Model
Trends
.ai
Model
Trends
.ai
os melhores modelos de IA de código aberto

One Obsession v20 Bold: saturated color, graphic anime and 3D looks

Tema: Modelos
Por Captain
Publicado em 2026-09-29
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.
Esta página ainda não foi traduzida, por isso é exibida em inglês.

Visão geral

One Obsession v20 Bold is the color-forward variant of maxfeifei8's Illustrious-based anime
checkpoint
. It emphasizes saturated palettes, strong contrast and clean shapes, and it stretches toward 3D-ish and photographic renderings when prompted.
Like the rest of the series it works without
LoRAs
and with short prompts.

Referência

Nome
Tipo
O que é
Prompt template
tags
masterpiece, best quality, then style tags such as graphic design, poster art, bold lineart, high contrast, limited palette
CFG
4-6
Lower
CFG
keeps colors from clipping.
Steps / sampler
25-30, Euler a
Standard.
Clip Skip
2
Negative
short
AD
Sem instalação: rode modelos de IA na nuvem
BitVector Prism é a forma mais fácil de começar: escolha um modelo, digite um prompt e gere em um app web limpo, sem configurar nada. O BitVector também está disponível no Discord e na web (SpyGlass).

Passo a passo

  1. Start with masterpiece, best quality.
  2. Add graphic style tags: poster art, bold lineart, flat shading, color blocking.
  3. Describe the subject.
  4. CFG 4.5, 28 steps.
  5. Hires fix at 0.35.

Exemplos

Poster

masterpiece, best quality, illustration, graphic design, poster art, stylized, bold lineart, high contrast, limited palette, flat shading, color blocking, 1girl, solo, motorcycle helmet under arm, city skyline

2.5D

masterpiece, best quality, realistic, soft shading, 1boy, solo, rain jacket, harbor, dramatic lighting, high contrast

Creative idea: album art series

masterpiece, best quality, poster art, two-color palette (teal and orange), texture, grain, 1girl, solo, headphones, abstract shapes

Dicas

  • Limited palette and color blocking make striking posters.
  • Add texture, grain for a printed look.
  • For 2.5D, add realistic and soft shading.
  • Dramatic lighting tags are followed strongly.

Solução de problemas

Clipped, neon colors

Por que acontece
CFG too high with high contrast tags.

Como corrigir
CFG 4 and limited palette.

Lineart too heavy

Por que acontece
bold lineart with high weight.

Como corrigir
Remove the tag or add thin lineart.

AD
PirateDiffusion
Sem instalação: rode modelos de IA na nuvem
O PirateDiffusion é exclusivo do Telegram e feito para profissionais: milhares de modelos, LoRAs e workflows por comandos de chat, com geração ilimitada a preço fixo.

Perguntas

Bold or v19?

Bold for graphic, saturated work; v19 for softer illustration.

LoRAs?

Illustrious
LoRAs at 0.6-0.8.

Links e fontes

Modelos deste guia

Escrito por
Captain

Guias relacionados

Modelos
One Obsession v19 Atypical: beginner-friendly anime with hidden artist strings
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.
Por Captain
2026-10-03
Modelos
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.
Por Captain
2026-10-02
Modelos
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.
Por Captain
2026-10-03
Modelos
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.
Por Captain
2026-09-29

Mais guias

Modelos
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.
Por Captain
2026-09-30
Modelos
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.
Por Captain
2026-10-01
Modelos
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.
Por Captain
2026-10-02
Modelos
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.
Por Captain
2026-10-03
Modelos
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.
Por Captain
2026-09-29
Modelos
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.
Por Captain
2026-09-30