Multimodal Models

Introduction

Multimodal models in this section combine understanding and generation capabilities across text and visual modalities. These model families may use custom training recipes, packed multimodal datasets, or task-specific model wrappers beyond the standard image-text-to-text fine-tuning path.

Supported Models

This table combines recipe-backed checkpoints with documented model families. Dates show when the current checkpoint first appeared in a recipe, or when a documentation-only family page was added. See the combined model support log for recipe-backed checkpoints of every model type.