Auto detecting, masking and inpainting with detection model.
GNU Affero General Public License v3.0
4.13k
stars
317
forks
source link
[Bug]: SD.NEXT Adetailer Control TypeError: image must be passed and be one of PIL image, numpy array, torch tensor, list of PIL images, list of numpy arrays or list of torch tensors, but is <class 'NoneType'> #506
Both the newest at the time SD.NEXT master branch 3c952675 and dev branch d76136fb (reverted to avoid an unrelated issue)
Windows 11 24H2, GTX 1080Ti 11Gb
Issue seems browser agnostic, tried with Mozilla Firefox, Microsoft Edge, and Chrome
When using control tab, with any processor and any controlnet model, in either of three modes of image input the following happens:
The generation proceeds as normal, until adetailer initialises, where it detects the face correctly, which shows on the TAESD preview, but when it begins generating it fails with an error message.
Describe the bug
Both the newest at the time SD.NEXT master branch 3c952675 and dev branch d76136fb (reverted to avoid an unrelated issue) Windows 11 24H2, GTX 1080Ti 11Gb Issue seems browser agnostic, tried with Mozilla Firefox, Microsoft Edge, and Chrome
When using control tab, with any processor and any controlnet model, in either of three modes of image input the following happens: The generation proceeds as normal, until adetailer initialises, where it detects the face correctly, which shows on the TAESD preview, but when it begins generating it fails with an error message.
sdnext-MASTER.log sdnext-DEV2.log
Screenshots
No response
Console logs, from start to end.
List of installed extensions
Adetailer