Unable to use example

[nonetrix]

Most likely user error but using the examples provided doesn't work

pip install imagen-pytorch

import torch
from imagen_pytorch import Unet, Imagen

# unet for imagen

unet1 = Unet(
    dim = 32,
    cond_dim = 512,
    dim_mults = (1, 2, 4, 8),
    num_resnet_blocks = 3,
    layer_attns = (False, True, True, True),
    layer_cross_attns = (False, True, True, True)
)

unet2 = Unet(
    dim = 32,
    cond_dim = 512,
    dim_mults = (1, 2, 4, 8),
    num_resnet_blocks = (2, 4, 8, 8),
    layer_attns = (False, False, False, True),
    layer_cross_attns = (False, False, False, True)
)

# imagen, which contains the unets above (base unet and super resoluting ones)

imagen = Imagen(
    unets = (unet1, unet2),
    image_sizes = (64, 256),
    timesteps = 1000,
    cond_drop_prob = 0.1
).cuda()

# mock images (get a lot of this) and text encodings from large T5

text_embeds = torch.randn(4, 256, 768).cuda()
images = torch.randn(4, 3, 256, 256).cuda()

# feed images into imagen, training each unet in the cascade

for i in (1, 2):
    loss = imagen(images, text_embeds = text_embeds, unet_number = i)
    loss.backward()

# do the above for many many many many steps
# now you can sample an image based on the text embeddings from the cascading ddpm

images = imagen.sample(texts = [
    'a whale breaching from afar',
    'young girl blowing out candles on her birthday cake',
    'fireworks with blue and green sparkles'
], cond_scale = 3.)

images.shape # (3, 3, 256, 256)

The base dimension of your u-net should ideally be no smaller than 128, as recommended by a professional DDPM trainer https://nonint.com/2022/05/04/friends-dont-let-friends-train-small-diffusion-models/
Traceback (most recent call last):
  File "test.py", line 26, in <module>
    imagen = Imagen(
  File "/home/user/.local/lib/python3.8/site-packages/imagen_pytorch/imagen_pytorch.py", line 1821, in __init__
    assert not (exists(video_frames) and video_frames < 1), 'video frames must be at least 1 or greater'
NameError: name 'video_frames' is not defined

Trying to define the missing variable does nothing or returns the blow error depending where I put it

The base dimension of your u-net should ideally be no smaller than 128, as recommended by a professional DDPM trainer https://nonint.com/2022/05/04/friends-dont-let-friends-train-small-diffusion-models/
Traceback (most recent call last):
  File "test.py", line 28, in <module>
    imagen = Imagen(
TypeError: __init__() got an unexpected keyword argument 'video_frames'

I am not trying to generate videos so I have no idea why it is asking for this in the first place

[lucidrains]

Oops, trying to fix this on phone

Try 1.6.4?

[debagos]

Thank you for the quick response, problem solved 👍