Instructions to use etri-vilab/koala-700m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use etri-vilab/koala-700m with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("etri-vilab/koala-700m", 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 Settings
- Draw Things
- DiffusionBee
KOALA Team - Congratulations
I read through the arrival published on the Bing network and jumped to your pre-published arXiv paper and started reading through it. Your work is quite amazing and the idea that AI Art Generation technology is slowly moving towards smaller platform requirements without sacrificing speed and image quality is a big step in the right direction regardless of the financial impact on AI Gen providers who have placed millions into making AI Art available at large cost to all that are interested. I myself would like to be self dependent with my own home system rather than rely on the big guys.
Thanks for doing the research and development and congratulations. Your hard and earnest work will help to bring down AI Art to the “crayon cost level” eventually.