tencentarc/photomaker

Create photos, paintings and avatars for anyone in any style within seconds.

Capabilities

Reference ImagesNegative PromptSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`input_image`*	string(uri)	The input image, for example a photo of your face.	`—`	—
`disable_safety_checker`	boolean	Disable safety checker for generated images.	`false`	—
`guidance_scale`	number	Guidance scale. A guidance scale of 1 corresponds to doing no classifier free guidance.	`5`	min: 1, max: 10
`input_image2`	string(uri)	Additional input image (optional)	`—`	—
`input_image3`	string(uri)	Additional input image (optional)	`—`	—
`input_image4`	string(uri)	Additional input image (optional)	`—`	—
`negative_prompt`	string	Negative Prompt. The negative prompt should NOT contain the trigger word.	`"nsfw, 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"`	—
`num_outputs`	integer	Number of output images	`1`	min: 1, max: 4
`num_steps`	integer	Number of sample steps	`20`	min: 1, max: 100
`prompt`	string	Prompt. Example: 'a photo of a man/woman img'. The phrase 'img' is the trigger word.	`"A photo of a person img"`	—
`seed`	integer	Seed. Leave blank to use a random number	`—`	min: 0, max: 2147483647
`style_name`	string	Style template. The style template will add a style-specific prompt and negative prompt to the user's prompt.	`"Photographic (Default)"`	(No style)CinematicDisney CharactorDigital ArtPhotographic (Default)Fantasy artNeonpunkEnhanceComic bookLowpolyLine art
`style_strength_ratio`	number	Style strength (%)	`20`	min: 15, max: 50

input_imagerequiredstring

The input image, for example a photo of your face.

disable_safety_checkerboolean

Disable safety checker for generated images.

Default: false

guidance_scalenumber

Guidance scale. A guidance scale of 1 corresponds to doing no classifier free guidance.

Default: 5min: 1, max: 10

input_image2string

Additional input image (optional)

input_image3string

Additional input image (optional)

input_image4string

Additional input image (optional)

negative_promptstring

Negative Prompt. The negative prompt should NOT contain the trigger word.

Default:

"nsfw, 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"

num_outputsinteger

Number of output images

Default: 1min: 1, max: 4

num_stepsinteger

Number of sample steps

Default: 20min: 1, max: 100

promptstring

Prompt. Example: 'a photo of a man/woman img'. The phrase 'img' is the trigger word.

Default: "A photo of a person img"

seedinteger

Seed. Leave blank to use a random number

min: 0, max: 2147483647

style_namestring

Style template. The style template will add a style-specific prompt and negative prompt to the user's prompt.

Default: "Photographic (Default)"

(No style)CinematicDisney CharactorDigital ArtPhotographic (Default)Fantasy artNeonpunkEnhanceComic bookLowpolyLine art

style_strength_rationumber

Style strength (%)

Default: 20min: 15, max: 50

Version: ddfc2b08d209Updated: 7/25/20268.8M runs