GoodCase.aiAI News · Radar↗AI Map↗Course · LearnPrompt↗
ProjectsGoodCase.aiAI News Radar ↗AI Map ↗LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
GoodCase.ai
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Projects

AI News · Radar ↗AI Map ↗Course · LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Loading…

GoodCase.ai · AI Prompt Case Collection
DSH PluginsChangelogFeedback
ModelsCreatorsSeedance 2.5Seedance 2.0GPT Image 2GeminiNano Banana ProClaudeClaude Opus 5.5Grok ImagineVeoKlingQwen ImageGPT Image 1.5MiniMax H3

Transform into Spider-Man: Generate a Long-Take Superhero Transformation from a Solo Photo

Creator · 卡尔

AI Video未知来源Added 08/12/2026Independently retested#超级英雄变身#图生视频
More tags (3)
#长镜头#画布节点生图生视频Seedance 2.5
View original source ↗

Prompt

Video prompt: Time: 0–1.8 seconds. Visual: A young Asian male lead wearing silver over-ear headphones, a gray hooded varsity jacket, and dark pants sits facing forward on an open windowsill. He suddenly leans backward, with his head and shoulders dropping first and his legs passing over the window frame as he falls straight out of the window without performing a full backflip. Camera movement: Stable, symmetrical medium-wide shot; as the male lead falls backward, the camera rapidly pushes forward and dives downward, passing through the window to follow him. Time: 1.8–3.2 seconds. Visual: The windowsill is not far above the street. The male lead falls briefly as the wet street and vehicles rapidly grow larger. He angles his body forward and raises one hand to shoot a web toward the upper part of a building. The web instantly pulls taut, converting his fall into forward swinging motion, with no connection to the headphones. Camera movement: Dive close to the character, then use a short whip pan into a close-up of his wrist; once the web pulls taut, accelerate in the direction of the pull and transition into a tracking shot close to street level. Time: 3.2–5.7 seconds. Visual: The male lead completes one smooth pendulum-style swing along the street, passing low over the vehicles. His body extends naturally with the momentum, while his clothes and hair are blown by the airflow. After reaching the lowest point, he rapidly accelerates, then releases the web and glides forward without flipping at any point. Camera movement: Follow from a low position behind and to the side, descending and then rising along the swing arc as vehicles and streetlights rapidly pass through the foreground. Time: 5.7–8 seconds. Visual: He continues forward with the momentum, following a projectile-like trajectory. As his body begins to descend slightly, the male lead immediately raises one hand again and shoots a web toward the upper part of a building on the opposite side. The web instantly pulls taut again, with a slight, natural acceleration in the image, converting his fall into forward swinging motion, with no connection to the headphones. Camera movement: Track rapidly alongside the character in a close lateral move, then use a short whip pan into a close-up of his wrist; once the web pulls taut, accelerate in the direction of the pull and transition into a tracking shot close to street level. Time: 8–10.3 seconds. Visual: The male lead glides close to the building’s exterior wall. His feet step in sequence onto the wall and a metal fire escape, completing two rapid wall push-offs before he leaps toward the street. The action must show clear force and rebound, with no flips. Camera movement: Track laterally close to the wall, briefly moving near the points where his soles make contact, then follow the character downward. Time: 10.3–12.8 seconds. Visual: The shot first shows an empty low-angle view of the wet sidewalk. The male lead’s shadow sweeps into frame, followed by his feet dropping in from above. His brown boots land and create a small splash. His knees bend naturally to absorb the impact, and he immediately rises and runs forward. Camera movement: Keep the camera fixed at ground level before landing; when his feet touch down, add a slight camera shake, quickly tilt upward, then transition into a low-angle tracking shot from behind and to the side. Time: 12.8–17 seconds. Visual: The male lead continues running. A yellow taxi drives across the foreground and briefly blocks the view. When the vehicle clears, the male lead has already reached the opposite side of the road. He steps onto a low barrier and leaps forward while shooting a third web. The web rapidly pulls taut, and the male lead forcefully pulls with the hand connected to the web, causing his entire body to be rapidly drawn toward the building’s rooftop. His feet step onto the wall again, completing two rapid wall push-offs before he leaps onto the rooftop. Camera movement: Low-angle tracking shot, using the taxi as an occlusion transition; then follow the male lead laterally as he leaps and tilt upward, using the building wall sweeping past to transition to the rooftop. Time: 17–19.2 seconds. Visual: The male lead lands beside a rooftop puddle and absorbs the impact in a low crouch. One hand touches the water, creating a restrained splash and ripples. He slowly rises, first looking toward the camera and then calmly gazing at the distant city. Camera movement: Rise smoothly from a low medium shot and push slightly forward into a medium close-up; stop moving when the male lead turns his head. Time: 19.2–20.8 seconds. Visual: The male lead turns to face the New York skyline. The camera moves behind and to the side and pulls back, widening from a medium close-up of the character to a wide rooftop shot. Distant high-rises and pointed skyscrapers enter the frame. Hold for the final half-second, then fade out naturally. Camera movement: Pull back steadily with a slight lateral move, then hold on a fixed shot at the end.
≡Provenance · verifiedPublished prompts are human-checked against the original post; platform-reconstructed prompts are not accepted.Compare with source ↗

Models & stability

Recommended models

Seedance 2.5
Stability
57 / 100
Cost
Low
Related SkillsStoryboard grid to video ↗

Independent retest evidence

See what the same prompt generated in our test.

Retest output · not the creator's original
VideoGenerated evidenceAI judged

MiniMax H3 Max 768p

Sep 7, 2026

Retest score56.5
Your browser does not support video playback.
claude-sonnet-5 · 64.7gpt-5.6-sol · 48.3gap · 16.4
  • Cross-model retest: the recommended model is Seedance 2.5, and this run used MiniMax H3 Max 768p. The result shows how the same prompt carries over to MiniMax H3 Max 768p; it does not show what the creator got with the original model.
  • The retest score is the mean of two AI judges (0–100) for this single generation. No person has reviewed it, and it is not a success rate.

Model and resolution follow the provider task receipt.

Keep exploring

Explore related cases.

View all AI Video Case →
Seedance 2.5 30-second couple bedroom POV: a boyfriend who can't comfort her, only pinch her cheek
AI VideoXAdded 10/11/2026

Seedance 2.5 30-second couple bedroom POV: a boyfriend who can't comfort her, only pinch her cheek

A 30-second 16:9 photoreal slice of couple life that the author says was made with Seedance 2.5. It plays as one boyfriend-POV long take in a bedroom at night: she seizes on his line "You're quite chatty today" to tease him, he clumsily calls her cute, pinches her cheek and deadpans that her face is so soft a pinch should make the anger go away, and she finally cracks up. The prompt scripts every line, pause, micro-expression, the hand's physical path and what the mirror may never reflect. Reproduction materials are incomplete: the prompt opens by asking for an uploaded character reference image of the female lead, and the original author did not provide it; this page only includes the original prompt and the finished video. To reproduce it you need to supply your own reference image of an adult that you have the right to use and that the person has consented to. GoodCase has not retested this prompt, so reproduction results are unverified.

Skill · POV and vlog presenceSkill · Epic fantasy and sci-fi spectacle

Prompt

Use the uploaded character reference image as the sole reference for the female lead. She is a young adult woman. Strictly keep the same character identity throughout, and tightly lock onto the face shape, facial feature proportions, eyebro

Source heat · X
82
Stability
View case →
GPT Image 2 + MiniMax H3 Player Stats Panel Intro Animation
AI VideoXAdded 08/19/2026

GPT Image 2 + MiniMax H3 Player Stats Panel Intro Animation

GPT Image 2 makes a player stats UI still from a character image, and that still is the only visual reference for MiniMax H3, which produces a 15-second anime sports-game stats panel intro: scan lines wake the panel, numbers roll into place, the radar chart expands, and skill cards light up one by one.

Skill · Epic fantasy and sci-fi spectacleSkill · Storyboard grid to video

Prompt

MiniMax H3 Prompt: @[ref img] is the sole visual authority for Kaze, the football, the complete player-stats interface, typography, numbers, icons, colors, lighting, layout, and vertical composition. …

Source heat · X
99
Stability
49
View case →
Claude Opus 5.5 - Grid Effect
AI VideoXAdded 10/26/2026

Claude Opus 5.5 - Grid Effect

Claude Opus 5.5 - Grid Effect I tried three different versions, in order: Poster Grid, Style Infection and Temporal Mosaic. The original video was 15 seconds lo…

Skill · Storyboard grid to video

Prompt

Claude Opus 5.5 - Grid Effect I tried three different versions, in order: Poster Grid, Style Infection and Temporal Mosaic. The original video was 15 seconds long, while the music was 40 seconds. P…

Source heat · X
92
Stability
View case →

Same creator

More from @卡尔 →

  • Localized Biscuit Ad Edit: Seamlessly Replace Biscuits with Ice Cream BarsAI Video · Seedance 2.5 · 2026-08-12
  • Fruit Cookie E-Commerce AdAI Video · Seedance 2.5 · 2026-08-12
  • Amusement Park Time Freeze: Denture PrankAI Video · Seedance 2.5 · 2026-08-12
  • SONORA Headphones Website UI/UX Motion VideoAI Video · Seedance 2.5 · 2026-08-12
  • “Magnet Riot” Gameplay Showcase: From Main Menu to SprintAI Video · Seedance 2.5 · 2026-08-12
  • American Collage-Style Sci-Fi Animated Film Opening: “NEON OVERDRIVE”AI Video · Seedance 2.5 · 2026-08-12

Same model

Latest with Seedance 2.5 →

  • A cartoon baby tennis player pops out of a pregnant bellyAI Video · Seedance 2.5 · 2026-11-07
  • Absurd pulp-space frames of a blonde woman astronautAI Video · Seedance 2.5 · 2026-11-07
  • Elevator drops to floor zero: a girl in red and a smiling doubleAI Video · Seedance 2.5 · 2026-11-07
  • At 3:17 a.m., a man finds his double on the apartment CCTVAI Video · Seedance 2.5 · 2026-11-07
  • A girl's fireball leaves an Edo-village samurai in shockAI Video · Seedance 2.5 · 2026-11-07
  • Pink-haired woman flees zombies across nighttime scaffoldingAI Video · Seedance 2.5 · 2026-11-07

Each detail page keeps the original result, the prompt, and retest evidence in one reading path.