fermatresearch/magic-style-transfer

Restyle an image with the style of another one. I strongly suggest to upscale the results with Clarity AI

Capabilities

Reference ImagesNegative PromptSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`apply_watermark`	boolean	Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.	`true`	—
`background_color`	string	When passing an image with alpha channel, it will be replaced with this color	`"#A2A2A2"`	—
`condition_canny_scale`	number	The bigger this number is, the more ControlNet interferes	`0.15`	min: 0, max: 2
`condition_depth_scale`	number	The bigger this number is, the more ControlNet interferes	`0.35`	min: 0, max: 2
`guidance_scale`	number	Scale for classifier-free guidance	`4`	min: 1, max: 50
`image`	string(uri)	Input image	`—`	—
`ip_image`	string(uri)	Input image for img2img or inpaint mode	`—`	—
`ip_scale`	number	IP Adapter strength.	`0.3`	min: 0, max: 1
`lora_scale`	number	LoRA additive scale. Only applicable on trained models.	`0.9`	min: 0, max: 1
`lora_weights`	string	Replicate LoRA weights to use. Leave blank to use the default weights.	`—`	—
`negative_prompt`	string	Input 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	Input prompt	`"An astronaut riding a rainbow unicorn"`	—
`resizing_scale`	number	If you want the image to have a solid margin. Scale of the solid margin. 1.0 means no resizing.	`1`	min: 1, max: 10
`scheduler`	string	scheduler	`"K_EULER"`	DDIMDPMSolverMultistepHeunDiscreteKarrasDPMK_EULER_ANCESTRALK_EULERPNDM
`seed`	integer	Random seed. Leave blank to randomize the seed	`—`	—
`strength`	number	When img2img is active, the denoising strength. 1 means total destruction of the input image.	`0.9`	min: 0, max: 1

apply_watermarkboolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

background_colorstring

When passing an image with alpha channel, it will be replaced with this color

Default: "#A2A2A2"

condition_canny_scalenumber

The bigger this number is, the more ControlNet interferes

Default: 0.15min: 0, max: 2

condition_depth_scalenumber

The bigger this number is, the more ControlNet interferes

Default: 0.35min: 0, max: 2

guidance_scalenumber

Scale for classifier-free guidance

Default: 4min: 1, max: 50

imagestring

Input image

ip_imagestring

Input image for img2img or inpaint mode

ip_scalenumber

IP Adapter strength.

Default: 0.3min: 0, max: 1

lora_scalenumber

LoRA additive scale. Only applicable on trained models.

Default: 0.9min: 0, max: 1

lora_weightsstring

Replicate LoRA weights to use. Leave blank to use the default weights.

negative_promptstring

Input Negative Prompt

Default: ""

num_inference_stepsinteger

Number of denoising steps

Default: 30min: 1, max: 500

num_outputsinteger

Number of images to output

Default: 1min: 1, max: 4

promptstring

Input prompt

Default: "An astronaut riding a rainbow unicorn"

resizing_scalenumber

If you want the image to have a solid margin. Scale of the solid margin. 1.0 means no resizing.

Default: 1min: 1, max: 10

schedulerstring

scheduler

Default: "K_EULER"

DDIMDPMSolverMultistepHeunDiscreteKarrasDPMK_EULER_ANCESTRALK_EULERPNDM

seedinteger

Random seed. Leave blank to randomize the seed

strengthnumber

When img2img is active, the denoising strength. 1 means total destruction of the input image.

Default: 0.9min: 0, max: 1

Version: 3b5fa5d360c3Updated: 7/25/202651.9K runs