<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 target="_blank" 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 target="_blank" 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 id="shima-konoka-blue-archive">Shima Konoka 志真コノカ — Blue Archive ブルーアーカイブ</h1>The halo is baked in. The mask is a knob.<hr />Character LoRA for Shima Konoka, a Blue Archive student out of Valkyrie's Public Peace Bureau. <code>konokaba</code> bakes in what her captions were stripped of: the face, the long grey hair, the grey eyes and the halo. No hair, eye or halo tags needed.Her mask and her wardrobe stayed tagged, so they stay steerable: <code>mouth mask</code>, <code>blue shirt</code>, <code>surgical mask</code>, <code>mask pull</code>, <code>blue necktie</code>, <code>black jacket</code>, <code>hawaiian shirt</code>, <code>gun</code>. Prompt them for canon, or drop the lot — the face holds either way.<h2 id="versions">🧩 Versions</h2><ul><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 Illustrious — for SDXL / Illustrious / Pony / NoobAI checkpoints. Weight 1.0 (usable range 0.85 – 1.0). Same trigger, its own stack below.</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><blockquote>Both bases ship on day one.</blockquote><h2 id="prompt-anima">📋 Prompt — Anima</h2>Full canon kit:<pre><code>konokaba, blue shirt, hawaiian shirt, blue necktie, blue skirt, pleated skirt, black jacket, mouth mask, mask pull</code></pre>Short stack — identity only:<pre><code>konokaba</code></pre>Negative:<pre><code>chibi, speech bubble, korean text, comic, multiple views, watermark, signature</code></pre><h2 id="prompt-illustrious">📋 Prompt — Illustrious</h2><pre><code>konokaba, grey hair, long hair, grey eyes, halo, blue shirt, hawaiian shirt, blue necktie, black jacket, mouth mask</code></pre>Negative:<pre><code>sketch,censor, chibi, speech bubble, korean text, watermark, signature</code></pre><h2 id="tips">💡 Tips</h2><ul><li>The mask is a tag, not a bake. <code>mask pull</code> pushes it under the chin. For a clear face, negative <code>mask, mouth mask, surgical mask</code>.</li><li>Her top is a blue aloha shirt. <code>hawaiian shirt</code> never appears without <code>blue shirt</code>. Name both.</li><li>Jacket colour is a real fork. <code>black jacket</code> and <code>grey jacket</code> both land. Name the one you want.</li><li>She comes armed, and patched up: <code>gun</code>, <code>weapon</code>, <code>assault rifle</code>, <code>bandaid on knee</code>, <code>bandaid on leg</code>.</li><li>Never negative her colours. <code>grey hair</code>, <code>grey eyes</code> and <code>halo</code> ride the trigger — negating them fights the LoRA.</li><li>Keep <code>solo</code> in — some images are two-ups.</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 ❤️

Shima Konoka 志真コノカ — Blue Archive ブルーアーカイブ [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: 96c9d06695cb2e1bda0f3e3b37ce205db473479ecc7f2191bf0eedcfea3a60fa