animated-image

Generate animated videos by providing a text prompt describing your concept. This Skill uses Google Gemini to create a clean, minimalist static image first, then animates it into a short video using Google Veo, requiring only an image prompt and optional animation prompt to produce both .png and .mp4 files.

Yes. This Skill automates visual concept creation by generating static images and animations from text descriptions, eliminating the need for complex design tools. It's ideal for rapid ideation, design previews, and storyboard-style animations for presentations or social media.

Describe your concept in a text prompt. The Skill generates a minimalist static image, then automatically animates it into motion graphics, producing both image and video outputs in seconds—perfect for quick design iterations and stakeholder previews without manual editing.

Yes. This Skill leverages Google's Gemini image model for static image generation and Google Veo for video animation. Both are integrated via the @google/genai dependency, handling image and animation generation end-to-end from your prompts.

The Skill automatically infers obvious motion from your generated image. You only need to provide an image prompt; animation inference occurs automatically, simplifying the workflow for users who want motion without detailed motion descriptions.

Outputs include a static .png image file, a .mp4 video file, and a one-sentence caption describing the result. All three are generated in a single execution, giving you both visual assets and descriptive metadata ready for use.