Frequently Asked Questions (常见问题）

[Zeqiang-Lai]

Q: Expecting value: line 1 column 1 (char 0)

A: This might be caused by network proxy. Please refer to #50 for solutions.

• #50

[Zeqiang-Lai]

Q: RuntimeError: PytorchStreamReader fail reading zip archive

A: The checkpoint is broken. Download again by removing the broken one. Optionally, you could download the checkpoint manually from here, and put it to the target directory.

The target directory could be found via

python -c "import draggan; print(draggan.home)"

• #48

[Zeqiang-Lai]

StyleGAN Custom OP, DLL not found

• #12
• #40
• #38
• #31
• #35
• #30

[Zeqiang-Lai]

Q: No Cuda Runtime

• #32
• #51
• #37

[Zeqiang-Lai]

Q: Requirements

• #11
• #10
• #13

[Zeqiang-Lai]

Q: Does this project support uploading custom image ?

A: Yes, this project support custom image.

[Zeqiang-Lai]

Performance

• #52
• #44

[Zeqiang-Lai]

Q: The custom image is of low quality, distorted, fail to drag.

A. The results might be distorted, this is an issue of the algorithms instead of the implementation. More advanced algorithms will be integrated in the future.

• #54
• #26
• #25
• #24
• #23
• #22
• #19
• #53

[Zeqiang-Lai]

Hardware Requirements

[Zeqiang-Lai]

Q: AttributeError: module torchvision.transforms has no attribute "Resize"

A: Then version of torchvision is too low. Upgrade it via

pip install torchvision --upgrade