Back
HolyCrabHolyCrab Studio

Red Hood & the Wolves | STORM II

A dusk-forest film with Red Hood and suited wolves: Seedance 2.5 blockout replacement, 15+7-second prompts, three image references and the final edit.

Make this video

The idea / HolyCrab Studio

From an idea to an original film.

One red hood stays calm among rows of suited wolves as their restrained anticipation breaks into head-swinging choreography. Blockout footage defines motion and camera; three images rebuild the characters and dusk forest. Includes the 15+7-second generation plan and the full 24.63-second final edit.

Red Hood & the Wolves | STORM II — The film

Seedance 2.5 | 15+7-second prompts

These prompts follow the final blockout version, not the original MV. Copy and use each part separately. The supplied final edit runs about 24.63 seconds.

00—15 secPart one | Close-up, entry and turn back

15 seconds establish identity, crowd depth and a continuous pullback; preserve the final pose for continuation.

[Reference bindings]
@Video 1 controls only the matching blockout's positions, paths, occlusion, action timing and camera. Bind the only blue figure to @Image 1 (01-red-hood.jpg): preserve the original Red Hood's delicate face, blonde hair, raised bright-red hood, long red coat, grey dress, gloves and boots; no aging or basket. Bind every grey-white figure to @Image 2 (02-wolves.jpg): complete realistic wolf head, long muzzle, pointed ears, thick furred neck, wolf paws and loose collegiate suit;

upright with two arms and two legs. @Image 3 (03-forest.jpg) supplies only the dusk forest, pink sunset and wide layered earth-and-rock terraces, without changing foot placements. Do not inherit studio backgrounds, lineup compositions, blockout colors, featureless heads or plastic material. The blue figure does not define height: standing naturally at equal depth and ground level, Red Hood is half a head (12–15 cm) shorter than the wolves, excluding hood and ears.

Keep natural proportions across both parts; no stretching, crouching or ground-height tricks.

[0–3 seconds]
Follow the blockout close-up. Red Hood inhales and exhales thin smoke with a restrained expression. Fingers, cigarette and lips make real contact; hand motion follows the blue figure. Every visible background figure is a suited wolf.

[3–10 seconds]
Turn as in the blockout, showing the red hood and coat from behind, then enter the assigned position. The camera pulls back continuously to reveal layered wolf rows. Preserve depth, spacing and occlusion; do not rearrange the crowd.

[10–15 seconds]
Red Hood turns toward the camera and continues holding the cigarette. Wolves retain the reference stillness and small reactions; no early choreography. Keep the ending pose for part two.

[Throughout]
Live-action photography and real biological texture under shared dusk lighting. Only Red Hood has a human face; all others retain wolf heads, necks and paws. Follow the blockout's original speed and audio synchronization. No new actions, shots, dialogue, howls or transitions.
15—22 secPart two | Anticipation and crowd eruption

7 seconds: three seconds of restraint, then four seconds of wolf choreography while Red Hood stays calm.

[Reference bindings]
@Video 1 controls only the matching blockout's positions, paths, occlusion, action timing and camera. Bind the only blue figure to @Image 1 (01-red-hood.jpg): preserve the original Red Hood's delicate face, blonde hair, raised bright-red hood, long red coat, grey dress, gloves and boots; no aging or basket. Bind every grey-white figure to @Image 2 (02-wolves.jpg): complete realistic wolf head, long muzzle, pointed ears, thick furred neck, wolf paws and loose collegiate suit;

upright with two arms and two legs. @Image 3 (03-forest.jpg) supplies only the dusk forest, pink sunset and wide layered earth-and-rock terraces, without changing foot placements. Do not inherit studio backgrounds, lineup compositions, blockout colors, featureless heads or plastic material. The blue figure does not define height: standing naturally at equal depth and ground level, Red Hood is half a head (12–15 cm) shorter than the wolves, excluding hood and ears.

Keep natural proportions across both parts; no stretching, crouching or ground-height tricks.

[0–3 seconds]
Continue part one's identities, clothes, crowd rows and dusk forest from this blockout's opening pose. Red Hood follows the blue figure's cigarette hand, head tilt and inhaling/exhaling phases with restraint. Wolves remain still and anticipate. Continue the camera pullback; do not replay the close-up or crowd entry.

[3–7 seconds]
Every suited wolf follows its grey-white figure's head shakes, swings, sideways tilts, back leans and bends. Preserve the directions, phase offsets and rhythm of front and rear rows; do not synchronize them into one uniform gesture. Red Hood remains calm and does not join the intense choreography.

[Throughout]
Muzzles, ears, furred crowns, rear skulls and thick necks remain connected during bending, back leans, blur, reappearance after occlusion and in the farthest rows. No human faces, hair, bare necks or hands. Terraces support all feet; no floating or vegetation clipping. Keep live-action texture and the blockout's original speed and audio synchronization. End during motion, without freeze-frame, transition, dialogue or howls.

HolyCrab

Editor's note

The key is separating motion structure from visual identity. Blockout footage owns the crowd arrangement, movement rhythm and continuous pullback; three images separately define Red Hood, suited wolves and the forest. The first part establishes the only human face among the wolves. The second lets the crowd erupt while the protagonist stays restrained. Inspect complete wolf anatomy through blur and distant rows, plus clothing, height contrast and crowd continuity at the join.

Three images + two blockout clips

Images own identity and space; blockout clips own motion and camera. Use the video references separately by part. All assets have been compressed for the web.

Original blonde Red Hood character reference with red hood and coat
@Image 1 | Original Red HoodLocks the original delicate face, blonde hair, raised red hood and clothing; naturally half a head shorter than the wolves.
Wolf character sheet with realistic wolf heads and collegiate suits
@Image 2 | Suited wolvesEvery background performer has a complete realistic wolf head, furred neck, wolf paws and a collegiate suit.
Dusk forest with pink sky and layered earth-and-rock terraces
@Image 3 | Pink-sunset forestDefines dusk light, pink sky, forest depth and wide footing without repositioning the blockout crowd.
Part one @Video 1 | 15 secondsSource 0–15 seconds: close-up, turn into the rows, continuous pullback and turn back holding the cigarette.Part one @Video 1 | 15 seconds ↓ MP4
Part two @Video 1 | 7 secondsSource 15–22 seconds: anticipation followed by head-swinging crowd motion with row-specific phase offsets.Part two @Video 1 | 7 seconds ↓ MP4

Prompt breakdown

  1. Motion and appearance have separate owners

    The blue figure becomes Red Hood and every grey-white figure becomes a suited wolf. Do not inherit plastic surfaces, blockout height, studio backgrounds or a fixed image lineup.

  2. One human face, half a head shorter

    Preserve Red Hood's original delicate face as the only human face. At equal depth and ground level she stands half a head below the wolves, without crouching or changing ground height.

  3. Calm lead, staggered crowd

    The 15-second part connects a close-up, entry into the rows and a turn back. The 7-second part moves from anticipation to crowd choreography, preserving row-specific directions and phase offsets.

  4. Anatomy under intense motion

    Head swings, bends, occlusion and blur must not turn wolves into humans. Muzzles, ears, rear skulls, thick furred necks and paws stay intact, with every foot supported by a real terrace.

How to use this prompt

  1. The creation link transfers only this part's prompt. Select Seedance 2.5 manually. For each part, upload its own blockout as @Video 1 and the three images as @Image 1–3. Do not label two simultaneous clips @Video 1 or add the superseded original MV.
  2. Check height, occlusion, distant wolf heads, bare necks, human faces and human hands before a final render. Timestamps are action budgets; verify the generated timing separately.
  3. Compare part one's last frame with part two's opening to align pose, clothing, camera distance and dusk lighting. The 15+7-second plan is distinct from the supplied 24.63-second final edit.

Seedance workflow

Seedance 2.5 Prompt Optimizer Skill

Download the Seedance-specific Skill for Codex to structure references, timing, camera movement, and audio more reliably.
Download Skill

MiniMax H3

MiniMax H3 Format Skill

Official MiniMax-AI Skill, including guides for base modes and full-reference video prompts.
Download Skill

HolyCrab Studio

Turn inspiration into your next film.

Make this video