Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.

Hunyuan World 1.0 turns a single image into a panorama or a 3D world. It creates realistic scenes from the image, allowing you to explore and view it from different angles.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Get waveform data from audio files using FFmpeg API.

Generate 3D models from a single image with Hi3D.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Generate 3D models from one or more images using ReconViaGen 0.5

Vision

Meshy T2.5 is Meshy's latest Smart Topology model. It converts a single image into a clean, triangle-only 3D mesh with natively separated parts, with a target polycount of up to 30,000 triangles (default 15,000). Compared with Meshy T2, it produces sharper detail and keeps shape and proportions clos

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Isaac-01 is a multimodal vision-language model from Perceptron for various vision language tasks.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?

Estimates metric 3D geometry from a single image, returning a point map, depth, surface normals, a validity mask and the camera field of view. A sparse 3D refiner sharpens the predicted depth, and the result can be exported as a textured GLB mesh and a colored PLY point cloud.

Generate 3D models from multiple view images using Hi3D.

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Estimates metric 3D geometry from a single image, returning a point map, depth, a validity mask and the camera field of view, with surface normals on the normal-capable checkpoints. Four ViT checkpoints trade accuracy for speed, and the result can be exported as a textured GLB mesh and a colored PLY

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Meshy T2 is Meshy's faster Smart Topology model. It converts a single image into a clean, triangle-only 3D mesh with natively separated parts, with a target polycount of up to 15,000 triangles (default 4,000). It generates faster than Meshy T2.5, which suits low-poly assets and speed-sensitive pipel

SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

ffmpeg utility to interleave videos

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels