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

zsxkib /diffbir:51ed1464

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
input
string
Path to the input image you want to enhance.
upscaling_model_type
string (enum)
general_scenes

Options:

faces, general_scenes

Choose the type of model best suited for the primary content of the image: 'faces' for portraits and 'general_scenes' for everything else.
restoration_model_type
string (enum)
general_scenes

Options:

faces, general_scenes

Select the restoration model that aligns with the content of your image. This model is responsible for image restoration which removes degradations.
reload_restoration_model
boolean
False
Reload the image restoration model (SwinIR) if set to True. This can be useful if you've updated or changed the underlying SwinIR model.
steps
integer
50

Min: 1

Max: 100

The number of enhancement iterations to perform. More steps might result in a clearer image but can also introduce artifacts.
super_resolution_factor
integer
4

Min: 1

Max: 4

Factor by which the input image resolution should be increased. For instance, a factor of 4 will make the resolution 4 times greater in both height and width.
repeat_times
integer
1

Min: 1

Max: 10

Number of times the enhancement process is repeated by feeding the output back as input. This can refine the result but might also introduce over-enhancement issues.
disable_preprocess_model
boolean
False
Disables the initial preprocessing step using SwinIR. Turn this off if your input image is already of high quality and doesn't require restoration.
tiled
boolean
False
Whether to use patch-based sampling. This can be useful for very large images to enhance them in smaller chunks rather than all at once.
tile_size
integer
512
Size of each tile (or patch) when 'tiled' option is enabled. Determines how the image is divided during patch-based enhancement.
tile_stride
integer
256
Distance between the start of each tile when the image is divided for patch-based enhancement. A smaller stride means more overlap between tiles.
use_guidance
boolean
False
Use latent image guidance for enhancement. This can help in achieving more accurate and contextually relevant enhancements.
guidance_scale
number
0
For 'general_scenes': Scale factor for the guidance mechanism. Adjusts the influence of guidance on the enhancement process.
guidance_time_start
integer
1001
For 'general_scenes': Specifies when (at which step) the guidance mechanism starts influencing the enhancement.
guidance_time_stop
integer
-1
For 'general_scenes': Specifies when (at which step) the guidance mechanism stops influencing the enhancement.
guidance_space
string (enum)
latent

Options:

rgb, latent

For 'general_scenes': Determines in which space (RGB or latent) the guidance operates. 'latent' can often provide more subtle and context-aware enhancements.
guidance_repeat
integer
5
For 'general_scenes': Number of times the guidance process is repeated during enhancement.
color_fix_type
string (enum)
wavelet

Options:

wavelet, adain, none

Method used for color correction post enhancement. 'wavelet' and 'adain' offer different styles of color correction, while 'none' skips this step.
seed
integer
231
Random seed to ensure reproducibility. Setting this ensures that multiple runs with the same input produce the same output.
has_aligned
boolean
False
For 'faces' mode: Indicates if the input images are already cropped and aligned to faces. If not, the model will attempt to do this.
only_center_face
boolean
False
For 'faces' mode: If multiple faces are detected, only enhance the center-most face in the image.
face_detection_model
string (enum)
retinaface_resnet50

Options:

retinaface_resnet50, retinaface_mobile0.25, YOLOv5l, YOLOv5n, dlib

For 'faces' mode: Model used for detecting faces in the image. Choose based on accuracy and speed preferences.
background_upsampler
string (enum)
RealESRGAN

Options:

DiffBIR, RealESRGAN

For 'faces' mode: Model used to upscale the background in images where the primary subject is a face.
background_upsampler_tile
integer
400
For 'faces' mode: Size of each tile used by the background upsampler when dividing the image into patches.
background_upsampler_tile_stride
integer
400
For 'faces' mode: Distance between the start of each tile when the background is divided for upscaling. A smaller stride means more overlap between tiles.

Output schema

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

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