You're looking at a specific version of this model. Jump to the model overview.
adarshnagrikar14 /manhwa-ai:ff134745
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
Field | Type | Default value | Description |
---|---|---|---|
prompt |
string
|
Input prompt (used if Gemini image analysis is not enabled)
|
|
spatial_img |
string
|
Spatial control image (also used for Gemini analysis if available)
|
|
base_prompt |
string
|
Create a K-pop manhwa style digital illustration of this image. Transform the person into a detailed manhwa-style artwork with the following specifications:
Art Style: Resemble K-pop manhwa style with clean lines, vibrant colors, and exaggerated features.
Outfit: Gender-specific outfit, modern K-pop-inspired attire: a tailored jacket/suit/coat featuring intricate patterns and a belted waist. Add glowing or magical elements for a mystical vibe.
Background: Fiery with deep red tones, crackling energy, glowing sparks, and lightning effects for a dramatic, mystical atmosphere.
Additional Elements: Add a magical aura with glowing energy around hands, small star-like symbols in the background, and subtle K-pop-inspired accessories.
Pose and Expression: Match the pose with cosmic fire in hand, glowing, enhance with manhwa-style drama—confident and serene expression.
|
Text to prepend to the Gemini-generated prompt (optional)
|
height |
integer
|
768
|
Height of the output image
|
width |
integer
|
512
|
Width of the output image
|
seed |
integer
|
16
|
Random seed
|
control_type |
string
(enum)
|
Manhwa
Options: Manhwa, None |
LoRA control type
|
lora_scale |
number
|
0.85
Max: 2 |
Scale for the LoRA weights
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}