Cutting the dataset to samples with Tc below 80 K, we find that the model is unable to make any predictions greater than 80 K. Not very surprising, but a critical failure for what we need this model to do.
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
