Inputs
| Parameter | Description | Data Type | Required | Range |
|---|---|---|---|---|
control_image | The input image used for canny edge detection control | IMAGE | Yes | - |
prompt | Prompt for the image generation (default: empty string) | STRING | No | - |
prompt_upsampling | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) | BOOLEAN | No | - |
canny_low_threshold | Low threshold for Canny edge detection; ignored if skip_preprocessing is True (default: 0.1) | FLOAT | No | 0.01 - 0.99 |
canny_high_threshold | High threshold for Canny edge detection; ignored if skip_preprocessing is True (default: 0.4) | FLOAT | No | 0.01 - 0.99 |
skip_preprocessing | Whether to skip preprocessing; set to True if control_image already is canny-fied, False if it is a raw image. (default: False) | BOOLEAN | No | - |
guidance | Guidance strength for the image generation process (default: 30) | FLOAT | No | 1 - 100 |
steps | Number of steps for the image generation process (default: 50) | INT | No | 15 - 50 |
seed | The random seed used for creating the noise. (default: 0) | INT | No | 0 - 18446744073709551615 |
skip_preprocessing is set to True, the canny_low_threshold and canny_high_threshold parameters are ignored since the control image is assumed to already be processed as a canny edge image. The control_image is then used directly as the preprocessed image.
Outputs
| Output Name | Description | Data Type |
|---|---|---|
output_image | The generated image based on the control image and prompt | IMAGE |
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Source fingerprint (SHA-256):
dedf55a2b2c183519d7f5be0d9a96abbe40716a247f574fc0d50f10f715949a7