Cats in 2000s Sitcom Apartment Sketch

A four-shot sitcom parody staged in an early-2000s three-camera network style, with two clothed cats in an apartment living room trading punchlines about teaching a computer to make dancing humans. The look mimics 35mm film telecined to NTSC videotape, with flat high-key studio lighting, practical lamp halation, and a 4:3 broadcast frame. Locked-off cameras, hard cuts, and canned studio audience laughter carry the joke.

This clip could not be loaded — it may have been removed from X.
Shan | Ai @ShanBuildsAI ·
View on X ↗

Prompt

An early-2000s multi-camera network sitcom, shot on 35mm film with a four-camera Panavision setup before a live studio audience, Kodak Vision2 500T stock, telecined to NTSC videotape for broadcast. Fine 35mm grain, gentle halation blooming around the practical lamps, slight interlaced video softness, flat high-key television lighting with no shadows, warm saturated early-2000s colour timing, 4:3 frame. SET: A three-wall apartment living room. Beige couch with a chenille throw, warm practical table lamps, a lava lamp, a beaded curtain over the kitchen doorway, a DVD tower, an inflatable chair in the corner, a cluttered desk with a chunky beige CRT monitor and a boxy tower, burned CDs in paper sleeves, front door stage right. SUBJECTS — identical in every shot: Ginger tabby in an oversized grey zip-up hoodie over a striped orange rugby shirt and a puka shell necklace, sitting upright on a desk chair. Grey longhair cat standing upright in a burgundy velour tracksuit with white piping, chunky silver flip phone clipped to the waistband, holding a chipped mug. Camera locked off, no camera movement, both cats angled slightly toward camera, camera never crosses into the fourth wall. SHOT ONE — 0–6s: Locked-off wide two shot. The ginger tabby taps the keyboard with his front paws, face lit by the CRT. The front door swings open and the grey longhair walks in holding the mug. The studio audience applauds. He looks at the desk and asks: “What are you doing?” HARD CUT. SHOT TWO — 6–11s: Medium close-up of the ginger tabby. Without looking away from the screen, he keeps tapping and says: “I'm teaching the computer to make funny dancing humans.” Studio audience laughs. HARD CUT. SHOT THREE — 11–16s: Medium close-up of the grey longhair. He lowers the mug, pauses, then says completely flat: “We have a human.” Another beat. “He's in the kitchen.” Studio audience laughs. HARD CUT. SHOT FOUR — 16–20s: Close-up of the ginger tabby. He stops typing, slowly turns toward the beaded curtain and calls out: “Mark.” Off-screen, a man immediately starts dancing, feet thumping on the floorboards and the beaded curtain swaying. The cat keeps staring off-screen as the audience laughs and applauds. Hold. Audio: Paw taps on keyboard, CRT whine, mug on wood, opening door, entrance applause, studio laughter after each punchline, beads clacking and off-screen footsteps at the end. No music or score. Constraints: Keep both cats identical throughout. Real cats in real clothes sitting upright. No human characters visible on screen, no camera movement, no extra cuts, no modern flat-screen monitors, no smartphones, no flat digital-video lo
? How to use this prompt ▾
  1. Copy the prompt using the green "Copy prompt" button above.
  2. Open your model — launch Seedance 2.0 on its official interface.
  3. Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 4:3 and clip duration to 20s.

What makes this prompt work

Every insight below is verified against benchmark generation parameters, not asserted. How our prompt engineering benchmarks work →

CAMERA
"close-up" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "static/fixed", "wide shot", "medium shot".
LIGHTING
"practical lights, soft light" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"playful, nostalgic" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 20s, this clip is optimized for high temporal coherence and fluid, realistic motion physics.
MODEL
Seedance 2.0 (ByteDance) provides the underlying diffusion and motion architecture. Camera, lighting and duration cues transfer across models — what differs is how literally each model interprets motion.
PROMPT LANGUAGE
The prompt is written in English. This library keeps every prompt in its original language rather than translating it — the exact words are what was conditioned during generation.
Seedance 2.5 BytePlus Cloud Partner

Tell bigger stories with Seedance 2.5

Create AI videos up to 30 seconds long with richer image, video, and audio references. Ideal for complex ideas that need consistency and control.

Explore on BytePlus Official ByteDance Enterprise Cloud