Downloads · 30 days
0
Kandinsky_2.1
ai-forever/Kandinsky_2.1
Kandinsky_2.1 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.
Access
Public
Updated Apr 5, 2023
Repo size
48.5 GB
Likes
187
Public
Repo makeup
Click a slice to open those files.
.ckpt12.6 GB · 85%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 15, 2023
- Updated
- Apr 5, 2023
- SHA
- 3eb96acc
Model card
From the Hugging Face model README
Kandinsky 2.1
Architecture
Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffusion, while introducing some new ideas.
As text and image encoder it uses CLIP model and diffusion image prior (mapping) between latent spaces of CLIP modalities. This approach increases the visual performance of the model and unveils new horizons in blending images and text-guided image manipulation.
For diffusion mapping of latent spaces we use transformer with num_layers=20, num_heads=32 and hidden_size=2048.
Other architecture parts:
- Text encoder (XLM-Roberta-Large-Vit-L-14) - 560M
- Diffusion Image Prior — 1B
- CLIP image encoder (ViT-L/14) - 427M
- Latent Diffusion U-Net - 1.22B
- MoVQ encoder/decoder - 67M
Authors
- License
- apache-2.0
- Created
- Mar 15, 2023
- Updated
- Apr 5, 2023