dreamify 0.12.0

No project description provided

Dreamify

A function that applies deep dream to an image using pre-trained CNNs trained on the ImageNet dataset.

Installation

pip install dreamify

Usage

To apply Dreamify to an image, use the following Python script:

from dreamify.dream import generate_dream_image


image_path = "example.jpg"

generate_dream_image(image_path):

You may customize the behavior of the dreamifyer by selecting a different pre-trained model, saving it as a video, etc.:

from dreamify.dream import generate_dream_image


image_path = "example.jpg"

generate_dream_image(
    image_path,
    output_path="dream.png",
    model_name="inception_v3",
    learning_rate=5.0,
    num_octave=5,
    octave_scale=1.3,
    iterations=100,
    max_loss=15.0,
    save_video=False,
    duration=10,
)

Available Models

Dreamify supports the following models:

Model Name	Enum Value
VGG19	vgg19
ConvNeXt-XL	convnext_xl
DenseNet121	densenet121
EfficientNet-V2L	efficientnet_v2l
Inception-ResNet-V2	inception_resnet_v2
Inception-V3 (Default)	inception_v3
ResNet152V2	resnet152v2
Xception	xception
MobileNet-V2	mobilenet_v2