Muhammad Ahmed

Yeah I also compared it with gfpgan and GPEN and the results are much better on GPEN and then gfpgan. I also don't know how they compare the results maybe...

> > Yeah I also compared it with gfpgan and GPEN and the results are much better on GPEN and then gfpgan. I also don't know how they compare the...

> Same trouble. I tried to remove ths specific version (after the =). But still lot of package are missing from Anaconda (Windows). Is it working on Linux ? Hi...

> Yeah maybe you need this in windows. I installed it on ubuntu and it was working fine.

@rinongal Actually I wanted to convert the trained model to torchscript but the input it takes isn't static and I am facing difficulty to convert it into torchscript because otherwise...

> @muhammad-ahmed-ghani Hello, have you solved this problem？ Yeah as @ckkelvinchan suggest above https://github.com/ckkelvinchan/BasicVSR_PlusPlus/issues/10#issuecomment-1116952418 to set the max sequence length to the minimum possible value according to your gpu memory.

[PROMPT] "Stunning portrait of a hijab-wearing girl with a confident and serene expression, natural lighting, soft colors, shallow depth of field, high-quality composition, 50mm lens, professional photography, trending on social...

@matyasbohacek Hi have you resolved this error ? I am also getting the same error

> I changed it but still it adds a slight blueish tint to the images. 

> That is a bit puzzling, as I am able to get reasonable colorization. If you share a reproduction I may have a look at some point. You can check...