Model
Trends
.ai
Model
Trends
.ai
the best open source ai models

WAI-illustrious-SDXL v16: character-rich anime with simple prompts

Topic: Models
By Captain
Published 2026-10-03
Share
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2073075463
Size
1024x1360
Clip skip
2
Prompt
1girl, hatsune miku, dress, long hair, jewelry, white dress, blue eyes, necklace, bubble, solo, underwater, hair between eyes, looking at viewer, bangs, blue hair, bow, reaching towards viewer, blue theme, air bubble, hair bow, collarbone, floating hair, frills, twintails, blurry foreground, frilled dress, off-shoulder dress, bare shoulders, blurry, very long hair ,masterpiece,best quality,amazing quality,
Negative prompt
bad quality,worst quality,worst detail,sketch,censor,
Settings
Sampler
Euler a
Steps
40
Guidance
5
Seed
337188721
Size
1872x2736
Prompt
lazypos, (masterpiece, best quality, ultra-detailed), very aesthetic, flat color, black outline, solo, abstract style, 1girl, Derpy Hooves_(Mlp), Pale, light grayish apple green Hair, Light sapphire bluish gray Skin, Pony, mare, tail, Pegasus Wings, slim, hooves, (golden crossed eyes), long eyelashes, ears, (playful and clumsy expression:1.2), goofy smile, looking at viewer, BREAK (casual stylish famale outfit:1.4), tight shorts, trip bag BREAK dynamic happy pose, one leg lifted awkwardly, body leaning forward, over-the-shoulder glance BREAK cozy suburban street, small houses, mailboxe, trees, morning sunlight, envelopes scattered mid-air, BREAK warm sunlight, soft shadows, playful atmosphere, cinematic composition, sharp focus, lazypos
Negative prompt
paws, paw pads, long neck, breasts, nsfw, nudity, pussy, penis, nipples, bad hands,Extra fingers,Extra hands,noisy,unattractive,sloppy,ugly,(worst quality, low quality, normal quality:1.45),low-res
Settings
Sampler
Euler a
Steps
30
Guidance
6
Seed
2044437036
Size
820x1168
Clip skip
2
Prompt
<lora:Utility_-_Detail_Enhancer_by_BSS_v3:0.75>, <lora:Utility_-_Visual_Enhancer_by_BSS:0.75>, (sketch, jagged lines, stippling texture, drawing style:1.3), <lora:11Xx:0.25>, <lora:XXX477:0.25>, xxx667_illu, sketch, ligne claire, <lora:FINALE:0.25>, <lora:USNR STYLE_XL_loha:0.25>, usnr, <lora:ma1ma1helmes_b:0.25>, ma1ma1helmes_b_illu, glowing, sketch, (masterpiece, very aesthetic, very awa, newest, ultra-detailed, detailed textures, best quality, absurdres, 8k, correct anatomy:1), 1girl, white glowing crown, sharp metallic thorns, ethereal radiant light, white silhouette queen, motionless pose, grand golden throne, intricate ancient runes, regal carvings, gilded details, dark shadowy background, black ominous minimal crown, floating above, dark twin, light and shadow contrast, divine power, spectral glow, commanding presence, throne room stillness, warm gold shimmer, monochromatic queen, high contrast lighting, mystical atmosphere, regal majesty
Negative prompt
censored, artist name, watermark, text, patreon username, patreon logo, watermark, signature, kafka \(honkai: star rail\), bad hands, missing fingers, extra fingers, Smooth Negative-neg, SmoothNegative_Hands-neg, neghands-neg, bhands-neg, worst quality, bad eyes, lowres, jpeg artifacts, bad anatomy, interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands, deformed, distorted, disfigured, cloned face, error
Settings
Sampler
Euler a
Steps
24
Guidance
6
Seed
221819506
Size
832x1216
Clip skip
2
Prompt
masterpiece, best quality, very aesthetic, CivitAI BatouLaMenace, (flat color:1.5), (no lineart:1.5), (semi-realistic:2), (artist:Incase:0), (artist:Tsuaii:0), seal, feral, no humans, animal focus, light_particles, nature, white theme, blue sky, artic, artic, iceberg
Negative prompt
bad quality, worst quality, worst detail, sketch, censor, signature, watermark, text,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
561061719
Size
1024x1360
Clip skip
2
Prompt
mature female, solo, breasts, red hair, long hair, red eyes, large breasts, sunglasses, looking over eyewear, hair over one eye, sweater, looking at viewer, sleeveless, watch, adjusting eyewear, kirijou mitsuru, white sweater, bare shoulders, turtleneck, wristwatch, bangs, smile, tinted eyewear ,abstract background, foreshortening, ,masterpiece,best quality,amazing quality,
Negative prompt
bad quality,worst quality,worst detail,sketch,censor,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2781816361
Size
1024x1360
Clip skip
2
Prompt
pastel colors,(abara heiki:1.1),(watanabe tomari:1.1), (watari \(nijimukiokuiro\):0.5), 1girl, monster girl,long hair,twin tails, pointed ears,horns,((alternate eye color, multicolored eyes,sparkles, glowing eyes, eyeshadows,short eyebrows,thick eyebrows,long eyelashes:1.2,big eyes,perfect eyes, detailed eyes,detailed pupils,detailed iris,detailed cornea,long anime eyelashes, bags under eyes, galaxy eyes)), school uniform, sailor collar, pink bow, long sleeves, choker, earrings, hand near face, pensive pose, calm expression, mysterious aura, ethereal, dreamy, enigmatic, cosmic theme, otherworldly, elegant,purple theme,black hair,gradient hair, pastel shading, neon highlights, soft lighting,dramatic lighting,dark background,aesthetic,stylized, mystical, fantasy, celestial,surreal, gothic elegance,looking sideways, dynamic pose, extreme perspective, rare angle, dynamic angle, leaning forward, hands up, pale skin, ,masterpiece,best quality,amazing quality,
Negative prompt
bad quality,worst quality,worst detail,sketch,censor,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
4254694678
Size
1024x1360
Clip skip
2
Prompt
glitch, halo, solo, wings, angel, angel wings, looking at viewer, earrings, 1girl, feathered wings, jewelry, upper body, chromatic aberration, purple eyes, white wings, bangs, blonde hair, short hair, white hair, black background, jacket ,masterpiece,best quality,amazing quality,
Negative prompt
bad quality,worst quality,worst detail,sketch,censor,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2366430661
Size
1024x1360
Clip skip
2
Prompt
final fantasy, final fantasy vii, aerith gainsborough, 1girl, brown hair, closed mouth, collarbone, cropped jacket, dress, drill hair, drill sidelocks, flower, forehead, green eyes, hair ribbon, holding, holding flower, jacket, long hair, parted bangs, pink dress, pink ribbon, reaching, reaching towards viewer, red jacket, ribbon, short sleeves, sidelocks, smile, solo, yellow flower, amano yoshitaka, abstract, watercolor \(medium\) ,masterpiece,best quality,amazing quality,
Negative prompt
bad quality,worst quality,worst detail,sketch,censor,

Overview

WAI-illustrious-SDXL by WAI0731 is an Illustrious-based anime
checkpoint
known for recognizing thousands of characters by name and for producing clean, vivid illustrations with very short prompts. Version 16 refines color consistency and background relevance.
The author's main advice runs against habit: do not pile on quality tags or long
negative prompts
, because they make the image blurrier. A hires fix pass is recommended and often repairs limbs on its own.

Reference

Name
Type
What it is
Prompt
tags
A few Danbooru tags plus one or two quality tags. Short is better.
tags
Keep it to a handful of words: lowres, bad anatomy, worst quality.
5-7
6 is a good default.
Steps
25-30
Euler a.
Hires fix
1.5x, 0.4-0.5 denoise
Recommended; it fixes arms, legs and hands frequently.
AD
No install required - run AI models on the cloud
BitVector Prism is the easiest way to start: pick a model, type a prompt and generate in a clean web app, with nothing to configure. BitVector is also available on Discord and on the web (SpyGlass).

Step by step

  1. Write masterpiece, best quality, then the subject and setting tags.
  2. Name a character or describe one with a few appearance tags.
  3. Use a short negative prompt and
    CFG
    6, Euler a, 28 steps.
  4. Enable hires fix at 1.5x with 0.45 denoise.
  5. If the character looks too young for the scene, add (aged up:1.2) or (mature female:1.2) at the start of the prompt, as the author suggests.

Examples

Minimal prompt

masterpiece, best quality, 1girl, solo, long blue hair, white dress, underwater, bubbles, looking at viewer

Scene

masterpiece, best quality, 1boy, 1girl, rooftop, city lights, night, wind, standing, from behind, detailed background

Creative idea: flat graphic style

masterpiece, best quality, flat color, black outline, abstract background, 1girl, solo, profile, geometric shapes, limited palette

Tips

  • Over-tagging is the number one cause of blurry output on this model; remove tags until it sharpens.
  • Background tags (city at night, library, beach) are followed closely in v16.
  • Style
    LoRAs
    for
    Illustrious
    load cleanly at 0.6-0.8.
  • Flat color and bold outline prompts give a graphic poster look.

Troubleshooting

Blurry, soft image

Why it happens
Too many quality and aesthetic tags or an overlong negative prompt.

How to fix it
Cut the prompt down to the essentials and keep the negative to a few words.

Broken limbs

Why it happens
Single-pass generation.

How to fix it
Turn on hires fix at 1.5x; v16 and v17 were tuned so this pass repairs limbs.

AD
PirateDiffusion
No install required - run AI models on the cloud
PirateDiffusion is Telegram only and built for pros: thousands of models, LoRAs and workflows driven by chat commands, with unlimited generation on a fixed price plan.

Questions

Which base is it?

Illustrious XL, so Illustrious and most NoobAI LoRAs work.

Does it understand natural language?

Partly. Tags remain the most reliable way to control it.

Links and sources

Models in this guide

Written by
Captain

Related guides

Models
Playground v2 1024 Aesthetic: a second opinion to SDXL
Playground v2 is an SDXL-architecture model trained from scratch for aesthetics. Learn how it differs from SDXL, its CFG and step preferences, and the painterly and realistic prompts where it beats the original.
By Captain
2026-10-02
Models
DreamShaper XL 1.0: versatile fantasy and realism on SDXL
Lykon's DreamShaper XL 1.0 brings the famous DreamShaper look to SDXL: fantasy, portraits, cinematic scenes and illustration in one model. Learn its settings, prompt style and creative uses.
By Captain
2026-10-01
Models
Smooth Detail Booster: cleaner shading and more detail on Illustrious and Pony
DigitalPastel's Smooth Detail Booster LoRA adds detail and smooth shading to anime checkpoints without changing the art style. Learn the weight range, the prompts that help it, and how to pair it with quality tags.
By Captain
2026-09-29
Models
Hyper-SD XL: one-to-eight-step SDXL with a flexible LoRA
Hyper-SD from ByteDance accelerates SDXL checkpoints to as few as one step. Learn which variant to pick, the CFG and sampler rules, and how to combine it with checkpoints and LoRAs without losing quality.
By Captain
2026-10-02

More guides

Cloud services
Flat fee vs tokens: why unlimited plans like Graydient.ai are the best value for AI creators in 2026
A ranked cost comparison, with prices checked on 8 October 2026, of flat-fee unlimited plans like Graydient.ai against token and credit pricing from Midjourney, Leonardo, fal.ai, Replicate, Runway and Kling: what 1,000 images and 1,000 videos a month really cost on each, and why one fixed fee for unlimited images, video, audio, Grok LLM chat and web apps is the best value for creators who iterate.
By Captain
2026-10-08
Models
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.
By Captain
2026-09-30
Models
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.
By Captain
2026-10-01
Models
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.
By Captain
2026-10-02
Models
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.
By Captain
2026-10-03
Models
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.
By Captain
2026-09-29