Last updated: July 15, 2026

OnikaTM is just a merge — no big story behind it. I mixed a bunch of Illustrious-based checkpoints, adjusted ratios, tested, redid it, tested again, until I landed on something I actually liked looking at. That's pretty much it.

I'm not going to pretend this is some groundbreaking model or oversell it — there are tons of solid Illustrious merges out there already. This is just my version, shared in case it fits your style too.

Recommended generation settings

• Sampler: DPM++ 2M / DPM++ 2M SDE / DPM++ 2M SDE Heun / DPM++ SDE / Euler a / Euler / LMS / Heun / DPM2 / Restart / DDIM / DDIM CFG / PLMS / UniPC / LCM

• Schedule type: Karras or Align Your Steps or Beta

• Steps: 35

• Resolution: 1040×1520 (same 2:3-ish ratio as 832×1216, just scaled up — gave noticeably richer detail in my own tests, more than Hires. fix did on its own)

• CFG Scale: 4.5–6.5 — both work well, just test what fits your prompt best

Style-specific sampler combos (found through testing):

• For a retro anime drawing look: LCM + Karras

• For a more modern anime look: DPM++ 2M + Karras, DPM++ 2M SDE + Karras, or Euler a + Karras

Prompting tips (learned from a lot of testing)

• Quality tags matter, a lot. Starting your prompt with

  masterpiece, best quality, amazing quality, very aesthetic, absurdres, highres, extremely detailed, intricate details, year 2025, newest

makes a noticeable difference — it pushes the merge toward its best-looking outputs.

• Pick one theme and commit to it. This merge shines when the whole prompt reinforces a single coherent idea (one color palette, one outfit style, one mood) rather than mixing a bunch of unrelated elements in one shot. A focused prompt beats a crowded one.

• Nuance on the above: stacking mood/aesthetic tags is fine (e.g. cyberpunk lighting + a single robotic accent, or punk texture + neon palette) — it's specifically stacking multiple clothing materials in one outfit (latex + denim + chrome together) that confuses the model. One material family per outfit, but mood layering is more forgiving than I first assumed.

• Keep composition simple when you want max quality. close-up / face focus gives cleaner, more reliable results than full-body + complex background + busy outfit all at once — there's just less for the model to get wrong.

• Camera angles: dutch angle, high angle shot, low-angle shot, three-quarter view all work well and change the vibe a lot for the same character. The merge also handles extreme versions better than expected:

  extreme low-angle shot, extreme top-down shot, extreme dutch angle, fisheye lens, worm's eye view

— as long as the outfit/material stays simple, these push composition further without breaking anatomy much.

• Body type & age descriptors render cleanly. For an adult, established look (rather than default youthful output):

  slim waist, generous curves, soft chubby face, mature adult woman, woman in her 30s

combine well and stay coherent even under extreme angles.

• Facial expressions vary reliably. Tags like smug, defiant, serene, playful, intense work well even under close-up/face focus, and help break repetitiveness across a themed batch without hurting quality.

• Materials & outfits: denim, latex, chrome/metallic textures, leather, silk all render well — but avoid stacking conflicting materials in the same prompt. One per generation.

• Texture tags like skin texture, fabric texture help a lot if your results feel too smooth or plastic-looking.

• Lighting: neon lighting, film grain, specular highlights, iridescent, paired with a coherent night-time palette (magenta, violet, deep blue), is consistently one of the merge's strongest zones stylistically.

• Negative prompt: keep it short and weighted on the model's actual weak points rather than a giant generic list. Hands are the main one:

  (bad hands:1.3), (extra fingers:1.3), (six fingers:1.4), fused fingers, missing fingers, deformed hands, mutated hands

makes a real difference.

Example prompt

masterpiece, best quality, amazing quality, very aesthetic, absurdres, highres, extremely detailed, intricate details, year 2025, newest, 1woman, solo, close-up, face focus, looking at viewer, [hair color], glossy hair, [eye color], detailed face, [outfit], skin texture, pores, neon lighting, specular highlights, film grain, depth of field, detailed background

Example negative prompt

worst quality, low quality, blurry, (bad hands:1.3), (extra fingers:1.3), (six fingers:1.4), fused fingers, missing fingers, deformed hands, mutated hands, bad anatomy, bad proportions, artist name, watermark, signature, text

Give it a spin and see what you get. Feedback and generated images are always welcome — genuinely curious what other people get out of it.