<a target="_blank" rel="ugc" href="https://www.patreon.com/cw/Techannel"><img src="https://cdn.jsdelivr.net/gh/Techannel/assets@v1/banners/patreon-banner.png" alt="Early access on Patreon: new LoRAs for free, 7 days early / 新作LoRAを無料で7日早くダウンロード" /></a>💬 Discord — <a target="_blank" rel="ugc" href="https://discord.gg/TYHy7fpEXx">join here / 参加はこちら</a> · 🔓 Patreon — <a target="_blank" rel="ugc" href="https://www.patreon.com/cw/Techannel">new LoRAs 7 days early / 新作LoRAを7日早く</a> · ☕ Ko-fi — <a target="_blank" rel="ugc" href="https://ko-fi.com/techannel">support the factory / 応援する</a> · 💼 <a target="_blank" rel="ugc" href="https://ko-fi.com/techannel/commissions">Request Commission / コミッション依頼</a><h1 id="hsin-2-outfits-wuthering-waves">Hsin 心, 2 Outfits — Wuthering Waves 鳴潮</h1>Black-tipped fox ears, red claws, and a smile with a fang in it.<hr />Character LoRA for Hsin, the white fox lady of Kuro Games' Wuthering Waves, with both of her forms in one file. Since v4.0 each form has its own trigger: <code>hsin \(wuthering waves\)</code> for her default form and <code>hsin \(illumining form\) \(wuthering waves\)</code> for the Illumining Form. The trigger carries her and the look together: fox ears and tail, white hair with black tips (white flowing into gold on the Illumining Form), red-rimmed amber eyes (yellow on the Illumining Form), the red glyph on her forehead, her chest and arm markings, and the outfit itself. The kit line pins the details; replace it with any outfit and she wears that instead.<h2 id="version">🧩 Version</h2><ul><li>🔵 v4.0 Anima — for Anima / Qwen-Image DiT checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0. New triggers, see the v4.0 prompt lines.</li><li>🟠 v4.0 Remapped Anima 2.9B — this version is the same LoRA remapped onto the 40-layer Anima-2.9B layout (weight 0.5–0.7, no patch node needed). It is a remap, not a retrain, so there may be issues with the 2.9B version — if there is enough interest I may retrain it natively for 2.9B.</li><li>🔵 v3.0 Anima — for Anima / Qwen-Image DiT checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0.</li><li>🟠 v3.0 Remapped Anima 2.9B — this version is the same LoRA remapped onto the 40-layer Anima-2.9B layout (weight 0.5–0.7, no patch node needed). It is a remap, not a retrain, so there may be issues with the 2.9B version — if there is enough interest I may retrain it natively for 2.9B.</li><li>🟢 v2.0 Illustrious — both outfits (Default + Moon), for SDXL / Illustrious / Pony / NoobAI checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0. Render on CLIP skip 2. Same prompt lines as v3.0 Anima.</li><li>🔵 v2.0 Anima — for Anima / Qwen-Image DiT checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0.</li><li>🟠 v2.0 Remapped Anima 2.9B — this version is the same LoRA remapped onto the 40-layer Anima-2.9B layout (weight 0.5–0.7, no patch node needed). It is a remap, not a retrain, so there may be issues with the 2.9B version — if there is enough interest I may retrain it natively for 2.9B.</li><li>🔵 v1.0 Anima — for Anima / Qwen-Image DiT checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0 (usable range 0.85 – 1.0).</li><li>🟠 v1.0 Remapped Anima 2.9B — this version is the same LoRA remapped onto the 40-layer Anima-2.9B layout (weight 0.5–0.7, no patch node needed). It is a remap, not a retrain, so there may be issues with the 2.9B version — if there is enough interest I may retrain it natively for 2.9B.</li><li>🌸 v1.0 Krea 2 — for Krea 2 checkpoints (Raw &amp; Turbo). Same trigger <code>hsinwuwa</code>. Weight 1.0. Prompts in natural language — see the Krea 2 section.</li><li>🟢 v1.0 Illustrious — for SDXL / Illustrious / Pony / NoobAI checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0. Render on CLIP skip 2.</li></ul><blockquote>v4.0: I rebuilt her dataset and retrained her. Each form has its own trigger now, and she takes other outfits far more easily: prompt the outfit, leave the kit line out, and the default dress stays off. The old <code>hsinwuwa</code> lines still work on the older versions; they are further down.</blockquote><h2 id="prompt-v4.0">📋 Prompt — v4.0 Anima</h2>Start with the form's trigger, then the kit line, then your pose and scene. Type the brackets with backslashes, exactly as below. Weight 1.0, or 0.5–0.7 on the 2.9B remap.Default, her black and red dress:<pre><code>hsin \(wuthering waves\), bare shoulders, black dress, off shoulder, detached sleeves, hair ornament, jewelry, earrings, bracelet, red nails</code></pre>Illumining Form, her white and gold look:<pre><code>hsin \(illumining form\) \(wuthering waves\), bare shoulders, white dress, forehead jewel, hair ornament, jewelry, earrings</code></pre><h2 id="prompt-v3.0">📋 Prompt — v3.0 Anima and v2.0 Illustrious</h2>These two lines work on v3.0 Anima and on v2.0 Illustrious. Start with <code>hsinwuwa</code> and the outfit word, then the kit line, then your pose and scene. Weight 1.0 (Illustrious: CLIP skip 2), or 0.5–0.7 on the 2.9B remap.Default, her black dress:<pre><code>hsinwuwa, baseout, black dress, red sleeves, detached sleeves, fur trim, off shoulder, chest jewel, jewelry</code></pre>Moon form, her transformed look:<pre><code>hsinwuwa, moonout, white dress, yellow dress, detached sleeves, fur trim, off shoulder, chest jewel, jewelry</code></pre><h2 id="prompt-v2.0">📋 Prompt — v2.0</h2>Use one of these paired triggers for v2.0 Anima. The clothing blocks help retain the selected outfit.Normal form<pre><code>hsinwuwa, baseout, black dress, red sleeves, detached sleeves, fur trim, off shoulder, jewelry</code></pre>Moon form<pre><code>hsinwuwa, moonout, white dress, yellow dress, detached sleeves, fur trim, off shoulder, jewelry</code></pre><h2 id="prompt-v1.0-(anima-and-illustrious)">📋 Prompt — v1.0 (Anima and Illustrious)</h2>Her wardrobe stayed steerable: the canon black dress with detached sleeves is the default, with a trained alternate pool on top — <code>alternate costume</code>, <code>swimsuit</code> / <code>bikini</code>. Her signature fox hand sign is trained too.Canon kit — her default look:<pre><code>hsinwuwa, black dress, detached sleeves, bare shoulders, hair ornament, cleavage, smile</code></pre>The fox hand sign — her signature gesture:<pre><code>hsinwuwa, fox shadow puppet, smile, fang</code></pre>Off-duty — the trained alternate wardrobe:<pre><code>hsinwuwa, alternate costume, black bikini, navel, sitting</code></pre><h2 id="krea-2">🌸 Krea 2</h2>The Krea version speaks prose, not tags. Same trigger, <code>hsinwuwa</code> — it carries her whole identity block on its own (fox ears and tail, white hair with black tips, the red glyph, the fang, the claw manicure). Ask for the kit in plain words:<pre><code>hsinwuwa, full body shot of the subject standing in red and white robes with gold trim</code></pre>No negative needed.<h2 id="tips">💡 Tips</h2><ul><li>Custom outfits: on v4.0 keep the trigger and replace the kit line with your outfit. On v3.0 keep <code>hsinwuwa</code> and the outfit word, and replace the kit words; to take the jewel off her dress there, drop <code>chest jewel</code> from the kit line.</li><li>Her tail is baked, so leave tail words out. On v4.0 the trigger colours it: a dark tip on the default form, pale gold on the Illumining Form. On v3.0 the outfit word does: black tips with <code>baseout</code>, gold tips with <code>moonout</code>. It shows up mainly at full-body framing.</li><li>Give her somewhere to be. Scenery is her weakest area — name the room and the light; <code>upper body</code> and <code>cowboy shot</code> are safest.</li><li>Junk negative. If a render goes chibi or grows text, add <code>chibi, english text, text, logo, watermark, character name, border</code>.</li><li>Chest bias: she runs <code>large breasts</code> by default. <code>medium breasts</code> is trained and pulls it down; <code>small breasts</code> is not.</li><li>On v3.0 and older the default dress is sticky. For other outfits use v4.0.
</li></ul><hr />More of my LoRAs: <a target="_blank" rel="ugc" href="https://civarchive.com/user/Techannel">Techannel on Civitai</a> — likes &amp; Buzz keep the factory running ❤️

Hsin 心, 2 Outfits — Wuthering Waves 鳴潮 [Anima+Illustrious+Krea2]

🟠 Remapped Anima 3.8B — this version is the same LoRA remapped onto the 52-layer Anima 3.8B / Delta Mix layout (weight 0.65–1.0, plain Load LoRA, no patch node needed). It is a remap, not a retrain, so there may be issues with the 3.8B version.

Files with SHA256: 71f1f8df8aa32b0e0481d1fad8c6eab6d0a495a28f46caec690ab53d1b179eb9