AI tools for Cloud

AI Song Maker is an advanced music creation platform powered by artificial intelligence, designed to enable users to generate high-quality songs effortlessly. The platform provi

Tencent Hy4 is the final hosted release of Tencent's flagship model for long-running agent tasks. It adds visual understanding to the earlier preview's text capabilities and sup

PURE reconstructs depth, camera poses, and colored 3D point clouds from video clips or image sequences. Its unlabeled post-training approach improves feed-forward reconstruction

Underdog Bark 3.0 is a compact English speech recognition family for private dictation and meeting transcription. The model runs locally on a Mac, with small downloadable varian

Comfy Agent is a named creative agent that plans, builds, runs, and iterates on generative-media workflows inside ComfyUI. It translates a natural-language request into workflow

OpenAI Dots are persistent agents that work on delegated projects using their own cloud computer and connected applications. Powered by GPT-6 Astra, they carry context across co

Mira-Scene reconstructs coherent, object-level 3D scenes from a single reference image. It jointly predicts object geometry and pixel-aligned canonical coordinates, aligning the

WeatherNext 3 is Google AI weather-forecasting model for frequently updated, localized predictions. It incorporates real-time satellite observations to improve forecasts of chan

FixAnything repairs rendering artifacts from several kinds of 3D representation using a generalist video model. It refines degraded views from Gaussian splats, NeRFs, meshes, or

Unified Motion Retargeting, or UMR, converts human motion into reference trajectories for humanoid robots with different body structures. It uses exterior body geometry as a com

Muse Glimmer is Meta's open 30-billion-parameter model for always-on local agents. It is optimized for tool use, local coding, multimodal understanding, long-context memory, and

GeoWeaver is a long-sequence 3D reconstruction framework for turning RGB video into globally consistent cameras and point clouds. It addresses the scale drift, pose errors, and

Bonsai 27B is PrismML's low-bit multimodal language model family based on Qwen3.6 27B and designed to run locally on consumer hardware, including phones. The release includes te

MeshFlow is an efficient artistic mesh generation method that combines MeshVAE with a flow-based diffusion transformer. It generates explicit mesh geometry and connectivity in a

RecGen is a generative 3D reconstruction framework for recovering complete multi-object scenes from sparse RGB-D observations. Instead of treating each visible fragment as the w

MiniCPM-V 4.6 is a compact multimodal language model for efficient image and video understanding on edge and mobile devices. It is built for scenarios where users need strong vi

Vista4D is a video reshooting framework that uses 4D point clouds to synthesize dynamic scenes from new camera trajectories and viewpoints. It is designed for cases where a sour

Mistral 3.5 Medium is a flagship 128B dense model from Mistral designed to combine instruction following, reasoning, and coding in one system. It powers remote coding agents in

World Reconstruction From Inconsistent Views is a 3D reconstruction project that builds worlds from video diffusion outputs. The key challenge it addresses is that generated vid