Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Upscale Node Expected return size matches value but emits error #2999

Open
PereViader opened this issue Jul 17, 2024 · 2 comments
Open

Upscale Node Expected return size matches value but emits error #2999

PereViader opened this issue Jul 17, 2024 · 2 comments
Labels
bug Something isn't working

Comments

@PereViader
Copy link
Contributor

Information:

  • Chainner version: 0.24.1
  • OS: Windows 11

Description
Use upscale node on an image of size 532x400
Upscale to size 2720x2048

image

Logs

Error

An error occurred in a Upscale node:

Expected the returned image to be 2720x2048px but found 2720x2048px instead

Input values:
• Image: RGB Image 532x400
• Upscaler Mode: Scale to
• Resize multiplier: 4
• Width: 2720
• Height: 2048
• Crop to fit: No
• Upscaler 1: SwinIR 4x
• Use second upscaler: No
• Upscaler 2: SwinIR 4x
• Upscaler 2 visibility: 0.3

Stack Trace:
Traceback (most recent call last):
  File "C:\Users\perev\AppData\Local\chaiNNer\app-0.24.1\resources\src\process.py", line 176, in run_node
    raw_output = node.run(*enforced_inputs)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\perev\AppData\Local\chaiNNer\app-0.24.1\resources\src\nodes\node_cache.py", line 163, in _run
    output = run(*args)
             ^^^^^^^^^^
  File "C:\Users\perev\AppData\Local\chaiNNer\app-0.24.1\resources\src\packages\chaiNNer_external\external_stable_diffusion\automatic1111\upscale.py", line 191, in upscale_node
    (rw, rh) == (int(iw * larger_ratio), int(ih * larger_ratio))
AssertionError: Expected the returned image to be 2720x2048px but found 2720x2048px instead 

@PereViader PereViader added the bug Something isn't working label Jul 17, 2024
@joeyballentine
Copy link
Member

Thanks for reporting. We will look into this at some point

@PereViader
Copy link
Contributor Author

As a workaround, I have manually run the upscaling within Automatic1111 and used the upscaled image directly as input for the rest of the process.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants