA Weight: <code>0.8</code> – <code>1.0</code>Character Trigger:<pre><code>mint \(nte\), cat girl, cat ears, animal ear fluff, long hair, multicolored hair,streaked hair, aqua hair, braid, cat tail, pink eyes, large breasts</code></pre>Outfit1: Default<pre><code>black gloves, hairband, (cat face on hairband:0.8), white over shirt, black dress, black corset, black skirt, white thighhighs,thigh strap, black boots, fanny belt pouch, gold aiguillette,</code></pre>Outfit2: Loungewear<pre><code>loungewear, x hair ornament, see-through clothes, neck bell, white dress shirt, pink bikini,striped underwear,baggy clothes</code></pre>Outfit3: <code>bikini, [specific tags]</code><pre><code>aqua bikini,hat,white frilled bikini, sun hat ,navel, white thigh strap</code></pre>Custom Outfits: <code>(alternate costume:1.3)</code>Simillar LoRA⇩<a target="_blank" rel="ugc" href="https://civarchive.com/models/2935268/mint-neverness-to-everness">https://civarchive.com/models/2935268/mint-neverness-to-everness</a><hr />Outfit1 Key Points A and B<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/79d8f014-607e-4ebb-a00c-62e0ba44eac1/original=true/79d8f014-607e-4ebb-a00c-62e0ba44eac1.jpeg" />single outfit models outperformed 3outfits models.As a side effect, having too much 3D source data caused the output style to look more like 3D.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4346bea0-ed92-483d-9cb0-e49ee4cf54d9/original=true/4346bea0-ed92-483d-9cb0-e49ee4cf54d9.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/75420af5-c6b9-4e75-b1af-40f0b12fd154/original=true/75420af5-c6b9-4e75-b1af-40f0b12fd154.jpeg" /><hr />Comparing Anima and ILThere is no difference between them.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/173fac1b-dd8a-45f8-961b-b52d877b81ee/original=true/173fac1b-dd8a-45f8-961b-b52d877b81ee.jpeg" />Surprisingly, Anima performed just as well as IL even though the text encoder wasn't a perfect match.Turns out, as long as the dataset quality is solid, training just the U-Net is more than enough.

Mint_NTE_3Outfits

Anima28 images datasetDim:16 Alpha:16

Files with SHA256: 8654e82ef75db4ebf705ff304b4916ceda00f8e053c96f91f1dbccd5adfeed78