# Multimodal input

Mistral Small 3.2 24B Instruct 2506 is a multilingual large language model that supports text and image input and text output, with a context length of 128k.

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google, built on the same research and technology as the Gemini model. It supports text, audio, and visual inputs and is suitable for various tasks.

Qwen2.5-Omni-7B-GGUF is the GGUF format version of the Qwen2.5-Omni-7B model, supporting multimodal inputs including text, audio, and images.

Qwen2.5-Omni-3B is a multimodal model that supports text, audio, and image input, but does not support video input or audio generation.

DAM-3B-Video is a 3-billion-parameter vision-language model capable of generating fine-grained local descriptions for user-specified image/video regions.

Canny edge detection control network adapted for Stable Diffusion 3.5 large model, used for precise control of image generation process

The first DiT-based video generation model capable of real-time generation of high-quality videos, supporting two scenarios: text-to-video and image + text-to-video.

DiVA Llama 3 is an end-to-end voice assistant model capable of processing both speech and text inputs, trained using distillation loss.