kalkal
> Hi @FlowDownTheRiver, I updated the face detector, for now our repo supports 4 detection networks, including: > > * large models: 'YOLOv5l' 'retinaface_resnet50' > * small models: 'YOLOv5n' 'retinaface_mobile0.25'...
> > > Hi @FlowDownTheRiver, I updated the face detector, for now our repo supports 4 detection networks, including: > > > > > > * large models: 'YOLOv5l' 'retinaface_resnet50'...
> > > > > Hi @FlowDownTheRiver, I updated the face detector, for now our repo supports 4 detection networks, including: > > > > > > > > >...
Addional thanks for taking the time for additional AI art enhancment, this is truly appreciated!
Thank you for all of this work generally, this is absolutely brilliant!
That's not just M1, happening with the precise error on Win 11 via WSL Ubuntu
Not all samplers work well with low steps, having said that, it seems to be fine for me with these settings which is as far as we can test with...
> > Not all samplers work well with low steps, having said that, it seems to be fine for me with these settings which is as far as we can...
The whole dataset was 512*512 you'll only ever get an output that resolves a certain level of detail/sharpness as a result of that. I'm not sure if the Devs ever...
@sczhou well that was certainly a 'hold my beer' moment. Thank you!