SAM 3 is the third - generation promptable segmentation foundation model launched by Meta. It can use text or visual prompts (points, boxes, masks) to detect, segment, and track objects in images and videos. Compared with previous generations, SAM 3 introduces the ability to exhaustively segment all instances of open - vocabulary concepts, supports a large number of open - vocabulary prompts, and achieves 75 - 80% of human performance on the SA - CO benchmark.

Computer VisionTransformersEnglish

Qwen3-VL is the most powerful vision-language model in the Tongyi large model series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context support, strong spatial and video dynamic understanding capabilities, and outstanding intelligent agent interaction capabilities. This model uses a Mixture of Experts (MoE) architecture and is a thinking version for enhanced reasoning.

MultimodalGguf

Qwen3-VL is the most powerful vision-language model in the Tongyi large model series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context support, strong spatial and video dynamic understanding capabilities, and outstanding agent interaction capabilities.

MultimodalSafetensors

Wan2.2 is a significant upgrade version of the basic video model. It introduces the Mixture of Experts (MoE) architecture, incorporates carefully curated aesthetic data, and is trained on larger datasets to enhance the ability to generate complex motions. This model supports generating 5-second videos with 480P and 720P resolutions, and has significant improvements in video generation quality and performance.

MultimodalDiffusers

Qwen3-VL is the most powerful vision-language model in the Tongyi large model series, with significant improvements in text understanding and generation, visual perception and reasoning, context length, spatial and video dynamic understanding, and agent interaction capabilities. This model offers both dense architecture and mixture-of-experts model architecture, supporting deployments of different scales from the edge to the cloud.

MultimodalTransformers

Wan2.1 is an open and advanced large-scale video generation model with top-tier performance, capable of running on consumer-grade GPUs and excelling in multitask processing.

MultimodalDiffusersMultiple Languages

VideoLLaMA2.1-7B-AV is a multimodal large language model focused on audio-visual question answering tasks, capable of processing both video and audio inputs to provide high-quality question answering and description generation.

MultimodalTransformersEnglish

An open and advanced large-scale video generation model suite supporting multiple tasks including text-to-video and image-to-video generation

MultimodalDiffusersEnglish

Wan2.1 is an open and advanced large-scale video generation model that supports various tasks including text-to-video and image-to-video, compatible with consumer-grade GPUs.

MultimodalDiffusersMultiple Languages

Hunyuan Video is a large-scale video generation model open-sourced by Tencent, achieving high-quality text-to-video generation through an innovative unified architecture

MultimodalSafetensors

A large-scale video generation model open-sourced by Tencent, supporting text-to-video generation, with performance comparable to mainstream closed-source models.

AuroraCap is a multimodal large language model for image and video captioning, focusing on efficient and detailed video caption generation.

MultimodalSafetensors

CogVideoX is an open-source version of the video generation model from Qingying. The 5B version has a larger model scale and can generate higher-quality video content.

MultimodalDiffusersEnglish

VideoLLM-online is a multimodal large language model based on Llama-3-8B-Instruct, focusing on online video understanding and video-text generation tasks.

MultimodalSafetensorsEnglish

This model combines large language models with video diffusion technology, supporting text-to-video generation and allowing control over video content through bounding box conditional input.

MultimodalDiffusers