orpatashnik/styleclip

Text-Driven Manipulation of StyleGAN Imagery

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`input` *	string (uri)	Input image	`—`	—
`disentanglement_threshold`	number	The higher the disentanglement threshold, the more specific the changes are to the target attribute. Lower values mean that broader changes are made to the input image	`0.15`	min: 0.08, max: 0.3
`manipulation_strength`	number	The higher the manipulation strength, the closer the generated image becomes to the target description. Negative values moves the generated image further from the target description	`4.1`	min: -10, max: 10
`neutral`	string	Neutral image description	`"a face"`	—
`target`	string	Target image description	`"a face with a bowlcut"`	—

input required string

Input image

disentanglement_threshold number

The higher the disentanglement threshold, the more specific the changes are to the target attribute. Lower values mean that broader changes are made to the input image

Default: 0.15 min: 0.08, max: 0.3

manipulation_strength number

The higher the manipulation strength, the closer the generated image becomes to the target description. Negative values moves the generated image further from the target description

Default: 4.1 min: -10, max: 10

neutral string

Neutral image description

Default: "a face"

target string

Target image description

Default: "a face with a bowlcut"

Version: 7af9a66f36f9 Updated: 2/26/2026 1.3M runs