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

Prefect Illustrious XL v7: polished anime with soft lighting

Topic: Models
By Captain
Published 2026-10-02
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
24
Guidance
6
Seed
1706603197
Size
832x1216
Clip skip
2
Prompt
masterpiece, best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, beautiful face, beautiful eyes, soft lighting, bloom effect, detailed background, cute girl, eyelashes, foreshortening, Aka-Oni, oni, (oni horns), colored skin, (red skin:1.3), smooth horns, black horns, straight horns, mature, long hair, hair intakes, braided sidelock, hair between eyes, fair skin, medium breasts, exposed shoulders, white compression shirt, high collar shirt, blue sash around waist, white harem pants, centered composition, close-up shot, face focus, looking at viewer, curious expression, parted lips, standing, leaning forward, dynamic pose, outdoors, day, ocean, tirol chocolate, valentine, incoming food, hand up, [(by alphonse_\(white_datura\):1.3)|(by kana616:0.8)], [(by hen-tie:1.3)|(by kagami_\(galgamesion\):1.2)], (by kinokohime:1.2), (by yatsuha_\(hachiyoh\):0.8),
Negative prompt
bad quality, worst quality, worst detail, sketch, censor, signature, watermark, text,
Settings
Sampler
Euler a
Steps
24
Guidance
6
Seed
582115674
Size
832x1216
Clip skip
2
Prompt
masterpiece, best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, beautiful face, beautiful eyes, soft lighting, bloom effect, detailed background, cute girl, eyelashes, foreshortening, Aka-Oni, oni, (oni horns), colored skin, (red skin:1.3), smooth horns, black horns, straight horns, mature, white hair, very long hair, high ponytail, bangs, hair flowing in wind, red hair ribbon, looking away, profile, side view, wearing white traditional clothing, white hanfu, white kimono, wide sleeves, ornate patterns, gold embroidery, large gold earrings, dangling earrings, tassels, holding katana, sword hilt, sword tassel, white background, simple background, painterly, watercolor (medium), sketchy, wash painting, expressive brushstrokes, [(by alphonse_\(white_datura\):1.3)|(by kana616:0.8)], [(by hen-tie:1.3)|(by kagami_\(galgamesion\):1.2)], (by kinokohime:1.2), (by yatsuha_\(hachiyoh\):0.8),
Negative prompt
bad quality, worst quality, worst detail, sketch, censor, signature, watermark, text,
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
5
Seed
13077473
Size
832x1216
Prompt
masterpiece,best quality,amazing quality,absurdres, BREAK tohsaka rin, 1girl, blonde hair, bow, breasts, closed mouth, earrings, female focus, hair bow, jewelry, light frown, long hair, looking to the side, medium breasts, portrait, red bow, red eyes, red lips, skull, solo
Negative prompt
bad quality,worst quality,worst detail,sketch,censored, artist name, signature, watermark,patreon username, patreon logo,pov, doorway, door, tattoo
Settings
Sampler
Euler a
Steps
29
Guidance
3.5
Seed
1940659621
Size
832x1216
Clip skip
2
Weight used
1
Prompt
masterpiece, best quality, very awa, absurdres, model style, stylist, soft lighting, masterpiece, absolutely eye-catching, (beautiful face), ultra-detailed, 8K, illustration,CG, cute girl, eyelashes, long eyelashes, shallow depth of field, anime coloring, flat color Aka-Oni, oni, (oni horns), colored skin, (red skin:1.3), smooth horns, black horns, straight horns, mature, pointy ears, (rella:1.2), (redum4:1.2) (au \(d elete\):1.2) (dino \(dinoartforame\):1.1), wlop, sitting on the whale, serafuku, Above the clouds, sky, goldfish, surreal, a girl sitting on a huge whale, flying whale, fluffy clouds, absurdly detailed composition, dynamic pose, foreshortening, light smile, moon, close-up,
Negative prompt
bad quality, worst quality, worst detail, sketch, censor, signature, watermark, text, lazyneg
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
5
Seed
1980025160
Size
832x1216
Clip skip
2
Prompt
masterpiece,best quality,amazing quality, absurdres,blush <lora:cissia_zenless_zone_zero_ilxl_goofy:1> cissia \(zenless zone zero\), 1girl, large breasts, hair ornament, yellow background, looking at viewer, open mouth, black skirt, black thighhighs, detached sleeves, hands on own hips, black choker, fang, ahoge, bare shoulders, pom pom (clothes), simple background, red shirt, ear piercing, thigh strap, virtual youtuber, leotard, red nails, covered navel, blush, hairclip, cowboy shot, earrings, tail
Negative prompt
bad quality,worst quality,worst detail,sketch,censored, artist name, signature, watermark,patreon username, patreon logo,pov, doorway, door , shiny skin, wet,
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
1396105694
Size
1024x1536
Prompt
masterpiece, best quality, amazing quality, absurdres, bW9t, flat color, solo, 1girl, k1k1, demon girl, monster girl, purple hair, long hair, yellow sclera, red eyes, red skin, horns, black lipstick, black eyeliner fangs, earrings, small breasts, slender body, screencap, open mouth, black top, high-waisted jeans, choker, indoors, bathroom, bathroom, tile wall, tiles, mai_pose_brushing_teeth, brushing_teeth, holding_toothbrush, foam in mouth, lazypos
Negative prompt
bad quality, worst quality, lowres, pony, cutie mark, (worst quality, low quality:1.4), blurry, (source filmmaker:0.3), duplicate, out of frame, blurry, gaping, pubic hair, censored, watermark, text, mutated, aliasing, distorted, 3d, ugly, ((extra limbs)), ((poorly drawn eyes)), poorly drawn, low quality, ((out of focus)), ((e621_p_low)), ((signature)), ((watermark)), username
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
5
Seed
1980025156
Size
832x1216
Clip skip
2
Prompt
masterpiece,best quality,amazing quality, absurdres,blush <lora:cissia_zenless_zone_zero_ilxl_goofy:1> cissia \(zenless zone zero\), 1girl, large breasts, hair ornament, yellow background, looking at viewer, open mouth, black skirt, black thighhighs, detached sleeves, hands on own hips, black choker, fang, ahoge, bare shoulders, pom pom (clothes), simple background, red shirt, ear piercing, thigh strap, virtual youtuber, leotard, red nails, covered navel, blush, hairclip, cowboy shot, earrings, tail
Negative prompt
bad quality,worst quality,worst detail,sketch,censored, artist name, signature, watermark,patreon username, patreon logo,pov, doorway, door , shiny skin, wet,
Settings
Sampler
Euler a
Steps
30
Guidance
3.5
Seed
470877991
Size
832x1216
Clip skip
2
Weight used
1
Prompt
masterpiece, best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, cinematic, ambient occlusion, raytracing, soft lighting, blum effect, masterpiece, absolutely eye-catching, intricate cinematic background, 8K, illustrating, CG, silhouette, outline, featureless, shadow play, masterpiece, best quality, erotic, I love yuri, impressionism, painterly (rella:1.2), (redum4:1.2) (au \(d elete\):1.2) (dino \(dinoartforame\):1.1), wlop,
Negative prompt
bad quality, worst quality, worst detail, sketch, censor, signature, watermark, text, lazyneg, furry,multiple hands
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.

Overview

Prefect
Illustrious
XL by Goofy_Ai is an Illustrious-based anime
checkpoint
focused on polished illustration with depth of field, bloom and detailed backgrounds. Version 7 continues the series' cleanup of style influence for a more neutral, flexible base.
Recommended settings from the author: Clip Skip 1, Euler a or DPM++ 2M,
CFG
5-6, ADetailer or a face inpaint pass, and an
img2img
upscale with 4x-UltraSharp.

Reference

Name
Type
What it is
Prompt template
tags
masterpiece, best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, then the subject
CFG
5-6
Author's range.
Steps / sampler
25-30, Euler a
Or DPM++ 2M.
Clip Skip
1
Unusual for anime models; the author used 1 on every example.
LoRAs
0.7-1.0
Illustrious
LoRAs
.
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. Paste the template, then the subject tags.
  2. Clip Skip 1, CFG 5.5, 28 steps, Euler a.
  3. Add soft lighting, bloom effect for the house style.
  4. Face detail pass with ADetailer or inpaint.
  5. Img2img upscale 1.5x at 0.3 with 4x-UltraSharp.

Examples

Portrait

masterpiece, best quality, ultra-detailed, very aesthetic, depth of field, best lighting, detailed illustration, detailed background, 1girl, solo, silver hair, red eyes, dark kimono, lantern festival, soft lighting, bloom effect

Scene

masterpiece, best quality, ultra-detailed, very aesthetic, detailed background, 2girls, cafe terrace, rain, umbrellas, warm light, smile

Creative idea: travel illustration

masterpiece, best quality, ultra-detailed, very aesthetic, depth of field, 1boy, solo, backpacker, mountain pass, prayer flags, wind, detailed background

Tips

  • Depth of field in the template gives its signature blurred backgrounds; remove it for flat scenes.
  • Named character tags work via Illustrious.
  • Keep the
    negative prompt
    short.
  • Style LoRAs at 0.7 blend well.

Troubleshooting

Overexposed bloom

Why it happens
Bloom tag plus high CFG.

How to fix it
CFG 5 or drop bloom effect.

Soft faces

Why it happens
Depth of field at small face sizes.

How to fix it
ADetailer or inpaint the face.

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

Clip Skip 1 or 2?

The author used 1; try both and keep what you like.

Compatible LoRAs?

Illustrious and most NoobAI LoRAs.

Links and sources

Models in this guide

Written by
Captain

Related guides

Models
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.
By Captain
2026-10-03
Models
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.
By Captain
2026-09-29
Models
CyberRealistic Pony v13: the settings and prompts that make it shine
Version 13 of CyberRealistic Pony is a favorite for cinematic environments and natural portraits. Learn Cyberdelia's recommended settings, the score chain, and ideas for atmospheric scenes.
By Captain
2026-10-01
Models
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.
By Captain
2026-10-03

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