You're looking at a specific version of this model. Jump to the model overview.
zsxkib /wd-image-tagger:f9cfa5be
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 |
|---|---|---|---|
| image |
string
|
Path to the input image file to be analyzed by the WaifuDiffusion tagger model
|
|
| model_repo |
string
(enum)
|
models/wd-swinv2-tagger-v3
Options: models/wd-swinv2-tagger-v3, models/wd-convnext-tagger-v3, models/wd-vit-tagger-v3, models/wd-v1-4-moat-tagger-v2, models/wd-v1-4-swinv2-tagger-v2, models/wd-v1-4-convnext-tagger-v2, models/wd-v1-4-convnextv2-tagger-v2, models/wd-v1-4-vit-tagger-v2 |
Name of the pre-trained model repository to use for image analysis
|
| general_thresh |
number
|
0.35
Max: 1 |
Probability threshold for including general tags in the output (between 0 and 1)
|
| general_mcut_enabled |
boolean
|
False
|
Whether to use the MCut algorithm to automatically determine the general tags threshold
|
| character_thresh |
number
|
0.85
Max: 1 |
Probability threshold for including character tags in the output (between 0 and 1)
|
| character_mcut_enabled |
boolean
|
False
|
Whether to use the MCut algorithm to automatically determine the character tags threshold
|
| category |
string
(enum)
|
all_tags
Options: all_tags, general, character, rating |
Category of tags to return in the output
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'properties': {'category': {'title': 'Category', 'type': 'string'},
'confidence': {'title': 'Confidence',
'type': 'number'},
'tag': {'title': 'Tag', 'type': 'string'}},
'required': ['tag', 'confidence', 'category'],
'title': 'Tag',
'type': 'object'},
'title': 'Output',
'type': 'array'}