# Multimodal Input

Gemma 3 is a lightweight open-source multimodal model from Google, supporting text and image input with text output, featuring a 128K ultra-long context window and support for 140+ languages.

3DTopia-XL is a diffusion Transformer architecture based on PrimX efficient 3D representation, capable of rapidly generating high-quality 3D assets

SAM 2 is a foundational model for promptable visual segmentation in images and videos developed by FAIR, supporting efficient segmentation through prompts.