search

FrozenBurning / Text2Light

[SIGGRAPH Asia 2022] Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
https://frozenburning.github.io/projects/text2light/
Other
598 stars 47 forks source link

About GPU memory cost #18

Closed VLadImirluren closed 12 months ago

VLadImirluren commented 1 year ago

Can this code run on 24G 3090 GPU? thanks

FrozenBurning commented 1 year ago

I do not have a 3090 on my side, thus the training is not guaranteed. You can decrease the batch size and give it a try. You can definitely run the inference code on it as we have Colab demo where even smaller GPU than 3090 can host the model.

VLadImirluren commented 1 year ago

thanks!

At 2023-07-19 22:30:15, "Zhaoxi Chen" @.***> wrote:

I do not have a 3090 on my side, thus the training is not guaranteed. You can decrease the batch size and give it a try. You can definitely run the inference code on it as we have Colab demo where even smaller GPU than 3090 can host the model.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>