Cat Sitcom VIDEO Breakdown (Prompts Included)

SCENE CONCEPT: the story hook must be instantly understandable in one frame: the woman is about to leave and is warning the cat not to invite anyone over.

COMPOSITION: Eye-level medium-wide master shot showing the apartment entry area, kitchen and the pink table area in one coherent frame. The woman is on the RIGHT or mid-right side of the frame near the apartment exit, turned partly toward the cat. The cat sits on the LEFT foreground at the tiny pink wooden table. Their eye lines must connect clearly.

WOMAN: A young woman in her mid-20s with fair skin, short dark-brown bob with blunt bangs, expressive blue eyes, subtle red lipstick, fitted white short-sleeve V-neck cropped T-shirt, relaxed high-waisted blue jeans and black platform shoes. She is clearly about to go out: one hand holds a small handbag, keys, or a light jacket, while the other hand is raised with one finger in a warning gesture toward the cat. Her body is angled toward the exit, but her head is turned back toward the cat. Her expression is firm, skeptical and slightly amused, like she is giving a final rule before leaving.

CAT: A fluffy gray Persian cat with realistic dense fur, rounded serious face, silver over-ear headphones, chunky gold chain, black graphic T-shirt and loose blue jeans. Keep believable feline anatomy and cat paws only. The cat sits upright at the tiny pink table like a normal roommate, with an open flip phone on the tabletop. The cat looks up-right toward the woman with a blank innocent expression, as if pretending he has absolutely no idea what she is talking about.

SETTING: Cozy colorful 1990s Manhattan-style apartment sitcom set. Warm wooden kitchen cabinets and open shelving, cream refrigerator covered with notes and magnets, purple-toned walls, patterned rug, cream sofa edge, standing mirror, old stereo, small household clutter and warm wooden floor. The apartment should feel compact, lived-in, cheerful and theatrical in a classic studio-sitcom way.

STORY CLARITY: The woman’s “I’m leaving” body language must be obvious through the handbag/keys and exit position. Her warning gesture toward the cat must visually communicate “no guests.” The cat’s open flip phone should subtly hint that he may use it the moment she leaves.

IMPORTANT: no extra people, no second cat, no text, no subtitle, no logo, no watermark, no black borders, no dark cinematic grading, no extra limbs, no human hands on the cat, no deformed paws, no duplicated props.

AI Generated Image②

Image Prompt③

Create a vertical 9:16 ultra-realistic live-action first-frame image for an original 1990s-style apartment sitcom. Warm bright multi-camera studio lighting, colorful slightly theatrical apartment set, soft retro television texture, realistic materials and expressive comedy staging.

STORY HOOK: The woman is clearly leaving the apartment and giving the cat one final warning not to invite anyone over. The cat has a flip phone nearby, subtly suggesting that he already has another plan.

WOMAN: A young woman around 24 with fair slightly sun-kissed skin, bright green eyes, soft natural makeup, peach lipstick and a playful expressive face. She has long honey-blonde hair tied into a high loose ponytail with soft volume at the crown, wispy face-framing strands and a scrunchie. No bob haircut, no dark hair.

She wears a fitted cherry-red short-sleeve cardigan with small cream buttons, a white camisole underneath, dark indigo high-waisted flare jeans, a slim black belt and cream platform sneakers. Add small gold hoop earrings and a compact brown shoulder bag.

She stands on the MID-RIGHT side close to the apartment doorway, clearly about to leave. One hand holds her shoulder bag and keys while the other hand points toward the cat in a playful but serious “behave yourself” gesture. Her body faces the exit but her head turns back left toward the cat. She looks directly at him with a skeptical “I know you” expression.

CAT: A plump black-and-white tuxedo cat with short plush fur, white muzzle, white chest and white front paws, vivid green eyes and an naturally dignified serious expression. Completely different from the previous long-haired gray cat.

The cat wears a tiny burgundy velvet bow tie, a cream knitted cardigan and dark olive miniature trousers. No headphones, no chain, no graphic T-shirt. Keep natural feline proportions, visible cat paws and realistic fur.

The cat sits upright on a blue-painted wooden chair at a small rectangular turquoise dining table in the LEFT foreground. An open silver flip phone is positioned very obviously beside his paw. He looks up-right toward the woman with a perfectly blank innocent face, as if wondering why she would ever suspect him.

SETTING: A colorful cozy 1990s Manhattan-style studio apartment. Warm wood kitchen cabinets, cream refrigerator covered with magnets, pale mauve and muted teal walls, framed prints, cream sofa, floral cushions, vintage patterned rug, wooden floor, small table lamp, old stereo, standing mirror and many charming everyday objects. The apartment feels lived-in and slightly theatrical, like a real classic sitcom soundstage.

COMPOSITION: Eye-level medium-wide master shot. The woman near the exit on the right, cat seated at the table on the left foreground. Both fully visible. Their eye lines connect naturally. The woman’s keys, handbag and exit position make it obvious she is going out, while the cat’s open flip phone visually foreshadows his secret plan.

No second cat yet. No extra people. No text, subtitles, logo or watermark. No human hands on the cat, no malformed paws, no duplicated phones or objects, no dark moody cinematic grading.

AI Generated Image③

Image Prompt④

Create a vertical 9:16 ultra-realistic live-action first-frame image for an original retro apartment sitcom scene. The image should look like the opening story frame of a 1990s American multi-camera studio sitcom: warm bright studio lighting, slightly soft retro television-broadcast texture, colorful cozy apartment decor, realistic skin, fur, knit fabric, laundry props and interior detail. It must feel like a real professionally filmed sitcom frame, not a modern cinematic commercial.

SCENE CONCEPT: the story hook must be instantly clear in a single frame. A young woman is about to leave and is specifically warning her cat not to put her favorite red sweater into the dryer.

COMPOSITION: Use an eye-level medium-wide master shot. The frame should clearly show both the apartment living area and a visible laundry nook or open laundry closet with a washer and dryer. On the RIGHT side of the frame, the woman stands beside a laundry basket or hamper near the washer-dryer area. On the LEFT foreground or mid-left, the cat sits like a normal roommate, looking up at her. Both characters must be clearly visible in the same shot, with strong eye-line connection and readable story staging.

WOMAN: A young woman in her mid-20s, fair skin, expressive eyes, natural makeup, casual sitcom-roommate styling. She is dressed in a fitted casual top, relaxed blue jeans and simple shoes. In one hand she holds up a beautiful bright-red knitted sweater, clearly presenting it as an important item. With the other hand she raises one index finger toward the cat in a warning gesture. Her body is angled toward the laundry area, but her head is turned back toward the cat. Her expression is firm, skeptical and slightly amused, like she is laying down one specific rule before leaving.

CAT: A fluffy house cat treated like an ordinary sitcom roommate. Keep realistic feline anatomy, natural cat paws only, expressive face, and a slightly innocent deadpan look. The cat may wear a cute retro outfit such as a knitted cardigan or vest with trousers, but must remain clearly feline. The cat is seated upright near the laundry basket, a small chair, or beside a table, looking up at the woman with a blank “I would never do that” expression. A flip phone or small household object may sit nearby to suggest the cat’s quirky roommate personality.

SETTING: A cozy cluttered 1990s Manhattan-style apartment sitcom set with warm wood floor, colorful lived-in decor, soft purple-toned walls, a cream sofa edge, standing mirror, old stereo, patterned rug and visible laundry area. The washer and dryer must be clearly readable somewhere in the shot, either stacked in an open closet or side-by-side in a small laundry nook. There should also be a laundry basket with clothes visible, reinforcing the laundry storyline.

STORY CLARITY: The red sweater must stand out clearly as the important object. The woman’s warning finger and stern-but-playful expression must instantly communicate “do not put this in the dryer.” The presence of the laundry machine must make the setup immediately understandable in one frame.

STYLE: Warm cheerful 1990s studio-sitcom atmosphere, fixed master-shot composition, clean readable blocking, no dark dramatic grading, no cinematic action framing.

IMPORTANT: no extra people, no extra cats, no text, no subtitles, no logo, no watermark, no black borders, no duplicated props, no extra limbs, no deformed paws, no human hands on the cat, no surreal distortion.

AI Generated Image④

Video Generation Screen

Step 2

Once your image is ready, move on to video generation. Select Video Generation, upload your finished image or pick it from your Creations library as source material. Choose image-to-video mode, then paste the provided prompt below.

Note: Add @your-image inside the prompt for image reference. You may pick any of these models: Seedance 2.5, Seedance 2.0, MiniMax H3 or Wan 3.0. Click Generate after confirming all settings.

Video Prompt-Version ① - Stealing Cake

IMPORTANT: Begin with dialogue immediately. Do not hold the uploaded frame silently. The viewer must understand “forbidden cake” within the first three seconds.

[0-1.5s] Begin exactly from the uploaded frame. The woman holds the strawberry cake beside the open refrigerator, raises her finger toward the cat and says immediately:

WOMAN: “This is for tonight. Don’t touch it.”

[1.5-3.2s] Quick cut to the orange cat. He looks up at her with a mildly offended, dignified expression and answers:

CAT: “I don’t even like cake.”

Audience laugh.

[3.2-5.5s] Wide kitchen shot. The woman gives him a skeptical look, places the cake carefully on the refrigerator shelf, closes the door and walks briskly out of the kitchen. Do not linger on her departure.

[5.5-7s] Cat close-up. The moment she disappears, he looks toward the refrigerator, waits half a beat and says quietly:

CAT: “That was a lie.”

Audience laugh. He immediately gets down from the chair.

[7-10s] Fast readable action. The cat hurries to the refrigerator, pulls the door open and carefully retrieves the strawberry cake. Keep the same cake design: round cream cake with clearly visible strawberries. He places it on the yellow table.

[10-13s] Medium shot. The cat produces a tiny cake knife or small serving utensil and studies the cake very seriously. He carefully cuts an absurdly thin slice, almost paper-thin, as if technically obeying the rule. He eats it.

Audience chuckle.

[13-17s] He looks at the cake. Looks toward the direction the woman left. Cuts another slightly larger piece. Eats it. Quick hard cut: another piece. Another quick cut: now a large section is missing. His movements get faster while his face remains completely serious. Audience laughter grows with each cut.

[17-20s] Wide table shot. Only a surprisingly small piece of cake remains. The cat suddenly realizes what he has done. His eyes widen slightly. He rotates the cake plate, trying to hide the missing side toward the wall. He steps back to inspect it. Obviously terrible.

[20-23s] Rapid sitcom montage. The cat tries to repair the cake using whatever is nearby: a slice of bread or sponge-like snack as filler, a little cream spread over the missing area, then one strawberry carefully placed on top. The result is visibly crooked, lopsided and much smaller than the original.

He proudly looks at it and says:

CAT: “Perfect.”

Big audience laugh.

[23-26s] The woman suddenly returns. She walks into the kitchen, opens the refrigerator and pauses because the cake is missing. She slowly turns toward the yellow table and sees the tiny badly reconstructed cake. Cut immediately to her reaction close-up.

[26-28s] She stares at the cat and asks:

WOMAN: “What happened to my cake?”

Audience laugh.

[28-30s] Cut to the cat sitting upright beside the ridiculous replacement cake. He calmly glances at the cake, then at her and answers:

CAT: “It lost weight.”

Huge final audience laugh. The woman stares at him in disbelief while the cat casually returns his attention to the flip phone. End immediately.

CAMERA AND EDITING: Use classic 1990s multi-camera sitcom grammar: eye-level locked master shots, medium dialogue coverage, character reaction close-ups and quick food inserts. Hard cuts only. Keep the pace energetic. Every shot must add information or comedy. Do not hold inactive characters. No long cinematic walks, no orbiting, no slow motion, no drone shots, no dramatic camera sweeps, no morphing or dissolve transitions.

CAKE CONTINUITY: The original cake must remain visually recognizable throughout: round cream-colored strawberry cake with strawberries on top and around the sides. Its size decreases progressively through visible eating. Do not magically replace it before the repair sequence. The final fake cake must clearly look like a clumsy attempt to recreate the original, not a completely new perfect cake.

AUDIO: Clear American English dialogue with accurate lip sync. Woman: expressive, playful young female voice. Cat: dry, sophisticated, slightly serious male voice. Use short audience laughter after “I don’t even like cake,” “That was a lie,” escalating cake-eating moments, “Perfect,” and especially “It lost weight.” No narration.

CONTINUITY: Preserve exactly one woman and one orange cat from the uploaded image. Exactly one strawberry cake and one burgundy flip phone. No duplicated food, no extra cats, no extra humans, no human hands on the cat, no deformed paws, no changing clothing, no floating objects, no subtitles, no logo, no watermark.

Video Prompt-Version ② - Don’t Touch My Shoes

Use the uploaded image as the absolute first-frame, character, wardrobe and apartment-layout reference. Create a 30-second vertical 9:16 ultra-realistic live-action comedy scene presented like an original 1990s American multi-camera apartment sitcom. Warm bright studio lighting, colorful cozy apartment set, slightly soft retro television texture, clean multi-camera cuts, expressive reaction shots, short audience laughter and clear spoken English dialogue.

IMPORTANT: THE FIRST 3 SECONDS MUST IMMEDIATELY ESTABLISH THE STORY. Do not hold a silent opening shot. Do not let the characters simply stare at each other. Dialogue begins almost immediately.

CHARACTER LOCK: Preserve the exact woman from the uploaded image: fair skin, short dark-brown bob with blunt bangs, white fitted V-neck cropped T-shirt, high-waisted loose blue jeans, black platform shoes. Preserve the exact fluffy gray Persian cat: round serious face, silver headphones, chunky gold chain, black graphic T-shirt, loose jeans, realistic cat paws and feline anatomy. The cat can speak naturally with subtle believable mouth movement.

APARTMENT LOCK: Preserve the uploaded kitchen and living-room geography: woman on the right beside the wooden kitchen counter, pink table on the left, cream refrigerator covered with notes and magnets, purple walls, cream sofa, standing mirror, old stereo, patterned rug and warm wooden floor.

COMEDY TONE: Everyone treats the talking, dressed cat as completely normal. Perform the dialogue like a real studio sitcom: quick delivery, deliberate reaction pauses, audience laughter after punchlines. The humor must come from setup → secret behavior → discovery → final comeback.

[0-1.3s] START EXACTLY FROM THE UPLOADED IMAGE. The woman is already looking down-left at the cat. Without waiting, she speaks firmly but casually:

WOMAN: “I’m going out.”

She immediately turns slightly away from the counter toward him. Cut quickly to a tighter medium shot.

[1.3-3.2s] The woman leans slightly toward the cat and points once toward him, half-serious and half-teasing:

WOMAN: “And stay out of my closet.”

Immediately cut to the cat. He barely looks up from the open flip phone and answers in a calm deadpan voice:

CAT: “Relax.”

Short audience laugh.

This exchange must finish within roughly the first three seconds. Fast, clear sitcom timing.

[3.2-5.5s] Wide kitchen shot. The woman gives him one suspicious final look, grabs her things and walks briskly out of the apartment area. Do not linger on her walking. The instant she disappears, cut back to the cat.

[5.5-7s] Medium close-up of the cat. He watches the direction she left, waits half a beat, then quietly says:

CAT: “Finally.”

Audience laugh. He immediately jumps down from the chair.

[7-10.5s] Fast but readable sitcom action. The cat hurries toward the cream sofa, reaches behind it and pulls out a cardboard box he has clearly hidden earlier. No long walking sequence. He opens the box immediately.

[10.5-12s] Clean insert shot inside the cardboard box: one pair of glossy bright-red high heels. Audience laughter rises immediately at the reveal.

[12-14s] Medium shot of the cat. His serious face suddenly becomes fascinated. He lifts the two shoes and softly says:

CAT: “Hello, gorgeous.”

Audience laugh.

[14-18.5s] Cut directly to a full-body shot beside the standing mirror. The cat is now wearing the same red heels. He carefully walks two or three tiny steps in front of the mirror, nearly loses balance once, catches himself, then admires his reflection. Keep the physical comedy quick and readable.

[18.5-20s] Close-up of the cat looking into the mirror. He straightens his gold chain and gives himself an extremely confident expression. Audience chuckle.

[20-21s] Very quick insert: one gray paw presses PLAY once on the old stereo.

[21-25s] Upbeat retro dance music begins immediately. Full-body mirror shot. The cat performs a funny but surprisingly confident dance in the red heels: small hip sways, shoulder bounces, two tiny steps, a runway turn and one dramatic pose. Keep the cat’s movement physically believable, not cartoonish. Mirror reflection matches perfectly.

[25-27s] The apartment door suddenly opens. Hard sitcom cut to the woman entering. She takes one step inside and FREEZES when she sees the cat. Cut immediately to her close-up. Wide eyes, mouth slightly open:

WOMAN: “Are those my shoes?”

Big audience laugh.

[27-29s] Cut to the cat. Music lowers slightly but does not stop. He pauses for half a beat, looks at her completely seriously and answers:

CAT: “They were lonely.”

Huge audience laugh.

[29-30s] Without waiting for her response, the cat resumes dancing and hits one ridiculously confident final pose in the red heels. The woman remains stunned in the background. Big final audience laugh. End immediately on the punchline.

CAMERA AND EDITING: Use energetic classic sitcom editing, not a slow cinematic style. Within the first three seconds use at least two shot sizes: opening master/medium shot → woman tighter shot → cat reaction. After that, alternate locked wide shots, medium shots, reaction close-ups and quick prop inserts. Every shot must either deliver dialogue, reveal new information or advance the joke. Never hold an inactive shot for more than about one second.

AUDIO: Clear natural English dialogue with accurate lip sync. Woman has a lively young American voice. Cat has a dry, slightly low, unimpressed male voice. Short studio-audience laughter after “Relax,” “Finally,” the shoe reveal, “Hello, gorgeous,” the woman’s discovery and especially “They were lonely.” Retro upbeat music only begins when the stereo is activated.

CONTINUITY: Exactly one woman, one gray Persian cat, one flip phone, one cardboard box and one pair of glossy red heels. No extra characters, no duplicated shoes, no human hands on the cat, no extra limbs, no deformed paws, no mirror mismatch, no sudden costume changes, no subtitles, no watermark, no logo.

Video Prompt-Version ③ - No Guests Allowed