pnyompen/sd-controlnet-lora

SD1.5 Canny controlnet with LoRA support.

Capabilities

Reference ImagesNegative PromptSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`auto_generate_caption`	boolean	Use BLIP to generate captions for the input images	`false`	—
`condition_scale`	number	The bigger this number is, the more ControlNet interferes	`1.1`	min: 0, max: 2
`generated_caption_weight`	number	Weight for the generated caption	`0.5`	min: 0
`guidance_scale`	number	Scale for classifier-free guidance	`7.5`	min: 1, max: 50
`image`	string(uri)	Input image for img2img or inpaint mode	`—`	—
`img2img`	boolean	Use img2img pipeline, it will use the image input both as the control image and the base image.	`false`	—
`ip_adapter_scale`	number	Scale for the IP Adapter	`1`	min: 0
`lora_scale`	number	LoRA additive scale. Only applicable on trained models.	`0.95`	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"`	—
`remove_bg`	boolean	Remove background from the input image	`false`	—
`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.	`0.8`	min: 0, max: 1

auto_generate_captionboolean

Use BLIP to generate captions for the input images

Default: false

condition_scalenumber

The bigger this number is, the more ControlNet interferes

Default: 1.1min: 0, max: 2

generated_caption_weightnumber

Weight for the generated caption

Default: 0.5min: 0

guidance_scalenumber

Scale for classifier-free guidance

Default: 7.5min: 1, max: 50

imagestring

Input image for img2img or inpaint mode

img2imgboolean

Use img2img pipeline, it will use the image input both as the control image and the base image.

Default: false

ip_adapter_scalenumber

Scale for the IP Adapter

Default: 1min: 0

lora_scalenumber

LoRA additive scale. Only applicable on trained models.

Default: 0.95min: 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"

remove_bgboolean

Remove background from the input image

Default: false

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: 0.8min: 0, max: 1

Version: 37ceaf8d4df1Updated: 7/25/2026548.9K runs