Open Source AI Finder

A multimodal model designed for understanding and interacting with the visual world. It can process and reason about images, videos, and text.

An open-source text-to-audio generation model that can create a wide range of sounds and music from textual descriptions.

A text-to-video model that can generate high-quality, long-duration videos with a focus on cinematic quality and storytelling.

An open-source language model with strong performance in coding and reasoning tasks.

A large language model with enhanced reasoning and multilingual capabilities, and a focus on open-source principles.

A multimodal model that can understand and reason across text, images, video, and audio. It is designed for complex reasoning tasks.

A multimodal AI agent that can autonomously create posters by integrating text, images, and layout generation.

A text-to-video synthesis method that generates realistic and expressive human avatars from textual descriptions.

Ovis is a versatile and user-friendly any-to-any image editing model that can handle various editing tasks with a unified framework.

An efficient and effective method for training text-to-image diffusion models for generating ultra-high-resolution images. It supports generating images up to 4K resolution.