Public KG record
MiniMax H3
Recorded overview
General-purpose multimodal model using a unified context for video generation wi
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Capabilities: image-text-to-video generation
- Capabilities: image-to-video generation
- Capabilities: text-to-video generation
- Capabilities: video-to-video generation
- Capabilities: In-Context Regeneration
- Integrations: minimax-h3 integration
- Integrations: safetensors integration
- Supported types: image/text input
Evidence coverage
The KG currently records 10 known information dimensions and has 9 undocumented dimensions, linked to 4 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- MiniMax — develops
- In-Context Regeneration — has feature
- Hailuo AI — part of
- Contextual Omni Representation — uses
- H3-Omni Transformer — uses