tomoviee-image-to-video_skill

This skill turns a static image into an engaging video with motion and camera movements based on your text prompt.
  • Python

2.5k

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill tomoviee-image-to-video

  • _meta.json308 B
  • SKILL.md1.9 KB

Overview

This skill generates videos from a single image plus a text prompt, animating static images with motion and camera movements. It exposes an API-style client to create tasks, poll progress, and retrieve rendered video URLs. Use it to convert photos or illustrations into short animated clips with configurable resolution and aspect ratio. The workflow is asynchronous and designed for batch or programmatic use.

How this skill works

You send an image URL and a motion-oriented prompt describing camera moves and scene animation; the client returns a task_id for asynchronous processing. Poll the task status until completion, then parse the returned JSON to obtain output video URLs and metadata. Optional parameters include resolution, aspect_ratio, and camera_move_index to control framing and predefined camera behaviors. Status codes indicate queueing, processing, success, failure, cancellation, or timeout.

When to use it

  • Turn product photos or portraits into short promotional videos with subtle motion.
  • Animate landscape or architecture images with camera pans and parallax effects.
  • Create social media assets in 720p or 1080p with specific aspect ratios like 9:16 for Reels.
  • Prototype animated scene concepts from concept art or storyboards.
  • Automate batch image-to-video conversion for content pipelines.

Best practices

  • Provide a clear, concise motion prompt (e.g., 'camera slowly panning right, leaves rustling') to get predictable animations.
  • Use high-resolution source images (JPG/PNG/WEBP) under 200 MB to preserve detail in the output.
  • Select aspect_ratio and resolution that match your target platform before rendering.
  • Test different camera_move_index values to reuse predefined camera behaviors and find the best motion.
  • Implement polling with exponential backoff and handle all status codes (including failures and timeouts).

Example use cases

  • Create a 15–30 second product showcase by animating a product photo with slow zoom and rotation.
  • Generate a vertical 9:16 clip from a landscape photo for mobile storytelling.
  • Batch-convert a set of event photos into short highlight videos for a recap montage.
  • Animate character portraits with subtle head turns and simulated depth for visual novels.

FAQ

Supported image formats include JPG/JPEG, PNG, and WEBP. Individual images must be under 200 MB.

How do I know when a task is finished?

Poll the provided task_id. Status code 3 indicates success and that output URLs are ready; other codes indicate queued, processing, failure, cancellation, or timeout.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational