Closed zhzLuke96 closed 1 month ago
You can set controlnet_processor_res
in /detect
endpoint to solve this issue. The default value for resolution is 512. That is why you see the result is resized to 640 x 512. See https://github.com/Mikubill/sd-webui-controlnet/blob/3b4eedd90fe8ebcac5363f586157d36dcd9a513f/scripts/api.py#L103-L105.
Is there an existing issue for this?
What happened?
When calling the preprocessing model using the detect interface, the pose data returned by openpose recognition is based on the coordinates of the canvas after resize/pad, which does not match the original image's position.
Steps to reproduce the problem
Using any image request API
/controlnet/detect
that is not likely to result in a resizeWhat should have happened?
Phenomenon
Detection image size is 600x700![photo_2024-05-12_21-25-23](https://github.com/Mikubill/sd-webui-controlnet/assets/37396659/a395e74b-69e8-4fdd-8bce-7104bb574bff)
Returned results:
The data in people are calculated based on the canvas (after resize/pad to 640*512), which does not correspond to the original image.
Expectation
Preferably, the coordinates before the resize/pad should be directly returned.
Commit where the problem happens
webui: 1.8.0 controlnet: eb451a00
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
List of enabled extensions
none
Console logs
Additional information
No response