TrendCraft Style Detailer v2.4 for Illustrious and NoobAI: community-tuned polish
Topic: Models
By Captain
Published 2026-09-29
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
25
Guidance
3
Seed
514524706
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
photorealistic, masterpiece, masterpiece quality, super fine concept art, dragon, made of bread, shout with fire:1.5, easynegative,
Negative prompt
lowres, error, low quality, low resolution, bad quality, worst quality, worst detail, sketch, censor, bad anatomy, logo, watermark, text, extra digits, patreon username, jpeg artifacts
Settings
Sampler
Euler a
Steps
40
Guidance
7
Seed
4092761545
Size
3424x6144
Prompt
Masterpiece, best quality, amazing quality, newest, very aesthetic, scenery, 8k, good anatomy, good shading, ultra detailed, refined details, high resolution, HD, masterwork, 4ur4_illu,shiny.
1girl, solo, laurel crown, white hair, straight bangs, elf ears, mouth veil, oversized hoodie, Skirt, cybernetic, translucent cloak(flowing cloak:1.2), blue eyes, glowing eyes, intense gaze, looking at viewer, thighboots, prosthetic cyber leg, matrix halo, pixelate halo, floating weapon around body, sword, holding sword, intricate weapon design, geometric accents, stylish design, epic character design, dynamic pose(Close-Up), sitting, Plantar flexion, motion blur, light rays, dutch angle, depth of field, foreshortening, blurry edges, light_theme, colorful, matrix, bold, geometric, pixelate, white background, abrstact background, detailed background.
Negative prompt
lowres, (bad quality,worst quality:1.2), bad anatomy,blurry,watermark, sketch,jpeg artifacts,ugly, poorly drawn,(censor),cross, nsfw, breast, Cleavage
Settings
Sampler
Euler a
Steps
30
Guidance
4
Size
2176x3840
Weight used
0.2
Prompt
lazypos, masterpiece, best quality, refined detailed, high quality, highres, cinematic lighting, absurdres, 8k, detailed, highest definition, manga, comic, 1girl, solo, long black hair, straight bangs, red eyes, serious expression, cyber leg, detailed cyberpunk prosthetic, white kimono with red sakura pattern, red obi, hood up, asymmetrical sitting pose, katana, holding katana, intricate weapon design, red chains wrapped around body, cherry blossom petals, layered outfit, mechanical boots, Japanese pattern, traditional meets sci-fi, glowing accents, stylish design, epic character design, looking at viewer, BREAK, dramatic lighting, falling petals, dark bokeh background, soft spotlight, floor reflection, scattered petals on ground, ethereal atmosphere, depth of field, high contrast, very aesthetic, bloom, fantasy art style, soft lighting, beautiful composition, ((masterpiece)), ((best quality)), (detailed face), (sharp eyes), (finely detailed outfit), (sakura themed), (mechanical elegance), (cyber-traditional fusion), digital art, surreal, dynamic composition, Y0ney4m4_illu, 2025A3STH, artist:moriimee, Flatline, Flat vector illustration
Negative prompt
Worst quality, blurry, bad anatomy, bad position, low quality, glitch, watermark, dull, painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, mutated limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hand, lazyneg, lazyhand, easynegative, score_4, score_3_up, score_2_up, boring, flat, lazyneg,
Settings
Sampler
Euler a
Steps
25
Guidance
4
Seed
1304240790
Size
2240x3840
Clip skip
2
Weight used
0.2
Prompt
lazypos, best quality, refined detailed, high quality, highres, cinematic lighting, absurdres, 8k, detailed, highest definition, high resolution, scenery, source_anime, absurd_res, masterpiece, best quality,high quality, newest, highres,8K,HDR,absurdres,1girl, hair ornament, weapon, hair flower, sword, holding, flower, japanese clothes, solo, kimono, black hair, looking at viewer, holding weapon, holding sword, floral print, katana, ring, bangs, jewelry, blue eyes, long hair, closed mouth, blush, glint, petals, long sleeves, red kimono, black background, wide sleeves, boots, obi,motion blur, dynamic pose, dynamic composition,dutch angle, depth of field,white_theme,detailed backgroud,foreshortening,blurry edges,((4k,8k,Ultra HD)), ((Masterpiece :1.2)),((Best quality :1.2)),((Detailed :1.4)),((dynamic pose:1.4)),((Detailed background :1.4)), digital art, surreal, dynamic composition, beautiful atmosphere
Negative prompt
low quality, worst quality, normal quality, jpeg artifacts, signature, watermark, text, error, blurry, ugly, poorly drawn, sketch, monochrome, mutated, extra limbs, deformed, distorted face, bad proportions, out of focus, cloned face, mutated hands, disfigured, extra arms, extra legs, extra fingers, missing arms, missing legs, missing fingers, disconnected limbs, long neck, bad anatomy, bad hands, poorly drawn hands, bad feet, extra eyes, glitched eyes, mutated eyes, cross-eye, asymmetrical eyes, rough sketch, discolored, lazyneg, lazyhand
Settings
Sampler
Euler a
Steps
25
Guidance
7
Seed
3340551526
Size
3424x6144
Prompt
Masterpiece, best quality, amazing quality, newest, very aesthetic, scenery, 8k, good anatomy, good shading, ultra detailed, refined details, high resolution, HD, masterwork, 4ur4_illu,shiny.
1girl, solo, white short hair with black highlight, straight bangs, blue eyes, glowing eyes (blue light trails), intense gaze, white kimono with red sakura pattern, layered outfit, Japanese pattern, obi, hood up, glint, petals, wide sleeves, thighboots, prosthetic cyber leg, rifle, holding rifle, intricate weapon design, glowing accents, stylish design, epic character design, Chain on body, dynamic pose(Close-Up), aiming at viewer, motion blur, light rays, dutch angle, depth of field, foreshortening, blurry edges, black background, detailed background.
Negative prompt
lowres, (bad quality,worst quality:1.2), bad anatomy,blurry,watermark,simple background,transparent background, sketch,jpeg artifacts,ugly, poorly drawn,(censor),,
janxd's TrendCraft is a style detailer LoRA trained on top-rated community images to make Illustrious and NoobAI renders look post-ready. Learn weight, prompt pairing and ideas.
Overview
TrendCraft: The People's Style Detailer (v2.4I for
Illustrious
) by janxd is a style
LoRA
trained on community-favored images. It aims to transform a render into something polished and shareable: cleaner detail, better lighting and a contemporary finish on Illustrious and NoobAI checkpoints.
It is meant to be paired with normal quality tags or the author's companion resources.
Reference
Name | Type | What it is |
|---|---|---|
LoRA weight | 0.5-0.9 | 0.7. |
Trigger | none | |
Base | Illustrious / NoobAI | |
CFG / steps | checkpoint default | |
Quality tags | keep them | masterpiece, best quality, amazing quality, newest |
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
- Quality tags, then subject.
- Attach TrendCraft at 0.7.
- Compare same-seed.
- Lower to 0.5 under a strong artist style.
- Hires fix for finals.
Examples
Concept
masterpiece, masterpiece quality, super fine concept art, a dragon made of bread breathing fire, photorealistic textures
TrendCraft 0.7
Character
masterpiece, best quality, amazing quality, newest, very aesthetic, scenery, 8k, good anatomy, good shading, ultra detailed, 1girl, adult, solo, laurel crown, white dress, shiny, garden
TrendCraft 0.7
Creative idea: product mascot
masterpiece, best quality, a chibi fox mascot holding a soda can, glossy, studio background, good shading
TrendCraft 0.6
Tips
- Works on concept-art prompts (a dragon made of bread) as well as characters.
- Shiny and good shading tags amplify its finish.
- Keep negatives modest.
- Stack under one artist LoRA at most.
Troubleshooting
Over-polished
Why it happens
0.9 plus other detailers.
How to fix it
0.5.
Style homogenized
Why it happens
High weight.
How to fix it
Lower it.
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
Trigger?
None.
Pony?
Illustrious/NoobAI build.
Links and sources
Models in this guide
Written by
Captain
Related guides
Models
Hyphoria Real v0.9: prompt adherence meets realism on Illustrious
ecaj's Hyphoria Real merges realistic Illustrious models into Hyphoria for lifelike results with strong prompt adherence and fewer retries. Learn settings, prompt structure and ideas for semi-real character shots.
By Captain
2026-10-03
Models
CAT - Citron Anime Treasure IL v10: bright, flat-color anime
CitronLegacy's CAT is a colorful, flat-shaded anime checkpoint for Illustrious and NoobAI. Learn its quality strings, the merge lineage, settings and ideas for vivid character art.
By Captain
2026-10-03
Models
ChenkinNoob XL v0.2: a NoobAI fine-tune for game art and illustration
The ChenkinNoob team's CKXL fine-tunes NoobAI XL 1.1 toward cleaner aesthetics and fewer AI artifacts for game art and illustration workflows. Learn its prompting, settings and ideas.
By Captain
2026-09-30
Models
MiaoMiao RealSkin EPS v1.4: realistic skin texture on Illustrious anime
MIAOKA's MiaoMiao RealSkin brings translucent, textured skin and strong composition to Illustrious anime without complex prompts. Learn its focus on limb stability, settings and ideas for semi-real portraits.
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

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026