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

Nova Anime XL v14: flat color, vector looks and illustrated scenes

Topic: Models
By Captain
Published 2026-09-30
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
DPM++ 2M Karras
Steps
40
Guidance
7
Seed
534739904
Size
832x1216
Clip skip
2
Prompt
Show the side of the mug as well as the top. A whimsical illustration featuring a miniature gingerbread village nestled inside the top of a steaming ceramic coffee mug. The mug is filled with rich, dark coffee that forms a gently flowing river through the center of the village, releasing soft curls of steam like a natural hot spring. Along the riverbanks sit tiny gingerbread houses with frosted roofs, candy-cane trim, and glowing sugar windows, lightly dusted with powdered-sugar snow. Marshmallow snowman villagers populate the scene, some gathered near the warm coffee river, others strolling between cookie pathways and icing-covered bridges. Snow blankets the village in soft mounds, made of whipped cream and sugar crystals, adding texture and depth. The mug rests on a wooden tabletop, evoking a cozy winter interior, with warm ambient lighting that casts gentle shadows and enhances the festive atmosphere. The composition uses a slightly elevated perspective, emphasizing the miniature scale and playful illusion. The overall mood is cozy, magical, and serene, echoing the warmth of winter holidays and Christmas. The illustration style resembles a watercolor or storybook illustration, with soft edges, warm tones, and a comforting, nostalgic feel.
Negative prompt
Base:bad quality,worst quality,worst detail,sketch,censor, worst quality, low quality, text, watermark, bad anatomy, artist name, signature, humans, people, 1girl, girl, woman, man, people, fire, flames
Settings
Sampler
DPM++ 2M
Steps
50
Guidance
7
Seed
2120215179
Size
1280x1856
Clip skip
2
Prompt
HDR, 8K, masterpiece, best quality, amazing quality, very aesthetic, (realism:1), (flat color:2), (haiz_ai:1), (no lineart:1), (no outline:1), (Flat vector:1), (artist:incase:0.5), (Ryuuou no Oshigoto!:1), (Blue archive style :0.8), facing the camera, looking at viewer, depth of field, volumetric lighting, cinematic lighting, cinematic atmosphere, (Lucky cat mascot, Lucky Cat, Maneki-neko, smug look), (winter time, snow)
Negative prompt
Base:bad quality,worst quality,worst detail,sketch,censor, worst quality, low quality, text, watermark, bad anatomy, artist name, signature,
Settings
Sampler
DPM++ 2M
Steps
30
Guidance
4
Seed
1841653292
Size
1280x1856
Clip skip
2
Prompt
HDR, 8K, masterpiece, best quality, amazing quality, very aesthetic, (realism:1), (flat color:2), (haiz_ai:1), (no lineart:1), (no outline:1), (Flat vector:1), (artist:incase:0.5), (Ryuuou no Oshigoto!:1), (Blue archive style :0.8), depth of field, volumetric lighting, cinematic lighting, cinematic atmosphere, a girl making a wish in her hands and blowing it into the sky like its a glowing star, (the girl is wearing a fluffy winter coat, black hair, white and red outfit coloring), (snow, snowing, lots of snow, winter time feeling, magical, night time, sparkling stars in the sky)
Negative prompt
Base:bad quality,worst quality,worst detail,sketch,censor, worst quality, low quality, text, watermark, bad anatomy, artist name, signature,
Settings
Sampler
DPM++ 2M
Steps
40
Guidance
7
Seed
534739904
Size
1280x1856
Clip skip
2
Prompt
Show the side of the mug as well as the top. A whimsical illustration featuring a miniature gingerbread village nestled inside the top of a steaming ceramic coffee mug. The mug is filled with rich, dark coffee that forms a gently flowing river through the center of the village, releasing soft curls of steam like a natural hot spring. Along the riverbanks sit tiny gingerbread houses with frosted roofs, candy-cane trim, and glowing sugar windows, lightly dusted with powdered-sugar snow. Marshmallow snowman villagers populate the scene, some gathered near the warm coffee river, others strolling between cookie pathways and icing-covered bridges. Snow blankets the village in soft mounds, made of whipped cream and sugar crystals, adding texture and depth. The mug rests on a wooden tabletop, evoking a cozy winter interior, with warm ambient lighting that casts gentle shadows and enhances the festive atmosphere. The composition uses a slightly elevated perspective, emphasizing the miniature scale and playful illusion. The overall mood is cozy, magical, and serene, echoing the warmth of winter holidays and Christmas. The illustration style resembles a watercolor or storybook illustration, with soft edges, warm tones, and a comforting, nostalgic feel.
Negative prompt
Base:bad quality,worst quality,worst detail,sketch,censor, worst quality, low quality, text, watermark, bad anatomy, artist name, signature, humans, people, 1girl, girl, woman, man, people, fire, flames
Settings
Sampler
DPM++ 2M Karras
Steps
36
Guidance
6
Seed
381961482
Size
832x1216
Clip skip
2
Prompt
Show the side of the mug as well as the top. Steam comes from the chimney of the gingerbread houses. A whimsical illustration featuring a miniature gingerbread village nestled inside the top of a steaming ceramic coffee mug. The mug is filled with rich, dark coffee that forms a gently flowing river through the center of the village, releasing soft curls of steam like a natural hot spring. Along the riverbanks sit tiny gingerbread houses with frosted roofs, candy-cane trim, and glowing sugar windows, lightly dusted with powdered-sugar snow. Marshmallow snowman villagers populate the scene, some gathered near the warm coffee river, others strolling between cookie pathways and icing-covered bridges. Snow blankets the village in soft mounds, made of whipped cream and sugar crystals, adding texture and depth. The mug rests on a wooden tabletop, evoking a cozy winter interior, with warm ambient lighting that casts gentle shadows and enhances the festive atmosphere. The composition uses a slightly elevated perspective, emphasizing the miniature scale and playful illusion. The overall mood is cozy, magical, and serene, echoing the warmth of winter holidays and Christmas. The illustration style resembles a watercolor or storybook illustration, with soft edges, warm tones, and a comforting, nostalgic feel.
Negative prompt
Base:bad quality,worst quality,worst detail,sketch,censor, worst quality, low quality, text, watermark, bad anatomy, artist name, signature, humans, people, 1girl, girl, woman, man, people, fire, flames
Settings
Sampler
Euler a
Steps
36
Guidance
5.5
Seed
984799017
Size
832x1216
Clip skip
2
Prompt
anime-style cinematic illustration, emotional storytelling, bittersweet, clearly defined, softly glowing thought bubble separating past and present, A young woman sitting on the floor of an empty suburban living room that once belonged to her grandparents, nighttime. The room is dark and quiet, lit only by soft blue light coming in through the windows from outside streetlights and distant houses. The furniture is sparse and slightly worn, evoking abandonment and nostalgia. The woman sits with her knees pulled close, looking down thoughtfully, expression gentle and melancholic, reflecting on warm memories of the past. A large, softly glowing thought bubble occupies nearly half of the composition, blending naturally into the scene. Inside the thought bubble is the same living room, but during Christmas in the past: warmly lit, cozy, filled with holiday decorations, a glowing Christmas tree, colorful ornaments, wrapped presents, and twinkling lights. A loving grandmother smiles warmly near the tree, creating a feeling of comfort, family, and joy. Strong contrast between cool, dark present and warm, golden memory, soft lighting, gentle glow, emotional atmosphere, subtle film grain, winter night mood, anime illustration style, highly detailed, expressive faces, cinematic framing.
Negative prompt
low quality, blurry, flat lighting, overexposed, distorted faces, extra limbs, bad anatomy, cluttered composition, text, watermark, logo, modern furniture, futuristic elements, horror, exaggerated expressions
Settings
Sampler
Euler a
Steps
19
Guidance
6
Seed
2122395225
Size
832x1216
Clip skip
2
Prompt
"(masterpiece, best quality, high quality, highres), very awa, highres, absurdres, (naguru \(cyoroama\):1.1), (chii-kun \(seedyoulater\):0.9), (no humans:1.1), (cute:1.2), comfy, solo, cozy, (frog:1.1), (forest stream:0.8), (barefoot crossing:0.8), (smooth stones:0.8), (sunlight through leaves:0.8), (water sound:0.8), depth of field, cinematic, beautiful background, "
Negative prompt
bad quality, worst quality, worst detail, censor, lowres, worst aesthetic, bad anatomy, signature, watermark, logo, (hair:1.2), (furry:1.2),
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.

Overview

Nova Anime XL IL v14 by Crody is an
Illustrious
release of the colorful Nova Anime line. Besides standard anime it responds strongly to flat color, no lineart and flat vector tags, producing clean graphic illustrations that look like vector art.
Settings as for the series: Euler a, 20-30 steps, Clip Skip 1-2,
CFG
5-7; licence restricts commercial use of unedited images.

Reference

Name
Type
What it is
Quality string
tags
HDR, 8K, masterpiece, best quality, amazing quality, very aesthetic
Flat recipe
tags
(flat color:2), (no lineart:1), (no outline:1), (flat vector:1)
CFG
5-7
Steps / sampler
20-30, Euler a
Clip Skip
1-2
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 the flat recipe if you want vector looks.
  2. Describe the subject.
  3. Euler a, 28 steps, CFG 6.
  4. Negative: text, watermark, worst quality.
  5. Hires fix 1.5x at 0.35 to keep edges clean.

Examples

Vector portrait

HDR, 8K, masterpiece, best quality, amazing quality, very aesthetic, (flat color:2), (no lineart:1), (no outline:1), (flat vector:1), 1girl, solo, bob haircut, headphones, simple background

Illustration

masterpiece, best quality, amazing quality, a whimsical illustration of a miniature gingerbread village nestled inside a steaming ceramic coffee mug, show the side of the mug and the top

Creative idea: sticker set

masterpiece, best quality, (flat color:2), (no outline:1), sticker, a sleepy cat in a teacup, simple white background

Tips

  • Weighted (flat color:2) is the key to the vector look.
  • Illustration prompts (a gingerbread village inside a coffee mug) work in natural language too.
  • Artist tags
    at low weight (artist:name:0.5) shift the style subtly.
  • Great for icons and stickers.

Troubleshooting

Lineart returns

Why it happens
Flat tags under-weighted.

How to fix it
(flat color:2) and (no lineart:1.2).

Muddy gradients

Why it happens
CFG high.

How to fix it
CFG 5.

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, per the author.

v14 vs v15?

v14 is favored for flat styles, v15 for general anime.

Links and sources

Models in this guide

Written by
Captain

Related guides

Models
One Obsession 17 RED: warm, friendly anime illustration
The 17 RED release of One Obsession is a favorite for cozy, warm-toned anime scenes. Learn its template, settings and ideas for cheerful character illustrations.
By Captain
2026-09-29
Models
Super Eye Detailer XL: sharper, more realistic eyes on Pony and SDXL
Stable Yogi's Super Eye Detailer brings crisp iris detail and natural eye realism to SDXL and Pony images. Learn the weight, trigger words, placement in the prompt and companion embeddings.
By Captain
2026-10-02
Models
Nova Anime XL (Illustrious): colorful anime, 2.5D and fantasy scenery
Crody's Nova Anime XL is a vivid Illustrious anime checkpoint. Learn its Euler a settings, quality tag strings, negative prompt, licence note and prompt ideas for colorful characters and landscapes.
By Captain
2026-09-29
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

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