Minting ClosedView All
8,000 Dreamers
Each Dreamer is the combination of traditional fine-art, machine learning, and collectibles. Until further notice, there are only 1485 Dreamers.
4 Different Creators
Model 1
Model 2
Dalle
@wheattreat
The Process
Step 1: Base layers
Traditional artist, @wheatatreat, creates a large set of individual faces and backgrounds.
Step 2: Data set
Large dataset is created by scrambling up all of the faces and backgrounds and adding variations.
Step 3: Training
Train AI models (GANs) on the dataset created in step 2.
Step 4: (lots of) Image Processing
The models output lots of images that were visually similar to one another. This step compares all and removes similar images.
Step 5: Traits
After hand labelling some of the outputs, a convolutional neural network was trained to learn how to assign traits to the rest of the images.We also used a pre-trained CLIP model in order to assign some additional traits.
