# Vision-language interaction

Qwen2-VL-72B-Instruct is a multimodal vision-language model that supports interaction between images and text, suitable for complex vision-language tasks.

Pixtral is a multimodal model based on the Mistral architecture, capable of processing both image and text inputs to generate detailed textual descriptions.

A vision-language large model based on InternLM2 with outstanding image-text understanding and creation capabilities