AI tools for Motion Control

Canvora is presented as the smartest visual assistant designed to instantly transform content into a vast array of over 70 different visual formats. Whether you have existing ma

This innovative online tool allows users to effortlessly transform static photographs into dynamic, romantic kissing videos using advanced synthesis technology. The process is d

RoboSkills is an open collection of lightweight agent workflows and tools for robotics. It packages five working approaches: automated research, agent-as-policy control, agentic

MotionBricks generates controllable character and humanoid motion in real time. NVIDIA provides pretrained human and Unitree G1 models, a Python runtime, interactive demos, and

RoboParty RP1 is an open full-stack humanoid platform spanning physical design, firmware, deployment, and learning. Connected repositories provide mechanical and electrical file

GaussiAnimate rigs and animates reconstructed humans, animals, garments, and other deformable 3D entities. An inner-outer skeleton representation combines kinematic control with

Drama 3 is Fish Audio's expressive voice-generation model for directing how a line is performed, not just which words are spoken. Natural-language instructions and inline contro

TERRA is an end-to-end system for terrain-aware musculoskeletal motion retargeting and control. It reconstructs support geometry from motion and contact evidence, then trains a

WorldPlay2 is an interactive world model for controlling generated scenes and characters over long sequences. It combines factorized action and semantic controls with compressed

Eleven v4 is ElevenLabs' expressive speech-model family, including a Turbo variant for real-time voice applications. The model interprets script context and inline audio tags to

Gemini 3.8 TTS is Google's expressive speech-generation family, including Flash TTS and Flash-Lite TTS. Natural-language directions guide character voices and line-by-line deliv

Sparse 3D Locomotion is a humanoid-control research system for traversing thin, elevated structures. It demonstrates jumping onto monkey bars, moving between them, and landing,

Show-Harness lets vision-language models control robots through a compact set of semantic action symbols. It connects high-level visual reasoning with fine-grained physical deci

H3-World turns keyboard-style character and camera actions into controllable video dynamics. It builds on MiniMax-H3 to generate visually coherent environments that follow chang

LTX-2.5 is LTX's open-source foundation model for generating and editing video. It combines a stronger distilled model with improved prompt understanding, cleaner motion, native

SCoPE is a camera-control method for video diffusion transformers. It gives every video token a camera ray as a second positional coordinate so target camera motion becomes part

ShadowDancer is a video world model research project that teaches a single model many different actions by learning unified dynamics representations from synchronized shadow pai

PRISM is a robotics research project for learning Polynomial Representations for Interaction-Structured Motor Control. It makes action-relevant interactions among observable rob

Seedance 2.5 is ByteDance Seed's video generation model for creating longer narrative clips with stronger prompt following, shot continuity, and production-oriented control. It

ID-V2V is an identity-preserving video restylization framework from Eyeline Labs for applying scene, lighting, and style changes to a source video while keeping human identity a

PhiZero is a research world model built around physical language, a compact discrete representation of world-state transitions learned from in-the-wild video. It separates physi

HOMIE is a human-object centric video personalization model for generating personalized videos involving people and objects. It uses multimodal cognition enhancement to preserve