Habr Post | | Telegram-bot | Technical Report| Our text-to-image model
KandiSuperRes is an open-source diffusion model for x4 super resolution. This model is based on the Kandinsky 3.0 architecture with some modifications. For generation in 4K, the MultiDiffusion algorithm was used, which allows to generate panoramic images. For more information: details of architecture and training, example of generations check out our Habr post.
To install repo first one need to create conda environment:
conda create -n kandisuperres -y python=3.8;
source activate kandisuperres;
pip install -r requirements.txt;
Check our jupyter notebook KandiSuperRes.ipynb
with example.
from KandiSuperRes import get_SR_pipeline
from PIL import Image
sr_pipe = get_SR_pipeline(device='cuda', fp16=True)
lr_image = Image.open('')
sr_image = sr_pipe(lr_image)