Almost same time taken with OV on in previous version of 5.4.5.Changed block size to 384x384, no difference noticed.Lots of parts have blurriness with ggn-v1-fp32-192x192 as compared to the 5.4.5.Time taken to process is same as time taken in version 5.4.5 CPU mode.This uses only CPU and block size of 192x192 from the logs. So i understand that the 192x192 or 384x384 is the block size. I also checked that 5.5 models are the same that the models in beta.I’m downloading all models, thanks for the share, but 17 Go will take me at least a day, I don’t know if I’ll succeed. The only thing I didn’t know yet is to check that *-tf.tz models produce blurry results.Let’s say that 80% areas I checked are better now. : I tried with a single picture, a cartoon in CGI and I can say this : by comparison with the same picture done in CPU only, sometimes old model is better, but most of the time new model is better, frankly.Yes the results are different, and yes I disabled “model downloading” so I just have models packed with the installer.
I re-installed 5.3.2, one of the last builds where I’m sure that I can use CPU only, as we can manage this in preferences. You have played around in the folder of the model files.
0 kommentar(er)
