The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘an abstract self portrait.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘my beautiful dark twisted fantasy.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘a painting of outer space.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘a group of aliens smoking weed.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘a group of people smoking weed.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘a group of robots smoking weed.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘a psychedelic experience on LSD.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘a spiritual experience on DMT’. Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
The above image was made using the Deep Haze, the simple command line tool for text to image generation using OpenAI’s CLIP and Siren. The prompt for this image was ‘a psychedelic experience on mushrooms.’ Here are the adopted hyperparameters: 1e-5 is the learning rate of the neural network, 16 is the number of hidden layers to use in the neural network, 8 is the number of epochs to run, 256 is the number of times to calculate and backpropagate loss in a given epoch, 4 is the number of samples used for each iteration to calculate the weighted loss, and 4 is the number of generated images to pass before calculating loss.
Untitled Digital Art #2
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
The above image was made using Adobe Fresco, the powerful drawing app with the world’s largest digital brush collection.
Solid Background (HEX: #880016).
