MamMuT
MamMuT is Google's image to text model. Google's Masked Multimodal Trajectory model for joint vision-language understanding using masked pretraining objectives.
Google's image to text model. Google's Masked Multimodal Trajectory model for joint vision-language understanding using masked pretraining objectives.google-mammut |
| Image to Text |
| Active |
| Google |
| Image |
| Text |
Capabilities
Input1/5
·
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MamMuT | — | — | — | — | Current |
| Earth AI Imagery MamMuT EAP | — | — | — | — | Available |