Kandinsky 3.0 is an open-source text-to-image diffusion model built upon the Kandinsky2-x model family. In comparison to its predecessors, Kandinsky 3.0 incorporates more data and specifically related to Russian culture, which allows to generate pictures related to Russin culture. Furthermore, enhancements have been made to the text understanding and visual quality of the model, achieved by increasing the size of the text encoder and Diffusion U-Net models, respectively.
For more information: details of training, example of generations check out our
post
. The english version will be released in a couple of days.
Architecture details:
Architecture consists of three parts:
Text encoder Flan-UL2 (encoder part) - 8.6B
Latent Diffusion U-Net - 3B
MoVQ encoder/decoder - 267M
Models
We release our two models:
Base: Base text-to-image diffusion model. This model was trained over 2M steps on 400 A100
Inpainting: Inpainting version of the model. The model was initialized from final checkpoint of base model and trained 250k steps on 300 A100.
Weights of the model are loaded internally but if want to change them one can use the following example:
The exact dependencies is got using
pip freeze
and can be found in
exact_requirements.txt
How to use:
Check our jupyter notebooks with examples in
./examples
folder
1. text2image
from kandinsky3 import get_T2I_pipeline
t2i_pipe = get_T2I_pipeline('cuda', fp16=True)
image = t2i_pipe( "A cute corgi lives in a house made out of sushi.")
2. inpainting
from kandinsky3 import get_inpainting_pipeline
inp_pipe = get_inpainting_pipeline('cuda', fp16=True)
image = ... # PIL Image
mask = ... # Numpy array (HxW). Set 1 where image should be masked
image = inp_pipe( "A cute corgi lives in a house made out of sushi.", image, mask)
Examples of generations
"A beautiful landscape outdoors scene in the crochet knitting art style, drawing in style by Alfons Mucha"
"a yellow house at the edge of the danish fjord, in the style of eiko ojala, ingrid baars, ad posters, mountainous vistas, george ault, realistic details, dark white and dark gray, 4k"
"dragon fruit head, upper body, realistic, illustration by Joshua Hoffine Norman Rockwell, scary, creepy, biohacking, futurism, Zaha Hadid style"
"Amazing playful nice cute strawberry character, dynamic poze, surreal fantazy garden background, gorgeous masterpice, award winning photo, soft natural lighting, 3d, Blender, Octane render, tilt - shift, deep field, colorful, I can't believe how beautiful this is, colorful, cute and sweet baby - loved photo"
"beautiful fairy-tale desert, in the sky a wave of sand merges with the milky way, stars, cosmism, digital art, 8k"
"Car, mustang, movie, person, poster, car cover, person, in the style of alessandro gottardo, gold and cyan, gerald harvey jones, reflections, highly detailed illustrations, industrial urban scenes""
"cloud in blue sky, a red lip, collage art, shuji terayama, dreamy objects, surreal, criterion collection, showa era, intricate details, mirror"
Kandinsky3.0 huggingface.co is an AI model on huggingface.co that provides Kandinsky3.0's model effect (), which can be used instantly with this ai-forever Kandinsky3.0 model. huggingface.co supports a free trial of the Kandinsky3.0 model, and also provides paid use of the Kandinsky3.0. Support call Kandinsky3.0 model through api, including Node.js, Python, http.
Kandinsky3.0 huggingface.co is an online trial and call api platform, which integrates Kandinsky3.0's modeling effects, including api services, and provides a free online trial of Kandinsky3.0, you can try Kandinsky3.0 online for free by clicking the link below.
ai-forever Kandinsky3.0 online free url in huggingface.co:
Kandinsky3.0 is an open source model from GitHub that offers a free installation service, and any user can find Kandinsky3.0 on GitHub to install. At the same time, huggingface.co provides the effect of Kandinsky3.0 install, users can directly use Kandinsky3.0 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.