<a target="_blank" rel="ugc" href="https://www.patreon.com/cw/Techannel"><img src="https://cdn.jsdelivr.net/gh/Techannel/assets@v3/banners/patreon-banner.png" alt="Early access on Patreon: all early-access LoRAs free for 7 days, then €5/month / 早期アクセスのLoRAすべて、7日間無料でお試し" /></a><a target="_blank" rel="ugc" href="https://techannel.app/"><img src="https://cdn.jsdelivr.net/gh/Techannel/assets@v3/banners/archive-banner.png" alt="Techannel archive: see what is in early access and vote on the next LoRA, free / 早期アクセス中のLoRAを見る・次のLoRAに無料で投票" /></a>💬 Discord — <a rel="ugc" href="https://discord.gg/TYHy7fpEXx">join here / 参加はこちら</a> · 🔓 Patreon — <a 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 rel="ugc" href="https://ko-fi.com/techannel">support the factory / 応援する</a> · 💼 <a rel="ugc" href="https://ko-fi.com/techannel/commissions">Request Commission / コミッション依頼</a><h1>Hu Tao 胡桃, 2 Outfits — Genshin Impact 原神</h1>The 77th Director of the Wangsheng Funeral Parlor.<hr />A character LoRA for Hu Tao with two outfits in one file: her Default look and Cherries Snow-Laden. Each outfit has its own trigger: <code>hu tao \(genshin impact\)</code> for Default and <code>hu tao \(cherries snow-laden\) \(genshin impact\)</code> for Cherries Snow-Laden. The trigger carries her and the look together: the long dark brown twintails with red tips, the red eyes, and the outfit itself: the black porkpie hat with the plum-blossom branch, the dark brown coat with long tails, the red collar, black shorts, white socks, rings and the bead bracelet for Default; the white beret with round red sunglasses on top, the white sleeveless dress with detached sleeves, the red skirt, the dark red shawl with the striped scarf and black thighhighs for Cherries Snow-Laden. The kit line pins the details; replace it with any outfit and she wears that instead.<h2>🧩 Version</h2><ul><li>🔵 v1.0 Anima — for Anima / Qwen-Image DiT checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0.</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><li>🟠 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></ul><h2>📋 Prompt</h2>Start with the outfit's trigger, then the kit line, then your pose and scene. Type the brackets with backslashes, exactly as below.Default<pre><code>hu tao \(genshin impact\), flower-shaped pupils, porkpie hat, hat flower, plum blossoms, chinese clothes, long sleeves, black shorts, tassel, jewelry, multiple rings, black nails</code></pre>Cherries Snow-Laden<pre><code>hu tao \(cherries snow-laden\) \(genshin impact\), flower-shaped pupils, white hat, beret, sunglasses, eyewear on head, red-tinted eyewear, white dress, bare shoulders, detached sleeves, red skirt, black thighhighs, scarf, red nails</code></pre><h2>💡 Tips</h2><ul><li>The trigger switches the outfit. It works alone; the kit line keeps the small pieces in place, so paste the whole line when you want the full look.</li><li>Keep <code>flower-shaped pupils</code> in the prompt, also with other outfits: that tag draws her flower pupils.</li><li>Weight 1.0 is where she sits best.</li><li>Outfits are steerable: drop the kit line and write another outfit, a winter coat and scarf for example, and she keeps her hair and eyes. Small pieces like to stay: the plum-blossom hair flower and the red collar on Default, the sunglasses on Cherries Snow-Laden.</li><li>Keep her to one character per image: with a second girl in frame, the other one can borrow her hair or kit.</li></ul><hr />More of my LoRAs: <a rel="ugc" href="https://civarchive.com/user/Techannel">Techannel on Civitai</a> — likes &amp; Buzz keep the factory running ❤️

Hu Tao 胡桃, 2 Outfits — Genshin Impact 原神 [Anima+Illustrious]

🟠 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: 86ad8ba551acc8cc40db0460515cc524ca9c65f320bd795cfa5896d7c41acb98