I have 12 GB of VRAM, yet I'm still experiencing an out-of-memory (OOM) issue. Can someone specify how much RAM I need for it?

[SAT431]

No description provided.

[Hussain-X]

Are you using cpu_offloading=True parameter?
As mentioned below:
#23

[SAT431]

Are you using cpu_offloading=True parameter? As mentioned below: #23

yes i used cpu_offloading=True and i have 24gb of ram and 12gb of vram. when it is trying to load models i getting like this: (myenv) sathvik@sathvik:/mnt/c/Users/pasun/Music/Pyramid-Flow$ python app.py
Model directory '/mnt/c/Users/pasun/Music/Pyramid-Flow/pyramid_flow_model' already exists. Skipping download.
using half precision
Using temporal causal attention
We interp the position embedding of condition latents
You set add_prefix_space. The tokenizer needs to be converted from the slow tokenizers
Loading checkpoint shards: 50%|█████████████████████████████ | 1/2 [00:45<00:45, 45.82s/it]Killed

[FurkanGozukara]

@SAT431 killed is out of ram error

You nerd buy more ram

[SAT431]

FurkanGozukara

thank you