pixeli99/SVD_Xtend

training gpu cost

zhw-zhang opened this issue · 3 comments

Hi, thank you for your open-source code. How much GPU consumption is required during training? Is it necessary to add additional deepspeed or checkpoint to save training memory consumption?

This depends on your specific training setup, with my current configuration (512*320, 16 frames, with all parameters of unet trainable), it will use approximately 63GB of VRAM (I haven't enabled any optimizations, such as deepspeed and so on)

Thank you for your reply. So your batchsize is 1? At 512*320 resolution.

Yes, batchsize=1