esc

TechieSA@TechieBySA

Seedance

PROMPT

Create an original square 1:1 composite sports-anime key-art illustration for two entirely fictional adult table-tennis finalists in an original indoor arena, designed as the exact opening frame for selective animation. Use polished cel-shaded character rendering, expressive hand-drawn linework, dynamic manga-inspired energy accents, and dramatic painted arena lighting while keeping faces, hands, rackets, and athletic anatomy coherent. Build two clean horizontal zones that share the same characters, uniforms, palette, and arena identity. In the upper 16:9 arena window, show the calm player in teal and cream and the energetic player in coral and navy facing across a small central table, with layered crowd depth and enough clear space for a rally. In the lower poster panel, show larger static illustrated portraits of the same two players in an opposing diagonal composition with painted energy accents and a small table motif. Keep the divider crisp and the whole square composition balanced. Preserve a clearly illustrated—not photorealistic—finish. Include no country names, flags, teams, logos, brands, public likenesses, copyrighted characters, or readable text.

Use the supplied generated square 1:1 composite image as the exact opening frame and preserve the full canvas without cropping, expanding, or reframing it. Animate only the upper arena panel for one continuous 15-second cinematic table-tennis final between the same two fictional adult players. Keep the lower poster panel perfectly static throughout—no parallax, shimmer, morphing, camera movement, or text changes below the divider. Inside the upper 16:9 window, preserve the players' faces, uniforms, colours, rackets, table, and arena layout; begin with a slow push toward the table, follow one fast but physically plausible rally with stable ball continuity, then ease slightly sideways as the coral-and-navy player returns the final shot and both players reset in frame. Keep every camera move and moving element clipped to the upper panel. Use believable footwork, cloth and crowd motion, controlled motion blur, bright arena ambience, and polished colour. No cuts, identity drift, extra limbs, flags, logos, public likenesses, dialogue, subtitles, watermarks, or unsafe contact.

Prompt guide · AI video

Animated Table Tennis Final — AI Video Prompt

A two-step FilmLune-optimized recipe creates a square split-layout sports-anime opening frame, then animates only its upper arena panel while keeping the lower poster fixed.

ModelSeedance 2.5
Use caseStoryboards, video & motion
StyleCinematic sports animation
CollectionAnimated table tennis finals

Why this example is useful

A two-step FilmLune-optimized recipe creates a square split-layout sports-anime opening frame, then animates only its upper arena panel while keeping the lower poster fixed. The square canvas contains an animated upper arena and a static lower poster. Keeping the same players and colours in both zones allows the lower key art to reinforce the rally without becoming a second moving scene.

How to adapt the method

Generate IMAGE 1 with GPT Image 2. After completion, explicitly continue to VIDEO 2 so FilmLune binds that exact private image revision and pre-fills the Seedance prompt. Opening VIDEO 2 directly leaves the reference slot empty. Inspect the divider across the entire clip, not just the opening frame. Ball motion, rackets and footwork belong above it; any drift or shimmer in the lower panel is a result to review, not selective-animation control guaranteed by the model.

How to use this prompt

1
This is an image-to-video recipe. Create the opening image first, then use that output as the input to the video step. Keep the image prompt and motion prompt separate.
2
Open the selected recipe in Studio with its model and starting settings. Check the available version, frame and resolution before generating; a size written in the source prompt is not an output setting or a guarantee.
3
Use the customization fields below to rewrite the brief: imageModel / videoModel / duration / canvas / motionRegion. Keep the composition and other constraints that make this example useful. Check the current credit quote before submitting.

What to check in your result

Watch the entire clip. Compare the main action, camera movement and scene continuity with the brief, and check for changing faces, distorted hands or unexpected cuts. A similar prompt can give a different result; refine the motion rather than assuming an exact copy.

Variables to customize

imageModel: GPT Image 2
videoModel: Seedance 2.5
duration: 15 seconds
canvas: square 1:1 composite
motionRegion: upper 16:9 arena panel; lower poster panel static

Source and attribution

This example is attributed to TechieSA @TechieBySA.

View the source on X

The work remains attributed to its public source; the link preserves access to its original context.

Report a rights or attribution issue

View all AI video examples

One-Take European Travel Diary

One-Take European Travel Diary

Wuxia Combat in a Lantern-Lit Inn

Wuxia Combat in a Lantern-Lit Inn

Seven Wonders Selfie Travel Hyperlapse

Seven Wonders Selfie Travel Hyperlapse

FPV Dive Through a Jungle Temple to a Golden Underground Sun

FPV Dive Through a Jungle Temple to a Golden Underground Sun