Thành viên PixAI
PixAI
PixAI
Generate
Sign in
Trang chủ
Tạo
Mô hình
Studio
Cuộc thi
Mio.2

Conversational creation

Hộp công cụ
Guide

SDXL

OnikaTM

Công cụ AI

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

Khám phá

  • Thẻ Đang Thịnh Hành
  • Xếp hạng
  • Thị trường Mô hình
  • Cuộc thi
  • Tin tức

Giới thiệu

  • Guide
  • Cách sử dụng PixAI
  • Tsubaki.2
  • Gặp gỡ Mio
  • Quy tắc nội dung

Giá & Trợ giúp

  • Thành viên
  • Gói tín dụng
  • Liên hệ

Ứng dụng di động

  • Tải ứng dụng PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Điều khoản dịch vụ
  • Chính sách quyền riêng tư
  • Chính sách bản quyền
  • Attributions
  • Luật Giao dịch Thương mại Đặc định
OnikaTM - AI Model cover image
Đã tải lên vào
16:16 7 thg 7, 2026
Lượt sử dụng
194
Đánh giá
Chưa có đánh giá
Quyền
  • Allow image generation & sharing
  • Cho phép người dùng tải xuống mô hình của bạn
  • Sử dụng thương mại

Mô tả

https://civitai.red/models/2760835/onikatm

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 SDESchedule type: KarrasSteps: 35Resolution: 832×1216CFG Scale: 4.5-6.5 — both work well, just test what fits your prompt best. Higher values sometimes helped with clothing/skin coherence in my own tests, but your mileage may vary.Hires. fix: on — R-ESRGAN 4x+ Anime6B upscaler, denoising ~0.45, upscale x2. Sharpens details/edges at higher res.Prompting tips (learned from a lot of testing):This merge responds really well to variety — don't be afraid to mix things up:Camera angles/shots: low-angle shot, dutch angle, cowboy shot, upper body, three-quarter view, portrait all work well and give very different vibes from the same prompt.Colors & materials: works great with Dynamic Prompts wildcards if you have the extension installed, e.g. {fuchsia|hot pink|magenta|violet|blue|cyan} for color, or {denim|latex|leather|silk|chrome|transparent} for outfit material. Stacking multiple conflicting materials in one prompt (like latex + denim + chrome together) tends to cause weird clothing inconsistencies — pick one per generation instead.Facing the camera: add looking at viewer if you want the character facing you — without it, this merge tends to default to more random poses/framing.Texture tags like skin texture, pores, fabric texture add a lot of "grit" if your results feel too smooth/plastic-y.Example prompt:[character/subject], fuchsia, low-angle shot, dutch angle, looking at viewer, denim, skin texture, pores, detailed texture, specular highlightsExample negative prompt (helps a lot with coherence):blurry, bad anatomy, bad proportions, deformed, extra limbs, missing limbs, fused fingers, mutated hands, poorly drawn hands, poorly drawn face, malformed limbs, merged clothing, skin blending into clothes, distorted, warped, low quality, worst quality, watermark, signature, text, cloned face, unclear edgesGive it a spin and see what you get. Feedback and generated images are always welcome — genuinely curious what other people get out of it.

Bình luận