Photo to Video AI is a browser-based workflow for turning a still image into a short video. A user uploads a JPG, PNG, or WebP image, enters a motion prompt or selects a preset, chooses an aspect ratio, and generates a clip that can be previewed and downloaded.
The frontend is built with Next.js App Router. Sanity is used to organize the structured product content and documentation around the application, including feature descriptions, example metadata, use cases, prompt guidance, FAQ entries, and localized material. This keeps editorial content separate from the upload and generation interface.
The application flow is intentionally small: image input, motion direction, generation state, preview, and output. Supporting multiple content formats and use cases without turning the page into a complex video editor is one of the main design constraints. The structured content in Sanity helps explain those controls consistently across landing pages and supporting guides.
The next step is to extend the Sanity content model with reusable demo assets, prompt examples, preset descriptions, tutorial entries, and localized sections. These structures can support additional portrait, product, landscape, and social-video examples while keeping the frontend components reusable.
