Available now

Marey Realism 1.5: text to video

By Moonvalley

Moonvalley's Marey makes 5 or 10 second clips from text or a first frame, and can move the motion or poses of a video you have onto a new scene.

Model ID
Maker
Moonvalley

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

Additional settings

The dimensions of the generated video in width x height format.

Negative prompt used to guide the model away from undesirable features.

Seed for random number generation. Use -1 for random seed each run.

Controls how strongly the generation is guided by the prompt (0-20). Higher values follow the prompt more closely.

Estimated total · 5s$2.38

You sign up first. Your settings are kept.

About this model

Overview

Marey Realism 1.5 renders at 1920x1080, square 1152x1152, or 1536x1152 and 1152x1536; the image mode adds a vertical 1080x1920. Moonvalley says Marey is trained on licensed data.

Motion transfer takes the movement and pacing of your control video and applies it to the scene in your prompt. Pose transfer follows the body poses in your video. Both can start from a first frame image and take a reference image.

What you can build

  • Live-action style b-roll for ads and films
  • A camera move from your own footage reused in a new setting
  • An actor's performance carried over to a different character
  • Square and near-square clips for social posts and presentations

Prompting tips

  • Write the prompt like a shot description: lens feel, light, subject and action.
  • The built-in negative prompt already blocks scene cuts and game-like looks; edit it rather than clearing it.
  • For pose transfer, use a control video where the whole body stays visible and unblocked.
  • Keep the seed when you like a result and want to change only one detail.

What to check

Review motion continuity and compare any transferred movement with the control video.

Inputs

  • Prompt (required): The prompt to generate a video from.
  • Dimensions (optional): The dimensions of the generated video in width x height format. Options: 1920x1080, 1152x1152, 1536x1152, 1152x1536.
  • Duration (optional): The duration of the generated video. Options: 5s, 10s.
  • Negative Prompt (optional): Negative prompt used to guide the model away from undesirable features.
  • Seed (optional): Seed for random number generation. Use -1 for random seed each run.
  • Guidance Scale (optional): Controls how strongly the generation is guided by the prompt (0-20). Higher values follow the prompt more closely.

Output and limits

  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 5s: $2.38 / request
  • 10s: $4.76 / request