General descriptionStyle LoRA based on illustrations by iwamushi (岩虫).Flat print color, muted sandy and olive palettes, rough uneven linework, grainy halftone texture.Available for four bases — pick the version that matches your model:<ul><li>Anima v8 — trigger @iwamushi (recommended)</li><li>Anima v5 — trigger @iwamushi (previous version, darker and rougher)</li><li>Illustrious — trigger iwamushi</li><li>Krea 2 — trigger @iwamushi. (new — natural-language prompts)</li><li>Pony — trigger iwamushi (new — 1.0 works on both base Pony and merges)</li></ul>This is a style, not a character — name the character you actually want.Not an official model by the artist.─────────────────────────────────────────────────────────Anima v8Trigger: @iwamushi (put it at the start of the prompt)Recommended style tags:rough uneven linework, halftone textureLoRA strength: 1.0Tips<ul><li>Don't add color tags like "olive muted palette" — they tint clothes olive-yellow. The LoRA already carries the palette.</li><li>Avoid the word "dirty" in texture tags — it paints stains on clothing.</li><li>If you ever see an "@iwamushi" signature in a corner, add signature to the negative prompt.</li></ul>What changed since v5<ul><li>Dataset grew from 79 to 112 images: new works added, low-res previews replaced with high-res originals, off-style pieces (neon, UI-heavy, 3D-like) removed.</li><li>Much less Re:Zero bias — characters stay on-model more often (hair color, outfits).</li><li>Noticeably more detail: backgrounds, clothing, lighting and shadows.</li><li>Handles complex scenes better: multiple characters, crowds, detailed interiors.</li><li>Warmer, sandier tone, closer to the artist's originals.</li></ul>Epoch 7 of 8 (784 steps), not the final epoch.TrainingBase: Anima Base v1.0. DiT with AdaLN trained, text encoder and LLM adapter frozen.Rank/alpha 16/16 · 112 images · 1024 res, buckets 512–1536 · AdamW8bit · LR 5e-5, constant, 5% warmupTrained on Anima Base v1.0 only. Behavior on Anima Turbo and third-party merges is unknown.─────────────────────────────────────────────────────────Anima v5Previous version. Superseded by v8, which has more detail and handles complex scenes better. v5 is kept for its darker, rougher look.Trigger: @iwamushi (put it at the start of the prompt)Optional style tags: flat print color, olive muted palette, rough uneven linework, dirty halftone textureEpoch 6 of the v5 run (474 steps), not the final epoch.TrainingBase: Anima Base v1.0. DiT with AdaLN trained, text encoder and LLM adapter frozen.Rank/alpha 16/16 · 79 images · 1024 res, buckets 512–1536 · AdamW8bit · LR 5e-5, constant, 5% warmupTrained on Anima Base v1.0 only. Behavior on Anima Turbo and third-party merges is unknown.─────────────────────────────────────────────────────────IllustriousTrigger: iwamushi (put it first, then regular Danbooru tags). No style tags needed.Recommended:<ul><li>LoRA 1.0 (up to 1.2)</li><li>euler_a, 30 steps, CFG 5–6</li></ul>Epoch 16 of 24 (640 steps), not the final epoch.TrainingBase: Illustrious XL v2.0. UNet and text encoder trained.Rank/alpha 32/16, conv 16/8 · 79 images · 1024 res, buckets 512–2048 · batch 2 · AdamW8bit · UNet LR 1e-4, TE LR 1e-5, constant, 5% warmup · min SNR 5 · noise offset 0.03Tested on WAI-Illustrious v16, Hyphoria v0.02 and Nova Anime XL il v1.9.─────────────────────────────────────────────────────────Krea 2Trigger: @iwamushi. at the very start, then describe the scene in plain sentences. No tags, no style words needed.Prompt template:@iwamushi. &lt;who or what&gt;, &lt;what they are doing&gt;, &lt;where&gt;, &lt;light and mood&gt;.Example: @iwamushi. Guts from Berserk in battered black armor sits by a small campfire at night, his huge sword leaning against a rock, embers rising into the dark, his face lit only by the fire.LoRA strength: 1.0 (0.8–1.2)<ul><li>Below 0.8 Krea starts writing "@iwamushi" in a corner — it reads the trigger as a social-media handle. The LoRA at full strength suppresses it.</li><li>Above 1.2 outfits and small details drift toward the training images.</li></ul>Recommended:<ul><li>Krea 2 Turbo, 8 steps, CFG 1, euler / simple</li><li>Native resolution, about 1 MP: 832×1248, 1248×832 or 1024×1024. No hires pass needed.</li></ul>Tips<ul><li>Atmosphere is where it shines: dusk, rain, firelight, fog, night streets.</li><li>Turbo gives very similar images across seeds — change the wording of the prompt for variety instead of rerolling.</li><li>Neon signs and other written text come out as made-up letters (base model behavior).</li></ul>Epoch 6 of 12 (1344 steps), not the final epoch — later epochs start copying signatures and outfits from the dataset.TrainingBase: Krea 2 Raw. LoRA on the DiT.Rank/alpha 32/32 · 112 images, each with a long and a short natural-language caption · 1024 res, buckets · batch 1 · AdamW8bit · LR 1e-4, constant · flow shift 2.5Tested on Krea 2 Turbo (fp8).───────────────────────────────────────────────────────── PonyLoRA strength: 1.0 — a balanced default for both base Pony and merges.<ul><li>Pony Diffusion V6 XL: ~0.8 if colors get heavy or red.</li><li>AutismMix and other Pony merges: up to 1.5 for a stronger style.</li></ul>Trigger: iwamushi (right after the score tags). No style tags needed.Prompt template:score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_anime, iwamushi, &lt;your tags&gt;Recommended:<ul><li>DPM++ 2M Karras, 30 steps, CFG 5–6, clip skip 2</li><li>A 1.5× hires pass at denoise ~0.45 makes a big difference on Pony.</li><li>Negative: score_6, score_5, score_4, source_pony, source_furry, source_cartoon, 3d, realistic, signature, artist name</li></ul>Tips<ul><li>Too much strength on base V6 (above ~1.2) turns everything muddy red-brown — lower it.</li><li>Pony struggles with hands in this style — poses with hands in pockets, arms behind back or portraits work best.</li><li>Closest to the artist's look is still Anima v8; the Pony version is a lighter take on the style.</li></ul>Epoch 16 (944 steps), final epoch.TrainingBase: Pony Diffusion V6 XL. UNet and text encoder trained, clip skip 2.Rank 32, conv 16, alpha scaled ×1.3 after training (32/20.8, conv 16/10.4) so 1.0 is the balanced strength · 112 images, Danbooru tags · 1024 res, buckets 512–2048 · batch 2 · AdamW8bit · UNet LR 1e-4, TE LR 1e-5, constant, 5% warmup · min SNR 5 · noise offset 0.03Tested on Pony Diffusion V6 XL and AutismMix Pony.

iwatomushi style (Anima/Illustrious/Krea2/Pony)

iwamushi_pony_e16.safetensors

Files with SHA256: aceea9bf9b843e7e29f3a795712b71578a63e52b20c47306bc9bc7af106e0510