Keanggotaan PixAI
PixAI
PixAI
Generate
Sign in
Beranda
Buat
Model
Studio
NEW
Kontes
Buat dengan Mio.2

Conversational creation

Toolbox
NEW
Dokumen PixAI

SDXL

Hotaru Blend

Alat 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

Temukan

  • Tag Populer
  • Peringkat
  • Model Market
  • Kontes
  • Berita

Tentang

  • Dokumen PixAI
  • Cara Menggunakan PixAI
  • Tsubaki.2
  • Kenalan dengan Mio
  • Aturan Konten

Harga & Bantuan

  • Keanggotaan
  • Paket Kredit
  • Kontak

Aplikasi Seluler

  • Dapatkan aplikasi PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Ketentuan Layanan
  • Kebijakan Privasi
  • Kebijakan Hak Cipta
  • Atribusi
  • Undang-Undang Transaksi Komersial Tertentu
Hotaru Blend - AI Model cover image
Diunggah pada
8 Sep 2025, 04.07
Penggunaan
32.1k
Ulasan
Luar Biasa  (6)
Izin
  • Izinkan pembuatan & berbagi gambar
  • Izinkan pengguna mengunduh model Anda
  • Penggunaan komersial

LoRA yang Direkomendasikan

Madoka - Idolmaster Shiny Colors (SD 1.5 & SDXL Pony) - AI Model cover image

LoRA Pengguna

Madoka - Idolmaster Shiny Colors (SD 1.5 & SDXL Pony)
9
Tanaka Mamimi 田中摩美美 THE iDOLM@STER SHINY COLORS 偶像大师 闪耀色彩 - AI Model cover image

LoRA Pengguna

Tanaka Mamimi 田中摩美美 THE iDOLM@STER SHINY COLORS 偶像大师 闪耀色彩
18
Mikoto Aketa / 緋田美琴 - AI Model cover image

LoRA Pengguna

Mikoto Aketa / 緋田美琴
8
ブルマ/buruma(XL,Pony) - AI Model cover image

LoRA Pengguna

ブルマ/buruma(XL,Pony)
80

Deskripsi

This Illustrious based checkpoint merge produces 2D Anime pictures with a clean and detailed style.It is the result of merging 2 of my current favorite anime checkpoints.UpdateVersion 4.0For this version I added an additional personal merge model which improves the creativity of the model. The colors are now a bit less vibrant and instead have "smoother" look now.Version 3.0This release provides some overall improvements. I tried to make the style more like 2D Anime illustrations.I made 2 quality embeddings for positive and negative prompt, that can be used an an alternative to the below mentioned Quality tags.You can find them here: https://civitai.com/models/1821398?modelVersionId=2061138Version 2.0This release improves the overall details a bit, most noticeable with the hair and reflections. The prompt adherence should also be better then the previous version.The recommended settings are the same as for Version 1.Recommended settingsSampler: Euler A / Scheduler: SGM UniformSteps: 25-30CFG: 3-5Resolutions: SDXL recommended resolutions (832x1216, 896x1152...)Highres fix depending on use caseQuality tags:Positive:masterpiece, best quality, amazing quality, very aesthetic, absurdres, cute face, slender, detailed eyes, detailed hairNegative:lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, blurry, watermark, bad eyes, bright pupils, white pupils, bad hands, bad face, censored, mosaic censoring, bar censor, censor bar, text, signaturemerged modelsHDA_Rainbow_Illus v1.4HotaruBreedXL_Anime_v20DPO full original checkpoint (for DPO fix)+additional style lorasPermission: no commercial use, no selling, use only on Civitai (please also check the sources for their respective permissions)

Komentar