Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
speedgoose
on Jan 15, 2023
|
parent
|
context
|
favorite
| on:
VToonify: Controllable high-resolution portrait vi...
The paper also says they used 8 Tesla V100. They are GPUs that are dedicated for ML and quite a bit more powerful than a m2.
godmode2019
on Jan 15, 2023
|
next
[–]
Can you confirm that was for inference? I thought that was only for training 55min on 8x v100
speedgoose
on Jan 15, 2023
|
parent
|
next
[–]
You are right, inference only uses one single v100 according to the paper.
techdragon
on Jan 15, 2023
|
prev
[–]
I missed the bit about using 8 of them to run it! Wow that’s a lot of GPU horsepower to do this. More efficient to just use a vtuber style pipeline using unreal engine and the metahumans or other avatars… only need one good GOU for that.
techdragon
on Jan 15, 2023
|
parent
[–]
Follow up,glad to know I read it right the first time.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
