Picture-in-Picture Focus L02
0.0s
Previews are illustrative demonstrations of the technique — not your footage. Your real edit is produced later by Claude Code.
L02 · Layouts · intermediate · 3–120s
The source media fills the frame while the speaker sits in a rounded window in one corner that glides to another corner when detail appears beneath it.
The evidence — a recording, demo or B-roll — becomes the main picture, and the speaker shrinks into a floating picture-in-picture window with a border and soft shadow. The window is movable: it can glide to another corner whenever important content would be hidden underneath. The audience keeps the human connection while giving the detail the space it needs.
Try the parameters
Glide the window to another corner when important content appears under it.
Best used for
- — Software tutorials
- — Website and app walkthroughs
- — Commentary over B-roll
- — Live-coding clips
Assets
- ● Source video required
- ○ Screen recording optional
- ○ B-roll footage optional
- ○ Second shot optional
Pairs well with
If assets are missing
Without a separate source (screen recording / B-roll), ask for one; do not pip the speaker over a duplicate of their own shot. If no clean corner exists, shrink the window to 24% width rather than covering essential content.
Accessibility
Keep the speaker's face ≥ 18% of frame width for lip-reading; avoid moving the window while the viewer needs to read the main picture.
Individual prompt
updates with the parameters above# CES style instruction — L02 Picture-in-Picture Focus You are an experienced motion designer and video editor working in Claude Code. Apply the **L02 Picture-in-Picture Focus** technique to the supplied footage as specified below. **B. Project configuration:** 1080×1920, 9:16, 30 fps · Source video: not provided — ask the user for the path before starting · Video language (on-screen text & captions): English **Layouts** — The evidence — a recording, demo or B-roll — becomes the main picture, and the speaker shrinks into a floating picture-in-picture window with a border and soft shadow. The window is movable: it can glide to another corner whenever important content would be hidden underneath. The audience keeps the human connection while giving the detail the space it needs. ### L02 Picture-in-Picture Focus - **When:** ≈ 00:00.00 → 00:15.00 (≈ derived — adjust to the nearest natural beat in the footage) - **Layer / track:** V1 (main picture) - **What it does:** The source media fills the frame while the speaker sits in a rounded window in one corner that glides to another corner when detail appears beneath it. - **Parameters:** PiP corner: Bottom right; PiP width: 34%; Window shape: Rounded rectangle; Inside the window: Speaker (source media fills the frame); Move away from detail: on; Border colour: #F4F2EB; Edge margin: 4%; Easing: Spring (physical) - **Steps:** 1. Between from 00:00.00 to 00:15.00, fill the 1080×1920 frame with the supplied source media (screen recording / B-roll) and place the speaker in a picture-in-picture window. Scale every source uniformly (object-fit: cover for crops, contain for fits) — never stretch footage, screenshots or recordings to a region's aspect ratio. 2. Window: 367×459px (34% of frame width, 4:5), corner radius 29px, 0.5% #F4F2EB border, shadow 0 1.5% 4% black at 45%. Crop the speaker so the face fills the upper 60% of the window. 3. Initial position: bottom right corner, inset 4% from the side edges and kept clear of platform UI (on 9:16, stay above the bottom 18% and left of the right 12% action rail). 4. Entrance: scale the window from 0.6 → 1.0 with opacity 0 → 1 over 11 frames using a physical spring (Remotion spring(): damping ≈ 12, stiffness ≈ 180, mass 1); exit with the reverse. 5. Movement: inspect the main picture for important content (cursor, highlighted UI, text being discussed) under the window. When it would be covered, glide the window to the nearest free corner over 14 frames with a physical spring (Remotion spring(): damping ≈ 12, stiffness ≈ 180, mass 1); at most one move every 2 seconds. List the move timecodes in your report. 6. Implement in Remotion with an <AbsoluteFill> main layer and a positioned window container (overflow hidden, borderRadius) whose left/top are interpolated between corner anchors; or in FFmpeg with scale + overlay=x:y using expressions for the move. - **Assets:** Source video (⚠ MISSING) · optional: Screen recording, B-roll footage, Second shot - **Fallback:** Without a separate source (screen recording / B-roll), ask for one; do not pip the speaker over a duplicate of their own shot. If no clean corner exists, shrink the window to 24% width rather than covering essential content. **G. Asset integrity and restrictions:** - Do not create or present invented testimonials, comments, quotes, reviews or endorsements. - Do not fabricate numbers, metrics, charts or results. Data visualisations use only the supplied data. - Do not create fake screenshots or UI and present them as real. Illustrative graphics must be clearly illustrative. - Do not attempt unsupported 3D reconstructions or perfect subject separation without a mask; use the documented 2D fallbacks instead. **I. Quality verification:** - Check output dimensions and aspect ratio with ffprobe — they must match the configuration exactly. - Check the output frame rate and that the duration is within ±0.5 s of the target. - Check audio/video synchronisation at the start, middle and end (lip-sync and SFX hits within 1 frame). - Inspect frames at every beat boundary for text clipping, overflow and safe-zone violations. - Confirm the output file exists and plays — never claim a render is complete without an actual output file. - Report any missing asset or unimplemented effect explicitly.
More layouts styles
Use a layout when two things must be seen at once. Only one full-frame layout can be active at a time.
- L01Vertical Split ScreenThe frame divides into two regions — speaker in one, a screen recording or second shot in the other — split by a divider at an adjustable ratio.
- L03Triple StackThree media bands stack vertically and the focal band grows to take most of the frame while the other two shrink and dim, shifting with the script.
- L04Floating Device FrameA screen recording plays inside a polished phone, tablet or browser mockup that floats in with a gentle 3D tilt over a soft background.
- L05Editorial SidebarA clean text panel slides in from one side while the speaker re-centres in the remaining frame, then fills with a heading and numbered notes.
- L06Center SpotlightThe shot contracts into a sharp central frame with a thin accent ring while the surrounding area becomes a blurred, darkened copy carrying context labels.
- L07Grid ConversationSpeakers or references populate a 2×2 (or 1+2) grid tile by tile, and a highlight moves to whoever is currently talking.
- L08Cinematic LetterboxBlack bars close in from top and bottom to a true 2.39:1, 2:1 or 1.85:1 band, cropping (never stretching) the shot into a cinematic frame.
- L09Collage CanvasPhotos, a speaker cut-out, a screenshot and a note card fly onto a paper canvas and settle at slight angles around a bold headline.
- L10Adaptive Proof PanelWhen evidence appears the speaker's shot shrinks into a band and a proof panel takes the rest, resizing as more evidence arrives, then hands the frame back.