I need help to download 3.1 in colab

[Quick-Eyed-Sky]

I need help downloading 3.1 in colab. I'm not a programmer so I tango with ChatGPT-4o.

I tried !pip install kandinsky3 : error
I tried !pip install git+https://github.com/author/kandinsky3.git

So I did:

!git clone https://github.com/ai-forever/Kandinsky-3.git
%cd Kandinsky-3

and I got : ERROR: Directory '.' is not installable. Neither 'setup.py' nor 'pyproject.toml' found.

In my next cell I have:

import torch
from kandinsky3 import get_pipeline # Import the correct function

Set the device to CUDA

device_map = torch.device('cuda:0')

Define the data types for different components

dtype_map = {
'unet': torch.float32,
'text_encoder': torch.float16,
'movq': torch.float32,
}

Initialize the T2I Flash pipeline for Kandinsky 3.1

t2i_pipe = get_pipeline(device=device_map, dtype=dtype_map)

Move the pipeline to GPU, if available

t2i_pipe = t2i_pipe.to('cuda')

and I get:

ImportError Traceback (most recent call last)
in <cell line: 5>()
3 get_ipython().system('pip install omegaconf # Install omegaconf required by kandinsky3')
4 import torch
----> 5 from kandinsky3.model import get_T2I_Flash_pipeline
6
7 # Set the device to CUDA

ImportError: cannot import name 'get_T2I_Flash_pipeline' from 'kandinsky3.model' (/content/Kandinsky-3/kandinsky3/model/init.py)

I think I can manage the creation of pictures, but I can't find how to import the model...

The examples you provide don't tell how to achieve this.

Please help!! I love Kandinsky and I want to make a colab for everyone...

The colab: https://colab.research.google.com/drive/1bCs9c6HJQS7HD5pQzZmfp4M1wuSQbdbb?usp=sharing

My colab for K 3.0: https://colab.research.google.com/drive/1Tf7rKQ8Yq0zgwsjUbJ11P4Maxzd_M7QL?usp=sharing

[Quick-Eyed-Sky]

I managed to download things with:

import sys
sys.path.append('..')

import torch
from kandinsky3 import get_T2I_Flash_pipeline

device_map = torch.device('cuda:0')
dtype_map = {
'unet': torch.float32,
'text_encoder': torch.float16,
'movq': torch.float32,
}

t2i_pipe = get_T2I_Flash_pipeline(
device_map, dtype_map,
)

When this part runs:

def generate_and_save_image(dynamic_prompt, i):
res = t2i_pipe(
text=dynamic_prompt,
guidance_scale=4,
height=image_dimensions[0],
width=image_dimensions[1]
).images[0]

I get:

OutOfMemoryError: CUDA out of memory. Tried to allocate 128.00 MiB. GPU 0 has a total capacity of 39.56 GiB of which 100.81 MiB is free. Process 146482 has 39.46 GiB memory in use. Of the allocated memory 38.69 GiB is allocated by PyTorch, and 265.55 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.

And I'm on A100 with 40 Gb GPU...