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

iLustMix v7 Cinematic: semi-realistic Illustrious with film lighting

Topic: Models
By Captain
Published 2026-09-29
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
4031141371
Size
832x1216
Prompt
close-up, solo, tongue, 1girl, food, saliva, , open mouth, candy, simple background, blue background, large lollipop, tongue out, aqua background, lips, hand up, holding, looking at viewer, licking, seductive, half-closed eyes,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2027005183
Size
832x1216
Prompt
1girl, horns, solo, long hair, pointy ears, looking at viewer, brown hair, bare shoulders, , upper body, sheep horns, , light brown eyes, dress, choker, curled horns, straight hair, breasts,, detached sleeves, , brown dress, nose, from side, , , brown hair, , eyelashes, , see-through, hazel eyes, looking to the side, strapless dress, demon girl, light particles, brown background, bangs, , backlighting, gradient background, bokeh,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
3575610301
Size
832x1216
Prompt
outdoors, lake,, water, , sunset, light ray, lens flare, reflection, scenery, no humans, horizon, city lights, , fog, trees,
Settings
Sampler
Euler a
Steps
30
Guidance
5
Size
832x1216
Prompt
safe_pos, masterpiece, best quality, good quality, very aesthetic, absurdres, newest, 8K, realistic, 1girl, solo, clare, blonde hair, glowing eyes, orange eyes, blonde hair, bob cut, cape, bodysuit, pauldrons BREAK simple background, orange background, argyle background, BREAK upper body, dutch angle, dynamic pose, posing, fighting stance, holding sword, <lora:MoriiMee_Gothic_Niji_Style_Illustrious_r1:0.5> artist:moriimee, <lora:ATRex_style:0.7> TRexStyle, , , (anime coloring, anime screencap), shiny skin,
Negative prompt
parted lips, safe_neg, worst quality, bad quality, low quality, missing fingers, extra fingers, sweat, dutch angle,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
1943843364
Size
832x1216
Prompt
1girl, close-up, tears, glowing, eye focus, freckles, crying, green eyes,,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
4044893441
Size
832x1216
Prompt
robot girl, ((robot body)), robot joints, proud, medium breasts, wide hips, metal body, angelic, glowing white details, gold details, scifi, transparent body, vintage robot, steampunk, wide robot head, inhuman head, , holding large shield, protector, (large thighs:1.2), steampunk face, being shot at, taking cover, action shot, side view,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
646626680
Size
832x1216
Prompt
1girl, solo, blonde hair, , goggles, snow, parted lips, long hair, lips, ski goggles, mountain, tree, portrait, pink jacket, winter, snowing, , nose, from side, jacket, outdoors, breath, flush, platinum blonde, , warming hands, hands up, looking at viewer,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2147761923
Size
832x1216
Prompt
1girl, pale, white skin, colored skin, pale skin, soft lips, glossy lips, elf, pointy ears, detailed eyes, glowing eyes, muscular woman, armor, cape, leather armor, scar, scars on face, white hair, long hair, messy hair, black armor, black leather,,

Overview

iLustMix is an Illustrious-based
checkpoint
by GZees aimed at semi-realistic results: detailed bodies, well-formed hands and refined faces with an artistic finish. The v7 Cinematic release adds film-style lighting and color grading.
Author's key settings: Euler a, 25 steps, and the quality tags masterpiece, best quality, amazing quality.

Reference

Name
Type
What it is
Quality tags
masterpiece, best quality, amazing quality
At the start.
5-7
Steps /
sampler
25, Euler a
Author's values.
Resolution
1024
Widescreen 1344x768 for cinematic frames.
Negative
short
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 tags, then subject and scene.
  2. Add cinematic lighting, film grain, anamorphic for the look.
  3. Euler a, 25 steps,
    CFG
    6.
  4. Use 1344x768 for widescreen.
  5. Face detail pass if needed.

Examples

Widescreen

masterpiece, best quality, amazing quality, 1girl, solo, trench coat, rainy train platform at night, cinematic lighting, film grain, anamorphic, detailed background

Graphic portrait

masterpiece, best quality, amazing quality, close-up, 1girl, solo, aqua background, holding a large lollipop, looking at viewer, soft light

Creative idea: fantasy film still

masterpiece, best quality, amazing quality, 1girl, horns, pointy ears, brown dress, detached sleeves, candlelit library, rim light, cinematic

Tips

  • Semi-realistic means describe materials; fabric and skin render well.
  • Low-key lighting and rim light are its strength.
  • Simple colored backgrounds (aqua background) give graphic portraits.

Troubleshooting

Too realistic or too anime

Why it happens
Missing style anchor.

How to fix it
Add illustration or realistic explicitly.

Dark, muddy frames

Why it happens
Cinematic tags with no light source.

How to fix it
Name the key light.

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

Steps?

25 with Euler a per the author.

Clip Skip?

2 works.

Links and sources

Models in this guide

Written by
Captain

Related guides

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
Models
Hassaku XL (Illustrious) v3.1: bright, distinct anime without Danbooru clutter
Ikena's Hassaku XL is a bright anime model with a clear house style. Learn why it avoids Danbooru metadata tags, its CFG and negative advice, and prompt ideas for vivid characters.
By Captain
2026-10-01
Models
CyberRealistic Pony v17: photographic portraits with Pony control
Version 17 of CyberRealistic Pony is prized for natural portrait lighting. Learn the score chain, Cyberdelia's exact settings, lens language and ideas for cinematic portraits.
By Captain
2026-10-02
Models
CyberRealistic XL v10: super clean photorealism on SDXL
Cyberdelia's CyberRealistic XL is the SDXL checkpoint for clean, sharp photoreal images. Learn the recommended DPM++ 2M SDE Karras settings, the DMD2 fast path, upscaling advice and prompt ideas.
By Captain
2026-10-03

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