How to fit Versatile Diffusion into colab RAM?

hadaev November 24, 2022, 6:06pm 1

Passing torch_dtype=torch.float16 doesnt help.
Any suggestions?

Topic		Replies	Views
[Diffusers] PyTorch running out of memory 🧨 Diffusers	1	785	August 30, 2022
Outofmemory error when running pipieline.to("cuda") 🧨 Diffusers	1	1832	March 16, 2023
Confused with setting up torch_dtype while using CPU as device 🤗Transformers	0	2315	October 12, 2022
Error 'expected scalar type Half but found Float' 🧨 Diffusers	2	3912	November 8, 2022
RuntimeError: Input type (CPUBFloat16Type) and weight type (torch.DoubleTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor Models	0	1119	October 12, 2022