updated and testing. It will take 1 hour to generate the video (hopefully less with the new teacache
updated and testing. It will take 1 hour to generate the video (hopefully less with the new teacache)
Flet us know results
DHere's my dumb question of the day lol. Would your supir app work on massed compute? if i installed it from the zip like normal. I have about 70 images i need to upscale and i don't want to wait 12 hours
Fyes it works
Dgreat. thank you
Feverything that has massed compute installer works and i have for almost everything
Flet me know if something broken i can fix hopefully tomorrow
Di really like massed compute for protoyping. i like to train locally, but sometime i get wierd issues with dataset and working them out at lightning speed is so nice
O@Dr. Furkan Gözükara Congratulations on a job well done. I tried the exact same generation from V31 to V32 after a fresh new install.
It works, two important points:
positive: the TeaCache implementation is much cleaner, better quality, less artifact with, of course, same settings of 0.15.
negative: during the process, on V27-31, with the 32Gb preset, on a 5090, it was often around ~28/29Gb used VRAM.
Now, 18.5Gb of used VRAM with the 32GB preset, I've even tried the 48GB preset, same result,
The same generation went from 310s (v31) to 418s (v32)
It works, two important points:
positive: the TeaCache implementation is much cleaner, better quality, less artifact with, of course, same settings of 0.15.
negative: during the process, on V27-31, with the 32Gb preset, on a 5090, it was often around ~28/29Gb used VRAM.
Now, 18.5Gb of used VRAM with the 32GB preset, I've even tried the 48GB preset, same result,
The same generation went from 310s (v31) to 418s (v32)
Fcan you share output txt file?
Fi can try tomorrow hopefully
Osure
OFye dont compare older teacache and newer teacache :d
Fnewer is different implementation better than older
Odid you read me ?
Fthey optimized VRAM. i will check vram usage tomorrow
Fthat could be why using lesser
For maybe
Fwe broken something
Fremind me tomorrow :d
Fi got to sleep
Oyes, ofc the new teacache is better, my willing was not to compare 2 teacaches, but obviously from v31 to v32, there is that new teacache, that seems great with certainly better vram usage, but there is a drop of performance on 24/32Gb GPUs
Ogood night!
JThe first test was not good at all, but I made a mistake by inserting a 9:16 photo and generated a 16:9 video. I'm making another video, but it will take some time
Ja frame of the first video...
J@Dr. Furkan Gözükara Aspect ratio doesn't work on the new update
JSecond video finished. This time with very good quality
JIt is rare. The first version of teacache started slow and ended very fast. The new update starts fast and ends very slow. I think the new update is a bit slower in general. I'll keep testing tomorrow
Fthanks
Fgpu presets broken too
Ffixing now
Fgpu preset broken that is probably why fixing now
OThanks, good luck
Ffixed
FWindows_Update.bat should be sufficienmt
Ffixed ty
OAlright, gonna try
OFrom v32 to v33 : Aspect ratio works correctly now, GPU uses 26.9GB of VRAM instead of 18.5Gb with the 32Gb preset, and for the exact same generation with Teacache 0.15 for 14B : 310s (v31), 418s (v32), 402s (v33) 
Fpresets can be made to use more VRAM looks like there are some vram improvements since i made :d
Fi need to fix RAM leftover issue though. currently it doesnt properly clear after generation
OYes, it's great gg, on your 5090, how much VRAM do you use during process basically ?
Fwell i need to restart pc and test
Fcurrently without wan app i am using 5 gb 
F
Ookay, 5 Gb without wan seems pretty high! I got 1.4 Gb without
Fyes. i try to set presets with thinking as 2gb free :d
Fi need to restart pc lots of apps running :d
Owould be perfect
Oyeah haha
