Я не буду
это делать.

FORMAT: 9:16 vertical photorealistic cinematic video.

Create ONE coherent continuous video.

There is ONLY ONE video reference: @Video1.
Do not search for or expect a second video reference.

The opening is a NEW comedic story described below.
The final part reproduces the FULL ORIGINAL FINAL DANCE from @Video1.

VIDEO = final dance motion and timing.
IMAGES = identities, clothing, appearance and visual continuity.

────────────────────
REFERENCE ROLES
────────────────────

@Video1 is the MAIN AND ONLY VIDEO REFERENCE.

It controls:

— the heroine’s final central position
— the final crowd formation
— the FULL ORIGINAL FINAL DANCE
— its complete original duration
— choreography and timing
— differences between rows and performers
— camera behavior during the final dance
— the original ending

DO NOT copy the original opening actions from @Video1.
Replace that opening with the NEW STORY below.

Approximately 0:00–0:15 = NEW STORY.
Approximately 0:15–0:20 = heroine quickly reaches her central position.
From approximately 0:20 onward = FULL ORIGINAL FINAL DANCE from @Video1.

Do not shorten, compress, skip, extend or redesign the final dance.
The choreography already exists in @Video1.

────────────────────
IMAGE REFERENCES — EXACT UPLOAD ORDER
────────────────────

@Image1 = MAIN HEROINE CLOSE-UP.

Use @Image1 for her recognizable face, red floral headscarf,
gold earrings, jewelry, upper part of her red embroidered dress
and the appearance of the opening close-up.

@Image2 = OPENING STAIRCASE AND REAR VIEW.

Use @Image2 for the same outdoor staircase,
the heroine standing near the camera with her back to the group,
the group ahead of her and the warm cinematic atmosphere.

This image establishes the location and spatial relationship.
It does NOT replace the new face-to-camera opening.

@Image3 = FINAL FASHION GROUP.

Use @Image3 for the exact appearance of the colorful fashion people,
their clothing, distinctive hats and silhouettes,
the heroine’s eventual central position,
and the elderly woman in yellow standing LOWER,
on the step in front of the heroine.

Keep the elderly woman on that lower step.
Do not move her upward or into the heroine’s position.

@Image4 = LITTLE GIRL WITH TEDDY BEARS.

Use @Image4 for the little girl’s appearance,
cream outfit, teddy-bear print on her T-shirt,
bear-face slippers, suited teddy bears
and their arrangement on the outdoor staircase.

@Image5 = LITTLE GIRL FACE.

Use @Image5 to keep the girl’s face recognizable
when she says “Будешь.”

@Image6 = MAIN HEROINE FULL-BODY APPEARANCE.

Use @Image6 for her natural body proportions,
the complete long red embroidered dress,
its length, silhouette, sleeves and floral pattern
during her walk and the final group scene.

@Image1 has priority for the heroine’s face and close-up.
@Image6 has priority for her body proportions and complete outfit.

Both images depict the SAME heroine.
Keep her face and body consistent between close and wide shots.

Photographs do NOT provide choreography.
@Video1 provides the final dance motion.

────────────────────
MAIN HEROINE — IDENTITY AND OUTFIT
────────────────────

The heroine wears the SAME outfit throughout:

— long deep-red Russian-style embroidered dress
  with white floral ornament
— matching red floral headscarf
  wrapped around her head and neck
— ornate gold earrings
— layered gold and red jewelry

Preserve her recognizable adult face
and natural head-to-body proportions.

Do not enlarge her head.
Do not change her face, headscarf, jewelry or dress.
Do not give her sunglasses.
Do not replace her outfit with a pink coat or green clothing.

There is only ONE main heroine.

The woman speaking close to the camera,
the woman walking toward the group
and the woman standing in its center
are the SAME person.

────────────────────
ONE CONNECTED ENVIRONMENT
────────────────────

All events happen on and beside the SAME outdoor staircase.

The girl and teddy bears are physically nearby,
just outside the heroine’s initial field of view.

The main fashion crowd is also nearby.

The camera discovers the girl and teddy bears
by turning toward them, then returns to the heroine.

The heroine then moves toward the nearby fashion crowd.

No unrelated location.
No teleporting.
No disconnected inserted scene.

Keep warm outdoor cinematic light,
natural skin and fabric texture,
realistic depth and live-action photographic quality.

────────────────────
OPENING OVERRIDE — NO SMOKING
────────────────────

Completely remove the original smoking behavior
from the opening of @Video1.

The heroine does NOT smoke.

No cigarette, smoke, vapor, smoking gesture
or cigarette near her hands or mouth.

────────────────────
SCENE 1 — APPROXIMATELY 0:00–0:04
────────────────────

Begin close to the MAIN HEROINE,
facing her as in @Image1.

Her face and eyes are sharply in focus.
The colorful fashion group is visible
softly out of focus behind her.

She looks directly into the camera,
slightly irritated, stubborn and resistant.

Her expression is natural and comedic,
not angry or aggressive.

She clearly says in RUSSIAN:

“Я не буду это делать.”

Generate natural Russian female speech
with lip movements matching the exact sentence.

She does not dance.
She does not make complicated gestures.
She does not touch her headscarf or hair.
She does not hold a telephone.

After the line, she faces the camera
for only a brief moment.

────────────────────
SCENE 2 — APPROXIMATELY 0:04–0:08
────────────────────

The heroine notices movement on her RIGHT.

First her eyes move RIGHT.
Then she quickly turns her head RIGHT.

Her expression changes naturally:

resistance → curiosity → surprise.

At the same moment, the CAMERA smoothly pans RIGHT
following her gaze.

One continuous camera movement.
No hard montage cut.

The camera reveals the LITTLE GIRL
and suited TEDDY BEARS from @Image4 and @Image5
on the nearby staircase.

They are already dancing together.

There is NO second dance video reference.

Create a SHORT, SIMPLE, FUNNY RHYTHMIC DANCE
lasting approximately 3 seconds.

The girl and teddy bears remain in their group formation.
They make simple coordinated upper-body,
arm and paw movements, with small rhythmic bends and rises.

They stay approximately in place.

No complicated choreography.
No running, wandering or chaotic spinning.
Do not add or remove teddy bears.
The teddy bears remain teddy bears.

While the short dance continues,
the girl looks confidently toward the heroine / camera
and says exactly ONE WORD in RUSSIAN:

“Будешь.”

Generate natural child speech
and lip movement matching that word.

Her delivery is short, calm, confident
and slightly funny.

No other dialogue from the girl.

────────────────────
SCENE 3 — APPROXIMATELY 0:08–0:10
────────────────────

Immediately after “Будешь,”
the CAMERA quickly pans back to the SAME heroine.

Her face is clearly visible.

She silently reacts in shock.

Her expression communicates “Что?!”
but she does NOT say it aloud.

Her eyes widen slightly.
She looks confused and stunned.

Keep this reaction short.
No long pause or additional dialogue.

────────────────────
SCENE 4 — APPROXIMATELY 0:10–0:15
────────────────────

Someone from the nearby MAIN FASHION GROUP
briefly enters from just outside the frame.

That person quickly turns the heroine toward the group
and gives her a light, playful guiding push.

The action is quick, comedic and harmless,
never violent.

The heroine does not want to go.
She slightly resists being redirected.

While being turned and guided,
she clearly says in RUSSIAN:

“Да не хочу я там стоять!”

Generate natural Russian female speech
with lip movements matching the exact sentence.

She is irritated and confused,
but the scene remains comedic.

She is NOT smiling yet.
She is NOT excited to participate.

────────────────────
SCENE 5 — APPROXIMATELY 0:15–0:20
────────────────────

The heroine is quickly guided
toward the MAIN FASHION CROWD.

Reconnect the camera and character positions
with the final formation required by @Video1
and visually shown in @Image3.

Do not make the approach slow.
Do not replay a long walk from the opening of @Video1.

She moves DIRECTLY to her final central position.

No wandering.
No extra steps, dialogue, interactions or scenes.

She reaches the correct position.
She stops.
She turns toward the camera.

She is still reluctant and bewildered.

The elderly woman in yellow remains
on the LOWER step in front of her,
as shown in @Image3.

DO NOT make the heroine smile
before the final dance begins.

────────────────────
CRITICAL DANCE TRANSITION
────────────────────

The MAIN FASHION CROWD must NOT begin
the final dance while the heroine is walking.

Wait until ALL THREE conditions are complete:

1. She reaches her central position.
2. She stops.
3. She turns toward the camera.

ONLY THEN begin the ORIGINAL FINAL DANCE from @Video1.

The sudden start should feel funny
because she has just reluctantly taken her place.

────────────────────
FULL ORIGINAL FINAL DANCE
────────────────────

From this moment, @Video1 is the
ABSOLUTE SOURCE OF DANCE MOTION.

Reproduce the FULL ORIGINAL FINAL DANCE
as closely as possible.

Do NOT invent, reinterpret, simplify,
shorten, compress, extend or replace the choreography.

Preserve:

— complete original dance duration
— original movement sequence
— original rhythm and timing
— original performer positions
— original crowd formation
— original row structure and spacing
— different movements of different rows
— phase differences between performers
— original camera behavior
— original camera framing progression
— original ending

Do not turn it into generic synchronized dancing.
Do not add a pause or freeze at the end.

Compose the action within the 9:16 vertical frame
while following the original final camera behavior
as closely as possible.

────────────────────
FASHION CROWD — APPEARANCE AND LIFE
────────────────────

Replace the surrounding original performers visually
with the same colorful fashion characters
from @Image2 and @Image3.

Images control their appearance.
@Video1 controls their positions,
movement, choreography, timing and formation.

Keep the same recognizable people,
clothes, hats and accessories.

Keep the elderly woman in the yellow coat,
turquoise glasses, teal skirt and red boots
on her LOWER step.

Do not swap people’s positions.
Do not flatten the rows.
Do not duplicate or remove people.
Do not add extra background rows.
Do not expand the crowd during camera movement.

The group consists of living people,
not an animated static photograph.

Before the final dance, allow subtle,
individual human behavior:

— natural blinking and breathing
— tiny facial changes
— believable posture
— natural clothing movement

As the heroine approaches,
a few people briefly notice her.

One may glance toward her.
Another may show a slight closed-mouth smile.
Another remains serious.

Do not make everyone turn or react together.

These small reactions must not alter
their places or the dance starting time.

During the final dance,
every fashion character follows
the corresponding performer’s motion from @Video1.

Their faces remain alive with subtle,
varied expressions and natural blinking.

Do not add new gestures
or choreography for these expressions.

────────────────────
MAIN HEROINE — EMOTIONAL CHANGE
────────────────────

The SAME heroine remains clearly visible
in her central position throughout the final dance.

She does not disappear, duplicate,
change identity or leave the group.

At the EXACT MOMENT the group suddenly starts dancing,
she is genuinely startled.

Her FIRST reaction is fear and surprise,
NOT a smile:

— eyes widen
— slight physical recoil
— quick looks at people beside her
— confusion and disbelief

She may briefly lift her hands in surprise,
but must not hide her face for long.

She does not run away.
She does not perform an invented solo dance.

AS THE ORIGINAL DANCE CONTINUES,
her feelings change gradually:

STARTLED / FRIGHTENED
→ CONFUSED
→ RELUCTANTLY AMUSED
→ GENUINELY HAPPY.

She realizes the situation is funny
and starts enjoying it.

She looks back into the camera.
A small natural smile appears,
then gradually grows into a warm,
genuinely delighted smile.

Do NOT smile before the startled reaction.
Do NOT jump instantly from fear to a big grin.

This emotional change happens DURING
the existing dance from @Video1.

It adds no extra time, pauses
or invented choreography.

Keep her face recognizable
through every expression.

────────────────────
CAMERA — STRICT
────────────────────

FORMAT: 9:16 VERTICAL.

NEW STORY camera order:

Heroine close-up facing camera
→ heroine looks RIGHT
→ smooth camera pan RIGHT
→ reveal girl and dancing teddy bears
→ girl says “Будешь”
→ immediate pan BACK to heroine
→ heroine’s shocked reaction
→ playful guiding push toward the group
→ camera follows her movement
→ heroine reaches the center and stops
→ heroine turns toward camera
→ ONLY THEN use @Video1’s final dance camera behavior.

Keep the camera logic simple.

No random close-ups, aerial shots,
unrelated inserts or montage.
No teleporting between locations.

────────────────────
ABSOLUTE EVENT ORDER
────────────────────

1. Heroine faces camera.
2. She says “Я не буду это делать.”
3. She looks and turns RIGHT.
4. Camera pans RIGHT.
5. Girl and teddy bears dance briefly.
6. Girl says “Будешь.”
7. Camera pans back.
8. Heroine silently reacts in shock.
9. Someone lightly turns and guides her toward the group.
10. She resists and says “Да не хочу я там стоять!”
11. She quickly reaches her exact central place.
12. She stops and faces the camera.
13. ONLY NOW the full original dance from @Video1 begins.
14. Heroine is initially frightened by the sudden dance.
15. During the continuing dance, she gradually has fun
    and smiles into the camera.
16. Continue the COMPLETE original dance
    until the original @Video1 ending.

DO NOT REORDER THESE EVENTS.
DO NOT START THE FINAL DANCE EARLY.

────────────────────
FINAL PRIORITY
────────────────────

@Video1 =
the ONLY video reference,
final choreography, movement, timing,
row differences, camera behavior and ending.

@Image1 =
heroine’s face and opening close-up.

@Image2 =
opening staircase, rear view,
group location and lighting continuity.

@Image3 =
fashion crowd appearance,
heroine’s central place
and elderly woman’s LOWER position.

@Image4 + @Image5 =
little girl and teddy-bear appearance.

@Image6 =
heroine’s complete red outfit
and natural full-body proportions.

NO second dance video.
NO smoking, cigarette, smoke or vapor.
NO telephone action.
NO extra dialogue or unrelated props.
NO duplicate heroine or character swapping.

Stable faces and clothing.
Natural human movement.
Warm cinematic outdoor light.
Realistic skin and fabric.
Photorealistic live-action video.
No cartoon appearance.