Spaces:
Paused
Paused
|
Download Real-ESRGAN/docs/FAQ.md from crash10155/Switcher: direct link, hf CLI and curl.
- Browser
- Download file 746 Bytes
-
https://huggingface.co/spaces/crash10155/Switcher/resolve/main/Real-ESRGAN/docs/FAQ.md
- Command line
-
hf download hf://spaces/crash10155/Switcher/Real-ESRGAN/docs/FAQ.md
-
curl -L -o FAQ.md https://huggingface.co/spaces/crash10155/Switcher/resolve/main/Real-ESRGAN/docs/FAQ.md
746 Bytes
A newer version of the Gradio SDK is available: 6.31.0
FAQ
Q: How to select models?
A: Please refer to docs/model_zoo.mdQ: Can
face_enhancebe used for anime images/animation videos?
A: No, it can only be used for real faces. It is recommended not to use this option for anime images/animation videos to save GPU memory.Q: Error "slow_conv2d_cpu" not implemented for 'Half'
A: In order to save GPU memory consumption and speed up inference, Real-ESRGAN uses half precision (fp16) during inference by default. However, some operators for half inference are not implemented in CPU mode. You need to add--fp32option for the commands. For example,python inference_realesrgan.py -n RealESRGAN_x4plus.pth -i inputs --fp32.