use this program in my own application

[ElmiraNa]

I try to use the first order model in my own web app. I wrote an api based on flask. For one request it takes about 30 seconds to compute the output for a 8 seconds video. But when I send two requests (I mean 2 parallel requests of two users) for animate the video, my GPU could not handle it. It says my cuda is out of memory. My gpu device is nvidia geforce gtx 1060 6GB. Does any one has same experience? let me know how do you use it in your own program and how do you manage parallel requests?

[ElmiraNa]

@AliaksandrSiarohin would you please guide me

[lilingdu]

Ｈi，I ａｌｓｏ　try to use the first order model in my own web app. ｂｕｔ　Ｉ　ｄｏ＇ｔ　ｋｎｏｗ　ｈｏｗ　ｔｏ　ｗｒｉｔｅ　ａｎ　ａｐｉ　ｂａｓｅ　ｏｎ　ｆｌａｓｋ，　ｃａｎ　ｙｏｕ　ｈｅｌｐ　ｈｅｒｅ？