
I generated a dataset to test the knowledge scope and capabilities of MiniMax H3. Samples are of various aspect sizes, and cover a wide range of media types and themes. The videos are 768 base resolution (~0.6 MP). They were generated with minimax_h3_fl2va_pruned_int8_convrot.safetensors with 30 steps.
A full video of this dataset can be viewed here https://youtu.be/akkwj9d943Y
9 commits

I generated a dataset to test the knowledge scope and capabilities of MiniMax H3. Samples are of various aspect sizes, and cover a wide range of media types and themes. The videos are 768 base resolution (~0.6 MP). They were generated with minimax_h3_fl2va_pruned_int8_convrot.safetensors with 30 steps.
A full video of this dataset can be viewed here https://youtu.be/akkwj9d943Y
9 commits