Krea2 Melancholy v2: cinematic, restrained, emotional realism
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
Size
3072x5504
Prompt
zidiusArt, anime-style tiny fox, made of sparkling white and black fire, sleeping, curled up, cradled in a nest of multicolored painterly styled butterflies. Forest floor at late evening, red and yellow golden sunset lighting. Autumn leaves.
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
1912977451
Size
832x1248
Weight used
1
Prompt
zidiusArt, A hyper-detailed magical realism illustration of an old, weathered glass lantern sitting on a wet, icy surface during a heavy snowfall. Inside the lantern, a miniature, cozy winter city scene is captured: narrow cobblestone streets, tall European-style buildings with glowing warm yellow windows, a vintage blue tram, and tiny silhouettes of people walking in the snow. The lantern has a rusty metal cap and handle. Snowflakes are falling both inside and outside the lantern. The wet ground below reflects the warm golden light from the lantern. Atmospheric, cinematic lighting, volumetric fog, cozy winter vibe, masterpiece, 8k resolution, intricate details, watercolor and digital painting hybrid style.
Settings
Size
3072x5504
Prompt
zidiusArt, a Christmas present, it's lid popping off in a dramatic fashion, revealing its contents. Under the Christmas tree. Different multicolored neon glowing snowflake ornaments hang delicately on the tree. very cute chibi 2D paper cutout kitten pops out from the present, with an adorable UwU face. It wears a pink collar with a Christmas bell on the collars center, is extremely adorable. It's eyes are large and filled with shimmery sparkling glee. The present is adorned with small snowflakes. Atmospheric lighting from the tree. atmosphere is both natural and cute. The kitten is a 2D paper cutout, hand-drawn with colored gel pens. A professional image taken from a Sony A7R IV, 50mm f/1.8 lens, resembling real-life photography, natural lighting, professional photography, soft natural lighting, realistic depth of field, shallow depth of field.
Settings
Sampler
euler
Steps
8
Guidance
1
Seed
320116228
Size
832x1248
Weight used
1
Prompt
zidiusArt, whimsical book illustration, a tall slender tree with a cozy two-story house built into the upper branches, a long rustic wooden ladder leaning against the tree trunk, a small squirrel standing at the bottom left looking up, a massive detailed full moon in the upper left corner, deep teal starry night sky, warm yellow light glowing from the arched door and windows, smoke drifting from the brick chimney, painterly style, magical atmosphere, gold and teal color palette.
Overview
Krea2
- Melancholy (v2.0, for Krea2 and Krea2 Turbo) by zidius is a style
LoRA
built for melancholic, cinematic images: carefully composed scenes, subdued colors, controlled lighting, very shallow depth of field and a grounded, realistic look. Version 2 improves consistency and image quality while keeping the signature mood.
Trigger word: zidiusArt. It also handles anime-style and illustrative subjects with the same atmosphere.
Reference
Name | Type | What it is |
|---|---|---|
Trigger | zidiusArt | Start of prompt. |
LoRA weight | 0.7-1.0 | |
Steps / guidance | 8 / 1 | Krea 2 defaults. |
Palette | subdued | Describe muted colors; it reinforces them. |
Combination | sliders | Light slider at -1 deepens the mood. |
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
- zidiusArt, then a quiet scene with one subject.
- Mention weather and time: late evening, snowfall, overcast.
- Weight 0.9.
- Use shallow depth of field words.
- Avoid cheerful color words.
Examples
Lantern
zidiusArt, a hyper-detailed magical realism illustration of an old weathered glass lantern on an icy surface during heavy snowfall, a miniature cozy winter city inside it, shallow depth of field.
Fox
zidiusArt, an anime-style tiny fox made of sparkling white and black fire, sleeping curled up in a nest of painterly butterflies, forest floor at late evening, golden sunset light.
Creative idea: empty places
zidiusArt, an empty laundromat at 3 a.m., one machine spinning, fluorescent light, rain on the window, 35mm.
Tips
- Lanterns, rain, snow and empty rooms are its vocabulary.
- Works for small animals and objects as much as people.
- Pair with the Melancholy aesthetic in anime prompts for a Ghibli-adjacent mood.
- Keep compositions simple.
Troubleshooting
Too dark
Why it happens
Mood words stack.
How to fix it
Add one light source and lower weight to 0.7.
Style weak
Why it happens
Trigger missing.
How to fix it
Add zidiusArt first.
AD

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
Turbo?
Yes, there is a Turbo version.
Trigger?
zidiusArt.
Links and sources
Models in this guide
Written by
Captain
Related guides
Models
Fat/Skinny Weight Slider for Krea 2: body weight as a number
Loraholic's Weight Slider adjusts body mass in Krea 2 across a -10 to 10 range designed for predictability. Learn how to use it, stability notes and ideas for character design and fitness illustration.
By Captain
2026-10-01
Models
Krea2 Enhancer: cleaner detail and lighting for any Krea 2 style
vrgamedevgirl's Krea2 Enhancer LoRA polishes Krea 2 images across realistic, anime, product and fantasy styles without changing the prompt's intent. Learn the weight, workflow and ideas.
By Captain
2026-09-30
Models
UltraReal for Krea 2 and Klein 9B: texture back into smooth AI images
vizsumit's UltraReal LoRAs reduce the soft, smooth AI look and add real texture and detail, especially for close-ups and clothing. Learn versions, weights and prompts.
By Captain
2026-10-02
Models
Light Slider for Krea 2: deepen shadows while the subject stays lit
Loraholic's Light Slider darkens the darkest parts of a Krea 2 scene while keeping focus areas lit, a contrast-style control. Learn the range, two-pass advice and when to use the Brightness slider instead.
By Captain
2026-09-30
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

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved



