Not a very robust report yet. We're not through all the data points and these results come from a few different models (trained with more data as it came available)
7
Use vision capabilities to understand images
fileimage→JSON
15 uses
Create variations of an existing image
fileimage→file
2 uses
Generate 3D assets from a single 2D input image
fileimage→file
1 use
Generate a short video from an image
fileimage→file
1 use
Image-to-image generation for controlled variations of existing images or sketches