Instructions to use kandinsky-community/kandinsky-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinsky-community/kandinsky-3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
CUDA Error in Google Colab
#4
by Atm4x - opened
I'm very new to AI and etc. So I don't know how to fix my problem.
I'm always getting CUDA Out of memory error when the pipeline starts to generate (T4 gpu in google colab). I've tried a lot of options, but it didn't work.
I also tried the Kaggle.com with P100 gpu, but it's the same thing..
cuda error also appears if I run pipe.to('cuda')
Could you please help?
Thanks in advance
Atm4x changed discussion status to closed
