Image & Video

An end-to-end video skill: plan, storyboard, render, caption, voice, QA and deliver a finished video entirely on your machine.

Turns scripts and ideas into dramaturgically sound prompts, storyboards and audits for AI video models like Seedance, Kling and Veo.

Turns an album's concept into a visual direction and writes cover-art prompts in the exact syntax of your chosen AI image tool.

Turn any YouTube link, podcast, or local media file into a transcript with subtitles, summary, chapters, and on-screen text.

An AI editing partner that catalogues camera and drone footage, rebuilds the trip's story, and edits scene-by-scene inside the editor you already use.

Give it a platform and an account ID/URL, and it pulls the channel's recent posts from Douyin, Kuaishou, Bilibili or YouTube, resolves direct download links, and can batch-download them.

Generates paste-ready, 5-stage cinematic video prompts for Seedance, Sora, Kling, Veo and Jimeng.

Renders a reel-ready 3D map animation where a coloured route draws itself from A to B with a bouncing pin and a counting-down ETA card.

Generates a calm black-and-white line-art reel where hairline steps rise and a white dot hops to the top.

Turns a handful of numbers into a minimal line-graph video with a counting-up number, ready for reels.

Turns a book title, pen name and genre into a structured cover prompt, then optionally renders the cover and exports it at the platform's exact upload size.

Turns documents and text into narrated audio or a two-host podcast using the ElevenLabs TTS API.

Generate Chinese/Japanese speech with StepFun's contextual TTS, controlling emotion via natural-language instructions and inline () prosody cues.

Transcribes the finished video's own audio and burns word-timed captions into vertical video ads.

Generate a single photoreal or designed image with OpenAI gpt-image-1/gpt-image-2 through fal.ai, with optional reference-image editing.

Turns a verbatim transcript into clean, readable burned-in subtitles with strict line, timing and cleanup rules, ready for DaVinci Resolve import.

Builds an Apple-keynote-style Mac product launch video entirely in code — no screen recording, no After Effects.

Turns a newsletter or blog cover into a seamless 896x640 looping GIF (180 frames at 20fps) where only one named element moves.

Builds a 30–45 second product launch video as a single seekable HTML file using your real brand colours and product screens, then exports it to MP4.

Takes an existing image ad and rebuilds it at every ratio you need — recomposed, not cropped.