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

xiankgx /controlnet-tile-image-detailer:d0bf83df

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
Prompt for the model
image
string
Control image for scribble controlnet
resolution
integer (enum)
2560

Options:

2048, 2560, 4096

Image resolution
resemblance
number
0.85

Max: 1

Conditioning scale for controlnet
creativity
number
0.35

Min: 0.1

Max: 1

Denoising strength. 1 means total destruction of the original image
hdr
number
0

Max: 1

HDR improvement over the original image
scheduler
string (enum)
DDIM

Options:

DDIM, DPMSolverMultistep, K_EULER_ANCESTRAL, K_EULER

Choose a scheduler.
steps
integer
20
Steps
guidance_scale
number
7

Min: 0.1

Max: 30

Scale for classifier-free guidance
seed
integer
Seed
negative_prompt
string
teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant
Negative prompt
guess_mode
boolean
False
In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended.
tile_size
integer (enum)
512

Options:

128, 256, 374, 512, 768, 1024, 1280

Size of partitions of the image. A 1/4 of the final resolution is recommended for optimal.
lora_sharpness_strength
number
4.5

Min: -3

Max: 10

Strength of the image's sharpness. For it to be noticeable, it is recommended to use values between 2 and 5.
lora_details_strength
number
1.25

Min: -3

Max: 3

Strength of the image's details

Output schema

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

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}