Directors and previsualization teams
Explore shots while controlling camera movement, subject motion, poses, trajectories, and key moments.
Independent tool overview
Marey is Moonvalley's filmmaker-focused generative video model, built around licensed training footage and granular controls for camera, motion, pose, trajectories, references, and keyframes.
Visit the official Marey by Moonvalley site ↗
Overview
Marey is an AI video system for filmmakers and professional creative teams that need more direction than a text prompt alone can provide. It supports text-to-video and image-to-video generation alongside control tools that use reference images, reference footage, paths, poses, and keyframes.
Moonvalley's core differentiation is provenance: the company says Marey was trained exclusively on licensed, high-resolution footage rather than scraped web video or user submissions. That can make the model easier to evaluate for commercial production, although each project still needs rights clearance for its prompts, uploads, people, brands, music, and final use.
Creators can use Marey through Moonvalley's own experience, while developers can access several Marey Realism workflows through official inference partner fal.ai. Moonvalley's direct public API page currently runs a waitlist, so teams should distinguish the creative app, partner endpoints, and any custom enterprise arrangement.
Use cases
The strongest fit depends on the job you need the product to complete, not the size of its feature list.
Explore shots while controlling camera movement, subject motion, poses, trajectories, and key moments.
Evaluate a video model whose provider explicitly centers licensed training data and production-oriented control.
Call Marey's text, image, pose, and motion endpoints through fal.ai or build native Comfy workflows.
Capabilities
Generate a new shot from a detailed description or animate a supplied image as the starting frame.
Creates directed camera movement from a still scene by treating the image as a three-dimensional environment.
Uses a reference performance or video to guide the timing, gestures, motion, or composition of a new subject and scene.
Lets a creator draw an object's intended path instead of relying on repeated prompt revisions.
Accepts multiple visual references on a timeline to guide subjects, objects, shot appearance, and transitions.
Extends an existing generated segment while attempting to preserve scene dynamics and motion continuity.
Process
Step 1
Write the visual objective, duration, aspect ratio, camera language, subject, action, setting, lighting, and continuity requirements.
Step 2
Start from text or an image, then add camera, motion, pose, trajectory, keyframe, or reference guidance where precision matters.
Step 3
Change one variable at a time, preserve useful seeds and references, and compare outputs against the shot brief.
Step 4
Inspect every frame, edit or composite the selected take, add separately cleared audio, and complete legal, brand, talent, and delivery review.
Cost
Moonvalley does not show a simple direct subscription table on its current public Marey pages. Official inference partner fal.ai lists pay-as-you-go prices for public Marey Realism endpoints; direct app or enterprise pricing should be confirmed before production.
$1.50 for 5 seconds; $3 for 10 seconds
Generate a new Marey video from a detailed text prompt.
$1.50 for 5 seconds; $3 for 10 seconds
Animate a supplied first-frame image with prompt and generation controls.
$2 per video
Transfer movement, composition, or a human performance from reference footage.
Confirm current terms
Direct creative-platform and production arrangements are not summarized in a stable public pricing table.
Pricing checked . Check current pricing at the source ↗
Assessment
Compare
The right alternative depends on the specific output, workflow, controls and budget your project requires.
Content Creator
Choose Runway Gen-4.5 for a broad commercial video platform with a mature creation and editing ecosystem.
Explore Runway Gen-4.5 →Content Creator
Choose LTX Studio for an end-to-end storytelling workspace that connects scripts, storyboards, shots, and generation.
Explore LTX Studio →Content Creator
Choose Google Flow when Veo-powered generation and Google's filmmaking workflow are the priority.
Explore Flow →Questions
Marey is a generative video model built for filmmakers, with text and image generation plus camera, pose, motion, trajectory, keyframe, reference, and extension controls.
Moonvalley says Marey was trained exclusively on licensed, high-resolution footage and not on scraped content or user submissions. Buyers should still review current contractual terms and clear all project-specific inputs and outputs.
Moonvalley's public product pages do not show a stable direct subscription table. On official partner fal.ai, reviewed text-to-video and image-to-video endpoints cost $1.50 for five seconds or $3 for ten seconds, while motion and pose transfer are listed at $2 per video.
Yes. Public Marey Realism workflows are available through fal.ai, which Moonvalley identifies as an inference partner. Moonvalley's own public API page currently invites developers to join a waitlist.
Moonvalley positions Marey as commercially safe, and fal.ai labels its Marey endpoints for commercial use. That does not remove the need to clear uploaded references, talent and likenesses, brands, music, scripts, and any contract-specific restrictions.
Use text-to-video for new concepts, image-to-video to preserve a first frame, Motion Transfer for movement and composition, Pose Transfer for human performance, and camera, trajectory, keyframe, or reference controls when a specific shot needs tighter direction.
Bottom line
Marey is most differentiated when a team cares about both production control and the provenance of model training data. It is a serious option for previsualization, advertising, and cinematic experiments, but teams should budget for multiple generations and treat licensed training as one part—not the entirety—of commercial clearance.
Visit Marey by Moonvalley website ↗
Genspark AI Docs - an agentic creator allowing users to generate and edit a variety of document times via natural language prompts.

LTXV - Lighttrick's open-source video model with 60-second outputs and real-time streaming

Veo 3 - Google's SOTA video generation model

Runway Aleph - A new “in-context” video model that edits and transforms existing footage through text prompts, handling tasks from generating new camera angles to removing objects and adjusting lighting.

Get access to all our AI courses, hundreds of real-world AI use cases, live expert-led workshops, an exclusive network of AI early adopters, and more.
Get unlimited access to all of our current & upcoming industry-specific AI courses for the duration of your subscription.
To keep up with the rapid pace of AI, our team publishes AI implementation guides daily. Our library contains 300+ practical use cases to automate real-world work.
Join weekly, live, interactive sessions with industry leaders who are at the forefront of AI for hands-on implementation guidance and exclusive insights.
Network with an exclusive community of AI-first professionals who are working smarter with AI. Learn how early adopters are using AI in their work and businesses.