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

csslc /ccsr:b66be6a6

Input

*file

Low quality input image.

number

Super-resolution scale.

Default: 4

integer
(minimum: 1, maximum: 500)

Number of sampling steps

Default: 45

boolean

If specified, a patch-based sampling strategy for diffusion peocess will be used for sampling.

Default: false

integer

Size of patch for diffusion process.

Default: 512

integer

Stride of sliding patch for diffusion process.

Default: 256

boolean

If specified, a patch-based sampling strategy for the encoder and decoder in VAE will be used.

Default: false

integer

Size of patch for VAE decoder, latent size.

Default: 224

integer

Size of patch for VAE encoder, image size.

Default: 1024

string

Size of patch.

Default: "adain"

number

The starting point of uniform sampling strategy.

Default: 0.6667

number

The ending point of uniform sampling strategy.

Default: 0.3333

integer

Random seed. Leave blank to randomize the seed

Output

No output yet! Press "Submit" to start a prediction.