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

Nova Anime XL v12.5: detailed character illustration with Illustrious

Topic: Models
By Captain
Published 2026-10-03
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
27
Guidance
4.5
Seed
1583078990
Size
672x1176
Clip skip
2
Prompt
kimono girl, orange and red kimono, oil-paper umbrella, nyotengu \(doa\), large breasts, cleavage, plump lips, red eyes, brown eyes, looking at viewer, long hair, straight hair, side locks, hime cut, makeup, bewitching, parted lips, Hair accessories, traditional, autumn leaves, red, orange, foreground, depth of field, Blurred periphery BREAK masterpiece, best quality, amazing quality, very aesthetic, newest, incredibly absurdres, ultra detailed, 8k, HDR, High quality digital art, official art, advertising style, detailed background, painting \(medium\), cinematic lighting, ray Tracing, ambient occlusion, dynamic composition, foreshortening,
Negative prompt
lowres, bad quality, worst quality, bad anatomy, bad hands, bad fingers, sketch, jpeg artifacts, watermark, censor, shiny skin
Settings
Sampler
Euler a
Steps
27
Guidance
5.5
Seed
3026014405
Size
672x1176
Clip skip
2
Prompt
Get on a bicycle Maid girl, Paper bag with bread, long hair, black hair, twin tails, brown eyes, red eyes, looking at viewer, slightly open mouth, black dress, white apron, knee-high socks, knee up, Street, In front of the store, bakery, foreground, depth of field, Blurred periphery, BREAK masterpiece, best quality, amazing quality, very aesthetic, newest, incredibly absurdres, ultra detailed, 8k, HDR, High quality digital art, official art, advertising style, detailed background, painting \(medium\), cinematic lighting, ray Tracing, ambient occlusion, dynamic composition, foreshortening,
Negative prompt
lowres, bad quality, worst quality, bad anatomy, bad hands, bad fingers, sketch, jpeg artifacts, watermark, censor, shiny skin
Settings
Size
1152x2016
Prompt
masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, 1girl, solo, cute, pink hair, long hair, choppy bangs, long sidelocks, nebulae cosmic purple eyes, rimlit eyes, facing to the side, looking at viewer, downturned eyes, light smile, red annular solar eclipse halo, red choker, detailed purple serafuku, big red neckerchief, (glowing stars in hand:1.2), fingers, arched back, from side, from below, dutch angle, portrait, upper body, head tilt, colorful, rim light, backlit, (colorful light particles:1.2), cosmic sky, aurora, chaos, perfect night, fantasy background, dreamlike atmosphere, BREAK, detailed background, blurry foreground, bokeh, depth of field, volumetric lighting
Negative prompt
multiple views, multiple angle, split view, grid view, two shot, outside border, picture frame, framed, border, letterboxed, pillarboxed, 2koma, modern, recent, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), sketch, jpeg artifacts, signature, watermark, username, (censored, bar_censor, mosaic_censor:1.2), simple background, conjoined, bad ai-generated Steps: 20, Sampler: Euler a, CFG scale: 4.5, Global Seed: 428649103, Seed: 141825754, Size: 768x1344, Clip skip: 2, Model hash: bd157e62de, Model: NovaAnimeILV125, Hires steps: 40, Hires upscale: 1.5, Hires Adjust: ("shadow": [0, 0, 0, 0.8, 1.0], "middle": [0, 0, 0, 0.9, 0.9], "highlight": [0, 0, 0, 1.1, 1.0]), Denoising strength: 0.4, Hires CFG Scale: 4
Settings
Size
1152x2016
Prompt
masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, 1girl, blonde hair, long hair, floating hair, blue eyes, looking at viewer, parted lips, medium breasts, puffy sleeve white dress, leaning side against tree, dutch angle, portrait, upper body, close-up, foreshortening, vines, green, forest, flowers, white butterfly, BREAK, dramatic shadow, depth of field, vignetting, (dappled sunlight, sunburst, lens flare:1.2), rim light, backlit, volumetric lighting
Negative prompt
multiple views, multiple angle, split view, grid view, two shot, outside border, picture frame, framed, border, letterboxed, pillarboxed, 2koma, modern, recent, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), sketch, jpeg artifacts, signature, watermark, username, (censored, bar_censor, mosaic_censor:1.2), simple background, conjoined, bad ai-generated Steps: 20, Sampler: Euler a, CFG scale: 4.5, Global Seed: 101724454, Seed: 1909963142, Size: 768x1344, Clip skip: 2, Model hash: bd157e62de, Model: NovaAnimeILV125, Hires steps: 40, Hires upscale: 1.5, Denoising strength: 0.4, Hires CFG Scale: 4
Version 12.5 of Nova Anime XL (Illustrious) is a reliable release for detailed character art and outfits. Learn its settings, prompt structure and ideas for themed character series.

Overview

Nova Anime XL IL v12.5 by Crody is an earlier
Illustrious
release of the series, still popular for consistent character rendering, detailed outfits and expressive faces. It shares the series' colorful palette and 2.5D range.
Settings as for the series: Euler a, 20-30 steps, Clip Skip 1-2,
CFG
5-7; unedited images are not for commercial use.

Reference

Name
Type
What it is
Quality string
tags
masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest
CFG
5-7
Steps / sampler
20-30, Euler a
Clip Skip
1-2
Negative
series list
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. Quality string, then a detailed outfit description.
  2. Add pose and expression tags.
  3. Euler a, 28 steps, CFG 6.
  4. Hires fix 1.5x at 0.4.
  5. Repeat with the same seed for a character series.

Examples

Kimono

masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest, 1girl, adult, solo, orange and red kimono, oil-paper umbrella, long straight hair, hime cut, red eyes, looking at viewer, autumn street

Maid on a bicycle

masterpiece, best quality, amazing quality, 1girl, adult, solo, maid, black dress, white apron, riding a bicycle, paper bag with bread, twin tails, street, bakery in the background

Creative idea: four seasons outfits

Same character, same seed: spring raincoat, summer yukata, autumn coat, winter scarf; keep the quality string.

Tips

  • Traditional clothing (kimono with an oil-paper umbrella) renders with rich detail.
  • Props (paper bag with bread, bicycle) are followed.
  • Add street or scenery tags for context.
  • Character names from Illustrious work.

Troubleshooting

Outfit details merge

Why it happens
Too many clothing tags.

How to fix it
Keep to four or five garment tags.

Large heads

Why it happens
Series tendency.

How to fix it
Add large head to the negative.

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

Commercial use?

Edited images only.

Which Nova for scenery?

v15 leans more to scenery; v12.5 to characters.

Links and sources

Models in this guide

Written by
Captain

Related guides

Models
CyberRealistic Positive (Pony) embedding: one word toward realism
Cyberdelia's positive textual inversion for Pony models nudges output toward realism when placed at the start of the prompt. Learn where to put it, how it pairs with the negative embedding and prompt ideas.
By Captain
2026-10-02
Models
Nova Cartoon XL v6: western cartoon and toon styles on SDXL
Crody's Nova Cartoon XL is focused on cartoon and toon aesthetics. Learn its CFG 3-5 setting, the toon prompt template, negative list that keeps anime out and ideas for character and scene work.
By Captain
2026-10-03
Models
Xu Er Thick Paint style filter: painterly impasto texture on Illustrious
XUERYCJ's style LoRA adds thick-paint texture, complex composition and light enhancement to Illustrious images, with different looks per sampler. Learn the XUER guangying trigger, weight 0.8-0.9, hires value and sampler effects.
By Captain
2026-09-30
Models
Nova Anime XL v14: flat color, vector looks and illustrated scenes
Version 14 of Nova Anime XL (Illustrious) is loved for flat-color and vector-like renders as well as regular anime. Learn its settings, the flat color tag recipe and creative uses.
By Captain
2026-09-30

More guides

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
Models
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.
By Captain
2026-09-30