Notice: GPT Image 2.6 Flare and Sunburst are newly launched with a limited-time 20% off, try it now
HiAPI
21:9 电影感 Hero 图:左侧柔光留白,右侧半透明胶片带与玻璃浮框延展,象牙暖底配水鸭蓝、腮红与长春花蓝渐变,muse-video-1.0 以发光蚀刻字融入胶片带。

Meta

Muse Video 1.0

muse-video-1.0/image-to-video

A video generation model launched by Meta Superintelligence Labs, supporting text-to-video and image-to-video. Each video is a fixed 10 seconds at 720p with built-in audio; image-to-video can use 1 to 9 reference images to guide the visuals, making it suitable for visualizing social media assets and storyboard concepts.

Try muse-video-1.0/image-to-video

Input

Output

video
Fill in the parameters and run — results show up here.

Pricing

muse-video-1.0/image-to-video per video

Unit Price $0.0336

Positioning Overview

This model accepts images and text prompts and outputs a fixed 10-second, 720p video with its own audio. Users can upload 1 to 9 reference images to guide the visuals and use prompts to describe subject motion and camera movement; it supports automatically following the aspect ratio of the reference images or manually specifying the frame size. It is suitable for developers and creators who need to quickly turn static concepts, product images, or storyboard drafts into video clips.

Core Highlights

  • Multi-image reference visual guidance — supports passing in 1 to 9 reference images at once to provide visual grounding for the scene, subject, or style.
  • Automatic or manual frame size specification — by default it automatically follows the aspect ratio of the reference images, or you can select an output frame size from seven common ratios.
  • Prompts describe motion and camera — use a prompt of up to 5000 characters to explain how the subject moves, how the camera moves, and the desired audio.

Capability Description

Image-reference video generation: pass in 1 to 9 reference images along with a prompt to generate a video clip with subject motion and camera movement; the reference images are used to guide the visuals and are not guaranteed to become a pixel-identical first frame.

Motion and camera description: the prompt can be up to 5000 characters and is used to describe how the subject in the reference images moves, the direction of camera movement, and the desired visual atmosphere.

Aspect ratio control: aspect_ratio can be auto, 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, or 2:3; when auto is selected, the output ratio follows the reference images, or you can manually specify the frame size.

Use Cases

  • Creators turn concept art into motion clips — upload concept design images and describe the action and camera to get motion footage that can be used directly in short films or social content.
  • Generate showcase videos from product images — use product images as references, describe orbit or dolly camera moves, and generate video clips for e-commerce pages or promotional materials.
  • Dynamic previews of storyboard sketches — use storyboard sketches as reference images, fill in the motion rhythm with prompts, and quickly get dynamic previews for pitches or internal reviews.

Limitations and Selection Advice

aspect_ratio accepts only one enum value per request and cannot output multiple frame sizes at the same time. Reference images are passed in via URLs and must use accessible http or https links, with a maximum of 9 per request. Reference images guide the visuals and are not guaranteed to become a pixel-identical first frame, nor are characters or scenes guaranteed to be absolutely consistent. The duration is fixed at 10 seconds and the resolution is fixed at 720p and cannot be adjusted. Requests with an empty prompt or a prompt containing only whitespace cannot be submitted.

  • New model New model: Muse Video 1.0 Image-to-Video
  • New model New model: Muse Video 1.0 Text-to-Video

Frequently asked questions

View all FAQs →
  • How long a video can this model generate?

    Each clip is fixed at 10 seconds. The duration is not adjustable; writing "longer duration" in the prompt will not take effect. If you need longer content, generate it in 10-second segments and stitch them together yourself.

  • Can the output resolution and aspect ratio be changed?

    The resolution is fixed at 720p and cannot be adjusted. Specify the aspect ratio with aspect_ratio: for image-to-video, the options are auto, 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, with the default being auto (which follows the aspect ratio of the reference image); for text-to-video, the latter 7 ratios are available, with the default being 16:9.

  • How many reference images can I upload at most?

    1 to 9 images, passed in as http or https links. Reference images are used to guide the visuals and are not guaranteed to become a pixel-identical first frame; if you want a particular image to dominate the composition, point to it explicitly in the prompt (for example, "use the person in the first image as the main subject"), and the remaining images will only supplement the style or elements.

  • How should I write the prompt so the image moves correctly?

    Write in the four-part order of “how the subject corresponds to the reference image → subject action → camera movement → sound,” with one specific sentence per part. For example, first write “Use the red sports car in image 1 as the subject,” then write “the wheels turn and the body slowly moves forward,” then write “the camera follows from a low side angle,” and finally write “low engine hum and tire-screeching sounds.” Put camera movement in its own sentence; do not mix it with subject action in the same sentence.

Related Models

View all models →

Same Type