Live
The machines.
Ten nodes in Los Angeles, four slots each. This page is live. Dark is rendering for a visitor, violet is rendering for the collection, light is resting.
Node 1
resting
resting
resting
resting
Node 2
resting
resting
resting
resting
Node 3
resting
resting
resting
Node 4
resting
resting
resting
Node 5
resting
resting
resting
resting
Node 6
resting
resting
resting
resting
Node 7
resting
resting
resting
resting
Node 8
resting
resting
resting
resting
Node 9
resting
resting
resting
resting
Node 10
resting
resting
resting
0 for visitors · 0 for the collection · 37 resting · 3 off
The hardware.
- Name
- NVIDIA Tesla K80
- Released
- November 2014
- Inside
- Two GK210 chips, 12 GB each. Each half is a slot.
- Precision
- fp32 only. No half precision, so no shortcuts.
- Last supported
- CUDA 11, PyTorch 2.0, diffusers 0.14. Frozen there on purpose.
- Work rate
- 2.7 seconds per step, about a minute per frame.
- Since
- Retired from client work, rehired for this.
The loop has stopped starting new works. 1200 of them are waiting for a curator, and it starts no more at 1200 until they are reviewed.
This week: 3930 rendered · 395 kept