lucataco/ip_adapter-sdxl-face

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt

Capabilities

Reference Images Negative Prompt Seed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`image` *	string (uri)	Input face image	`—`	—
`negative_prompt`	string	Negative Prompt	`""`	—
`num_inference_steps`	integer	Number of denoising steps	`30`	min: 1, max: 500
`num_outputs`	integer	Number of images to output.	`1`	min: 1, max: 4
`prompt`	string	Prompt (leave blank for image variations)	`""`	—
`scale`	number	Scale (influence of input image on generation)	`0.6`	min: 0, max: 1
`seed`	integer	Random seed. Leave blank to randomize the seed	`—`	—

image required string

Input face image

negative_prompt string

Negative Prompt

Default: ""

num_inference_steps integer

Number of denoising steps

Default: 30 min: 1, max: 500

num_outputs integer

Number of images to output.

Default: 1 min: 1, max: 4

prompt string

Prompt (leave blank for image variations)

Default: ""

scale number

Scale (influence of input image on generation)

Default: 0.6 min: 0, max: 1

seed integer

Random seed. Leave blank to randomize the seed

Version: 226c6bf67a75 Updated: 2/26/2026 38.8K runs