QVQ-Max is a vision reasoning model developed by Alibaba, based on Qwen2-VL-72B. It is designed to enhance AI’s capabilities in visual understanding and solving complex problems.
Qwen2.5-Omni is an end-to-end multimodal AI model released by Alibaba, designed to achieve comprehensive perception capabilities. It can process various input formats, including text, images, audio, and video.
Ideogram 3.0 is an AI-powered text-to-image generation model that has undergone significant improvements to enhance user creativity and image generation quality.
Gemini 2.5 Pro is an AI model launched by Google, hailed as its "most intelligent model" yet. It is designed to handle complex tasks, excelling in reasoning capabilities, coding performance, and multimodal input processing.
Qwen2.5-VL-32B is a multimodal vision-language model released by Alibaba, featuring 3.2 billion parameters. It excels in tasks such as image understanding, mathematical reasoning, and text generation.
Reve Image is an AI image generation model developed by Reve, designed to combine aesthetics with layout capabilities, delivering outstanding image generation performance.
Reka Flash 3 is a newly released multimodal language model with 2.1 billion parameters, designed for efficient reasoning and generation.
Step-Video-TI2V is an advanced text-driven image-to-video generation model capable of producing videos up to 102 frames based on text descriptions and image inputs.
EXAONE Deep is a series of reasoning-enhanced language models launched by LG AI Research, designed to improve reasoning capabilities in fields such as mathematics, science, and programming.