You're looking at a specific version of this model. Jump to the model overview.

tonyhopkins994 /sdxl-prod:e52b7d0f

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
prompt
string
Living Room
Input prompt
negative_prompt
string
blurry, distorted
Negative Prompt
image
string
Input image for img2img or inpaint mode
mask
string
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
width
integer
1024
Width of output image
height
integer
1024
Height of output image
sizing_strategy
string (enum)
width_height

Options:

width_height, input_image, controlnet_1_image, controlnet_2_image, controlnet_3_image, mask_image

Decide how to resize images – use width/height, resize based on input image or control image
num_outputs
integer
1

Min: 1

Max: 6

Number of images to output
scheduler
string (enum)
KarrasDPM

Options:

DDIM, DPMSolverMultistep, HeunDiscrete, KarrasDPM, K_EULER_ANCESTRAL, K_EULER, PNDM

scheduler
num_inference_steps
integer
30

Min: 1

Max: 500

Number of denoising steps
guidance_scale
number
7.5

Min: 1

Max: 50

Scale for classifier-free guidance
prompt_strength
number
0.8

Max: 1

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
seed
string
-1
Random seed. Leave blank to randomize the seed
refine
string (enum)
no_refiner

Options:

no_refiner, base_image_refiner

Which refine style to use
refine_steps
integer
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
apply_watermark
boolean
False
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.
lora_scale
number
0.6

Max: 1

LoRA additive scale. Only applicable on trained models.
lora_weights
string
Replicate LoRA weights to use. Leave blank to use the default weights.
disable_safety_checker
boolean
False
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
controlnet_1
string (enum)
none

Options:

none, edge_canny, illusion, depth_leres, depth_midas, soft_edge_pidi, soft_edge_hed, lineart, lineart_anime, openpose

Controlnet
controlnet_1_image
string
Input image for first controlnet, base64 encoded string
controlnet_1_conditioning_scale
number
0.75

Max: 4

How strong the controlnet conditioning is
controlnet_1_start
number
0

Max: 1

When controlnet conditioning starts
controlnet_1_end
number
1

Max: 1

When controlnet conditioning ends
controlnet_2
string (enum)
none

Options:

none, edge_canny, illusion, depth_leres, depth_midas, soft_edge_pidi, soft_edge_hed, lineart, lineart_anime, openpose

Controlnet
controlnet_2_image
string
Input image for second controlnet, base64 encoded string
controlnet_2_conditioning_scale
number
0.75

Max: 4

How strong the controlnet conditioning is
controlnet_2_start
number
0

Max: 1

When controlnet conditioning starts
controlnet_2_end
number
1

Max: 1

When controlnet conditioning ends
controlnet_3
string (enum)
none

Options:

none, edge_canny, illusion, depth_leres, depth_midas, soft_edge_pidi, soft_edge_hed, lineart, lineart_anime, openpose

Controlnet
controlnet_3_image
string
Input image for third controlnet, base64 encoded string
controlnet_3_conditioning_scale
number
0.75

Max: 4

How strong the controlnet conditioning is
controlnet_3_start
number
0

Max: 1

When controlnet conditioning starts
controlnet_3_end
number
1

Max: 1

When controlnet conditioning ends
ip_adapter_image
string
Input image for ip_adapter, base64 encoded string
ip_adapter_scale
number
0.5
IP adapter guidance strength

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'items': {'type': 'string'}, 'title': 'Output', 'type': 'array'}