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	778	August 30, 2022
Outofmemory error when running pipieline.to("cuda") 🧨 Diffusers	1	1821	March 16, 2023
Changing bnb_4bit_compute_dtype Beginners	0	136	July 18, 2024
Confused with setting up torch_dtype while using CPU as device 🤗Transformers	0	2269	October 12, 2022
Error 'expected scalar type Half but found Float' 🧨 Diffusers	2	3877	November 8, 2022