Downloads · 30 days
0
Kandinsky_2.0
ai-forever/Kandinsky_2.0
Kandinsky_2.0 is a machine learning model from ai-forever. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Kandinsky 2.0 — the first multilingual text2image model.
Access
Public
Updated Nov 24, 2022
Repo size
13.7 GB
Likes
42
Public
Repo makeup
Click a slice to open those files.
.pt5.3 GB · 54%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Nov 22, 2022
- Updated
- Nov 24, 2022
- SHA
- 04e8fc7e
Model card
From the Hugging Face model README
Kandinsky 2.0
Kandinsky 2.0 — the first multilingual text2image model.
UNet size: 1.2B parameters
It is a latent diffusion model with two multi-lingual text encoders:
- mCLIP-XLMR (560M parameters)
- mT5-encoder-small (146M parameters)
These encoders and multilingual training datasets unveil the real multilingual text2image generation experience!
How to use
pip install "git+https://github.com/ai-forever/Kandinsky-2.0.git"
from kandinsky2 import get_kandinsky2
model = get_kandinsky2('cuda', task_type='text2img')
images = model.generate_text2img('кошка в космосе', batch_size=4, h=512, w=512, num_steps=75, denoised_type='dynamic_threshold', dynamic_threshold_v=99.5, sampler='ddim_sampler', ddim_eta=0.01, guidance_scale=10)
Authors
- License
- apache-2.0
- Created
- Nov 22, 2022
- Updated
- Nov 24, 2022