banner_image ×
SeaArt AI Enterprise Version

Anime character with a nurse hat and a syll in her hand

Lineart, masterpiece,  cool posing, (lab reaction systems:1.4),  { experiment, lab, {{{chemistry laboratory}}}, delicate background, cool, {with a  laboratory as background}},   best quality, a girl, solo: {papercut, thick outline: 2, short red hair, short wavy hair, floating lab-gown, flat chest, white school uniform, white beret, bowknot over white beret , outline}, masterpiece

Thick outlines increase the probability of producing more people。
When describing a scene,If you can't generate a scene,Try adding more words that describe the scene(Instead of simply repeating it a few times or increasing the weight)
If the background is particularly realistic,It can be done like a 2D vertical painting performance style;If it blends in with the background,Then it will be very lineart(And the difference in implementation between the two,Generally, it is whether the lineart tag is added)
Remove lineart and emphasize that the real background can be brushed to effect 2D on 3D,To a certain extent, the effect of "multi-layer" is reproduced(But it is still extremely distant in nature)

(Maybe I will write a detailed explanation in the future)
chatIcon
You might be interested in my private matters.
Create AI Character
image
avatar
C
cosk
Prompts
Copy
Lineart , masterpiece , cool posing , (lab reaction systems:1 . 4) , { experiment , lab , {{{chemistry laboratory}}} , delicate background , cool , {with a laboratory as background}} , best quality , a girl , solo: {papercut , thick outline: 2 , short red hair , short wavy hair , floating lab-gown , flat chest , white school uniform , white beret , bowknot over white beret , outline} , masterpiece Thick outlines increase the probability of producing more people 。 When describing a scene , If you can't generate a scene , Try adding more words that describe the scene(Instead of simply repeating it a few times or increasing the weight) If the background is particularly realistic , It can be done like a 2D vertical painting performance style ; If it blends in with the background , Then it will be very lineart(And the difference in implementation between the two , Generally , it is whether the lineart tag is added) Remove lineart and emphasize that the real background can be brushed to effect 2D on 3D , To a certain extent , the effect of "multi-layer" is reproduced(But it is still extremely distant in nature) (Maybe I will write a detailed explanation in the future)
INFO
Prompts
Lineart, masterpiece, cool posing, (lab reaction systems:1.4), { experiment, lab, {{{chemistry laboratory}}}, delicate background, cool, {with a laboratory as background}}, best quality, a girl, solo: {papercut, thick outline: 2, short red hair, short wavy hair, floating lab-gown, flat chest, white school uniform, white beret, bowknot over white beret , outline}, masterpiece Thick outlines increase the probability of producing more people。 When describing a scene,If you can't generate a scene,Try adding more words that describe the scene(Instead of simply repeating it a few times or increasing the weight) If the background is particularly realistic,It can be done like a 2D vertical painting performance style;If it blends in with the background,Then it will be very lineart(And the difference in implementation between the two,Generally, it is whether the lineart tag is added) Remove lineart and emphasize that the real background can be brushed to effect 2D on 3D,To a certain extent, the effect of "multi-layer" is reproduced(But it is still extremely distant in nature) (Maybe I will write a detailed explanation in the future)
Negative Prompts
q-version, nsfw, lowres, bad anatomy, bad hands, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, symmetry, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,watermarks, bad hands
CFG Scale
7
Steps
20
Sampler
Euler a
Seed
4032896818
Clip Skip
1
Image Size
768 X 768
Model
Three Delicacy Wonton (三餡馄饨Mix)
Generate
Size
1536X1536
Date
Aug 24, 2023
Mode
Default
Type
upscale
Checkpoint & LoRA
Three Delicacy Wonton (三餡馄饨Mix)
Checkpoint
Three Delicacy Wonton (三餡馄饨Mix)
0 comment
0
3
0

SeaArt Swift AI Apps

ai_video_generationimg
AI Video Generation

Unleash your imagination and let AI create visual wonders for you

face_swap_titleimg
Face Swap Online Free

Create funny or realistic face swap videos & photos in a snap

DisneyFilter_top_titleimg
Disney Filter

Instantly transform your photos into Disney characters.

gender_swapimg
Gender Swap

Swap genders in photos and videos with SeaArt's AI gender swapper. Enjoy fun and realistic transformations effortlessly, free online!

wanimg2vid_h1img
Wan 2.1 Image to Video

Animate photos with realistic motion and cinematic effects.

cartoon_avatar_h1img
Cartoon Avatar Maker

Turn your photos into unique cartoon avatars instantly.

Explore More AI Apps 

Explore Related

ControlNet
logo
English
Application
Create Image AI Characters Swift AI Model Training Canvas AI Apps Workflow
About
Studio Rankings AI Chat AI Blog AI News
Help
Guides Customer Service
Get App
icon
Download on the
APP Store
icon
GET IT ON
Google Play
Follow Us
iconiconiconiconiconiconiconicon
© 2025 SeaArt, Inc.
Copyright Policy
Terms
Privacy 特定商取引法 資金決済法に基づく表示
More