One Obsession v19 Atypical: beginner-friendly anime with hidden artist strings
Topik: Model
Oleh Captain
Diterbitkan 2026-10-03
maxfeifei8's One Obsession is an Illustrious/NoobAI anime checkpoint that makes good pictures without LoRAs or complex tags. Learn the clean illustration template, settings and how to discover the artist tags hidden in its examples.
Halaman ini belum diterjemahkan, jadi ditampilkan dalam bahasa Inggris.
Ikhtisar
One Obsession by maxfeifei8 is an Illustrious-based anime
checkpoint
with NoobAI influence. Its author's pitch is friendliness: good images without
LoRAs
and without complicated tags. Version 19 Atypical leans into a distinctive, slightly stylized look.
The example images on its page carry their prompts, and the author encourages hunting for the artist tag strings inside them; that is half the fun of the model.
Referensi
Nama | Tipe | Artinya |
|---|---|---|
Prompt template | tags | masterpiece, best quality, high detail, clean illustration, blurry background, depth of field, then subject |
CFG | 4-6 | 5 default. |
Steps / sampler | 25-30, Euler a | |
Clip Skip | 2 | Typical anime setting. |
Negative | short | lowres, worst quality, bad hands |
AD
Tanpa instalasi – jalankan model AI di cloud
BitVector Prism adalah cara termudah untuk memulai: pilih model, ketik prompt, dan hasilkan di aplikasi web yang bersih tanpa perlu mengatur apa pun. BitVector juga tersedia di Discord dan di web (SpyGlass).
Langkah demi langkah
- Template first, then one character description.
- CFG5, 28 steps, Euler a.
- Try one artist string you found on the model page.
- Keep the negative short.
- Hires fix 1.5x at 0.4.
Contoh
Character
masterpiece, best quality, high detail, clean illustration, blurry background, depth of field, 1girl, solo, purple hair, single braid, hair bell, yellow eyes, pink ribbon choker
Blonde portrait
masterpiece, best quality, high detail, clean illustration, blurry background, 1girl, solo, blonde hair, two braids, orange eyes, light skin, pink ribbon
Creative idea: seasonal set
Same character across four prompts: cherry blossoms, summer festival, autumn leaves, first snow; keep the template and seed.
Tips
- It does not need LoRAs; try it bare first.
- Clean illustration and blurry background give its poster-like look.
- Character knowledge comes from Illustrious; names work.
- Vivid color palettes come out well; name them.
Pemecahan masalah
Too stylized
Mengapa terjadi
v19 Atypical's deliberate look.
Cara memperbaikinya
Try v17 RED or add an artist string that pulls toward your target.
Backgrounds too blurry
Mengapa terjadi
Template tags.
Cara memperbaikinya
Remove blurry background and depth of field.
AD
Tanpa instalasi – jalankan model AI di cloud
PirateDiffusion hanya tersedia di Telegram dan dibuat untuk para profesional: ribuan model, LoRA, dan workflow lewat perintah chat, dengan pembuatan tanpa batas pada paket harga tetap.
Pertanyaan
Which version should I pick?
The author says newer is not always better; v17 RED, v19 and v20 Bold each have a character.
Does it need LoRAs?
No.
Tautan dan sumber
Model dalam panduan ini
Ditulis oleh
Captain
Panduan terkait
Model
Prefect Illustrious XL v7: polished anime with soft lighting
Goofy_Ai's Prefect Illustrious XL v7 is tuned for clean, soft-lit anime illustration. Learn the author's settings (Clip Skip 1, Euler a, CFG 5-6), prompt template and creative ideas.
Oleh Captain
2026-10-02
Model
One Obsession v20 Bold: saturated color, graphic anime and 3D looks
The Bold edition of One Obsession pushes color and contrast and reaches into 2.5D and poster styles. Learn its template, settings and ideas for graphic, high-contrast illustrations.
Oleh Captain
2026-09-29
Model
CounterfeitXL: clean, high-contrast anime on SDXL
gsdf's CounterfeitXL carries the beloved Counterfeit look to SDXL: crisp lines, vivid color, elegant characters. Learn its tag prompting, settings and ideas for striking anime scenes.
Oleh Captain
2026-10-03
Model
iLustMix v7 Cinematic: semi-realistic Illustrious with film lighting
GZees' iLustMix v7 Cinematic blends Illustrious anatomy with a cinematic, semi-realistic finish. Learn its Euler a / 25-step settings, quality tags and ideas for moody, movie-like frames.
Oleh Captain
2026-09-29
Panduan lainnya
Model
FLUX.1 Dev: how to prompt it, best settings and creative ideas
A practical guide to FLUX.1 Dev by Black Forest Labs: natural-language prompting, guidance and step settings, LoRA stacking, text rendering and prompt ideas that play to its strengths.
Oleh Captain
2026-09-30
Model
Stable Diffusion XL 1.0: prompts, settings and what it still does best
How to get the most out of the official SDXL 1.0 base model: native resolutions, CFG and sampler settings, the refiner, negative prompts and ideas for styles where SDXL still shines.
Oleh Captain
2026-10-01
Model
Stable Diffusion 1.5: the classic model, prompted properly
Stable Diffusion 1.5 is still worth knowing: the right resolution, CFG and sampler, how to use its huge library of LoRAs and embeddings, and creative prompt ideas suited to a 512-pixel model.
Oleh Captain
2026-10-02
Model
FLUX.2 Dev: prompting the newest Black Forest Labs model
FLUX.2 Dev brings larger prompts, better text, stronger realism and multi-reference editing. This guide covers the turbo workflow, guidance and resolution settings, prompt structure and ideas that use its new strengths.
Oleh Captain
2026-10-03
Model
Qwen-Image: long prompts, perfect text and bilingual posters
Qwen-Image is the model to reach for when the words in the picture matter. Learn how to write its long descriptive prompts, render English and Chinese text accurately, set CFG and steps, and explore layout-heavy creative ideas.
Oleh Captain
2026-09-29
Model
SDXL-Lightning: four-step generation on any SDXL checkpoint
ByteDance's SDXL-Lightning LoRA turns a 30-step SDXL render into a 4-step one. Learn the step counts, the CFG you must use, the sampler, and how to combine it with your favorite checkpoints and style LoRAs.
Oleh Captain
2026-09-30
Model
Trends
.ai
© ModelTrends.ai
|
Dibuat di Jepang
|
© 2026