ai-forever / kandinsky-2

text2img model trained on LAION HighRes and fine-tuned on internal datasets

  • Public
  • 6.2M runs
  • GitHub
  • License
Run with an API
Playground API Examples README Versions

Examples

View more

Run time and cost

This model costs approximately $0.061 to run on Replicate, or 16 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 44 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Kandinsky 2.1

Model architecture:

Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffucion, 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

Kandinsky 2.1 was trained on a large-scale image-text dataset LAION HighRes and fine-tuned on our internal datasets.