💬 Discord — join here · 🔓 Patreon — new LoRAs 7 days early · ☕ Ko-fi — support the factory · 💼 Request Commission
Torino Aqua とりのあくあ — Art Style
Ornament everywhere, glossy light, eyes like cut glass — and nothing to type.
A style LoRA built from the illustrations of Torino Aqua (とりのあくあ · pixiv 1960050 · @TorinoAqua) — dense ornate compositions, saturated blue, violet and pink light, glossy skin and hair with hard highlight bands, iridescent multi-ring eyes, and frills, lace and gold filigree in every corner that holds them. The look is his — this is a fan LoRA of it, and all credit for the art goes to him.
It is trigger-less — no token to add. Write the scene you want and the finish arrives with it.
🧩 Version
🔵 v1.0 Anima — for Anima / Qwen-Image DiT checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0.
🟠 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.
📋 Prompt
No trigger, no tag stack. Describe subject, clothes, place and light and the finish arrives with it.
Negative — he signs his work, so the signature came along for the ride:
signature, watermarkIf your generator has an artist-name token, put that in the negative too.
💡 Tips
Weight 1.0 is home. Drop to 0.8 when you want a calmer frame with less ornament; 1.5 overshoots and the detail collapses in on itself.
Don't prompt the lens.
blurry,depth of field,lens flare,light raysandbacklightingare already part of the look; asking again just doubles them.Give it something to decorate — architecture, gowns, glass, flowers, gold. A bare scene wastes it.
Built on Anima base and rides Anima finetunes too; on a finetune with a strong look of its own, start at 0.8.
Stacks over character LoRAs — keep the character at its usual weight.
More of my LoRAs: Techannel on Civitai — likes & Buzz keep the factory running ❤️
Description
🟠 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.
