WAI-illustrious-SDXL v16: character-rich anime with simple prompts
Fast Facts:
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. |
Step by step
- Write masterpiece, best quality, then the subject and setting tags.
- Name a character or describe one with a few appearance tags.
- Enable hires fix at 1.5x with 0.45 denoise.
- 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.
- 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.
Questions
Which base is it?
Does it understand natural language?
Partly. Tags remain the most reliable way to control it.
Links and sources
Models in this guide
Written by
Runs this ship. Has opinions about VAE decode times that nobody asked for. Believes weights want to be free and that any model you cannot download is a subscription with extra steps. Will not be taking questions about the 400 GB of checkpoints on the NAS.
All guides by Captain
Related guides
Playground v2 1024 Aesthetic: a second opinion to SDXL
Oct 2, 2026
DreamShaper XL 1.0: versatile fantasy and realism on SDXL
Oct 1, 2026
Smooth Detail Booster: cleaner shading and more detail on Illustrious and Pony
Sep 29, 2026
Hyper-SD XL: one-to-eight-step SDXL with a flexible LoRA
Oct 2, 2026
Pony vs Illustrious (2026): which anime model should you use?
Oct 14, 2026
More guides
Stable Diffusion XL 1.0: prompts, settings and what it still does best
Oct 1, 2026
Best AI Models for Anime in 2026: MOSS-Image, Anima, Illustrious
Oct 16, 2026
CyberRealistic Pony v13: the settings and prompts that make it shine
Oct 1, 2026
Prefect Illustrious XL v7: polished anime with soft lighting
Oct 2, 2026
One Obsession v19 Atypical: beginner-friendly anime with hidden artist strings
Oct 3, 2026