zylim0702/perspective_net

Public
11 runs

Run zylim0702/perspective_net with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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
input_image
string
Input image to transform into 4 views
num_inference_steps
integer
50

Min: 10

Max: 200

Number of inference steps (10-200, higher = better quality but slower)
cfg_scale
number
2.5

Min: 1

Max: 10

CFG scale (1.0-10.0, higher = follows prompt more closely)
seed
integer
42
Random seed for reproducible results (set to -1 for random)
maintain_aspect_ratio
boolean
True
Preserve original image aspect ratio
target_size
integer
1024

Min: 512

Max: 2048

Target size for longer dimension when maintaining ratio (512-2048)
custom_pose
string
Custom pose description (e.g., 'heroic stance', 'sitting', 'fighting pose')
pose_reference_image
string
Reference image to extract pose from (overrides custom_pose)
clothing_type
string
Type of clothing (e.g., 'armor', 'dress', 'suit', 'casual clothes')
clothing_color
string
Clothing colors (e.g., 'red and blue', 'gold and silver')
clothing_pattern
string
Clothing pattern (e.g., 'stripes', 'geometric', 'plain')
clothing_material
string
Clothing material (e.g., 'metal', 'fabric', 'leather')
accessories
string
Accessories to add (comma-separated, e.g., 'hat, glasses', 'crown, earrings')
holding_objects
string
Objects to hold (comma-separated, e.g., 'sword, shield', 'magic wand')
hair_style
string
Hair style (e.g., 'long', 'short', 'curly', 'ponytail')
hair_color
string
Hair color (e.g., 'blonde', 'black', 'red', 'blue')
facial_expression
string
Facial expression (e.g., 'smiling', 'serious', 'angry')
eye_color
string
Eye color (e.g., 'blue', 'brown', 'green', 'red')
body_type
string
Body type (e.g., 'muscular', 'slim', 'tall', 'short')
art_style
None
3d_object
Art style preset
art_style_custom
string
Custom art style description (only used if art_style='custom')
additional_prompt
string
Additional details to add
negative_prompt_extra
string
Things you specifically don't want
printing_friendly
boolean
True
Optimize for 3D printing
detail_level
None
high
Detail level
consistency_threshold
number
0.7

Max: 1

Minimum consistency score required (0.0-1.0, lower = more retries)
max_retries
integer
3

Min: 1

Max: 5

Maximum number of retry attempts for low consistency
view_count
None
4_views
Number of views to generate (1 view = front only, 4 views = all angles)
body_style
None
same_as_input
Body style (same as input image or full body view)

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "string",
    "format": "uri"
  },
  "title": "Output"
}