Fast And Short Transition Templates

GLOBAL LOCK:
Subject: A young South Asian woman, approximately 20-25 years old, with warm skin tones and dark hair tied back in a neat bun. She wears a white ribbed long-sleeve turtleneck top and high-waisted greyish-brown trousers. 
Environment: Indoor office/studio setting. 
Lighting: High-contrast cinematic lighting. 
Color Grade: Vibrant, saturated colors with deep blacks. 
Camera: Sharp focus, shallow depth of field, 4k resolution. 
Speech: Clear, energetic female voice, UGC-style direct-to-camera delivery.

[00:00–00:03]
Subject: The woman is sitting in a black mesh office chair, holding a small black wireless microphone to her mouth. She is smiling and looking directly at the camera.
Environment: A room with a whiteboard in the background covered in diagrams. The entire scene is washed in a vibrant purple and magenta neon light.
Action: She speaks the words "This effect is called..."
Camera: Medium shot, static, eye-level.
Lighting: Strong purple LED key light from the left, magenta fill from the right.
Speech: "This effect is called" (Energetic, clear).

[00:03–00:07]
Subject: The woman remains in the same pose, but her surroundings begin to morph.
Environment: The purple room physically breaks apart. Panels of the wall and pieces of furniture fly and rotate through the air, re-assembling into a new scene.
Action: A mechanical, fluid transition where the whiteboard disappears and is replaced by a wooden desk with a computer monitor.
Camera: Slight zoom-in during the morph to emphasize the motion.
Lighting: The purple light fades out as a warm, natural key light and a bright orange background light fade in.
Motion: High-speed "transformer-like" re-arrangement of objects.

[00:07–00:19]
Subject: The woman is now in the new environment, sitting at the desk.
Environment: A desk with a large monitor, a mechanical keyboard, headphones, and a notebook. The background is a split wall: one side bright orange, the other dark grey.
Action: She gestures toward the desk and then points down. Intercut with screen recordings of a Google search for "Midjourney" and the Midjourney "Vary Region" interface.
Camera: Medium close-up.
Lighting: Warm key light from the front-right, creating a soft glow on her face.
Speech: "The RE-ARRANGE effect. And here's how I made it under 30 seconds. Step one: Take two pictures of yourself from different angles."

[00:19–00:25]
Subject: Screen recording of a video editing software (Premiere Pro style).
Environment: Digital interface with video tracks, audio waveforms, and a preview window showing the woman.
Action: A cursor moves across the screen, dragging a video clip (the AI transition) between two other clips.
Camera: Screen capture.
Speech: "Step two: Go to your favorite editing app and edit this transition video with your original two videos."

[00:25–00:34]
Subject: The woman is back on camera in the orange/grey desk setup.
Environment: Desk setup with the orange wall. A neon sign saying "the CYBORG girl" appears behind her in the final seconds.
Action: She smiles, pats herself on the back, and gestures for the viewer to comment.
Camera: Medium shot, static.
Lighting: Warm, professional studio lighting.
Speech: "Now pat yourself in the back because you just made this effect as well. Comment down 'PROMPT' so I'll share mine with you, and if you like to make cool AI videos as such, follow the Cyborg Girl for more."

NEGATIVE PROMPT:
Visual: Blurry face, inconsistent clothing textures, flickering lights, distorted hands, floating objects that don't belong to the transition, low resolution, watermark, messy hair strands.
Speech: Robotic tone, background hiss, muffled audio, lip-sync delay, unnatural pauses, clipping audio.

SPEECH PACK:
[00:00-00:03] "This effect is called"
TAKE_A: (Excited) This effect is called...
TAKE_B: (Mysterious) This effect is called...
TAKE_C: (Direct) This effect is called...

[00:03-00:07] "The RE-ARRANGE effect."
TAKE_A: (Punchy) The RE-ARRANGE effect!
TAKE_B: (Smooth) The re-arrange effect.
TAKE_C: (Emphasized) The... RE-ARRANGE... effect.

[00:07-00:34] "And here's how I made it under 30 seconds. Step one: Take two pictures of yourself from different angles. Go to Midjourney and add images as the starting and ending frame. Prompt this and now you will have a transition video of yourself. Step two: Go to your favorite editing app and edit this transition video with your original two videos. Now pat yourself in the back because you just made this effect as well. Comment down 'PROMPT' so I'll share mine with you, and if you like to make cool AI videos as such, follow the Cyborg Girl for more."
TAKE_A: (Fast-paced, tutorial style)
TAKE_B: (Friendly, encouraging)
TAKE_C: (Authoritative, expert)

GLOBAL LOCK: 9:16 vertical creator tutorial Reel, split between a young adult white male presenter in a dark warm-lit room and large screen-recorded workflow panels above or behind him. Generated visual world is a rockstar / cyberpunk action aesthetic with the same male lead wearing black sunglasses, dark jacket, chains, and leather styling, placed in fiery stage-like scenes, industrial interiors, neon-lit action frames, weapon poses, and cinematic close-ups. Interface layer shows start-frame / end-frame pairings, timeline tracks, transition bars, editing controls, artist-branded pages, audio waveform panels, prompt input fields, and media-generation cards. Keep a clear difference between the human presenter and the generated character world, while maintaining consistency within the generated character sequence.

00:00-00:08
Open with multiple start-frame and end-frame comparisons showing the same sunglasses-wearing rockstar character in fiery performance and action scenes, the presenter below points upward and speaks with high-energy tutorial cadence, timeline tracks and color bars visible on the UI, warm orange practical lighting on the presenter, gritty cinematic orange-blue grade on the generated visuals.

00:08-00:16
Continue showing side-by-side or stacked scene variations: weapon-holding poses, stage-performance close-ups, and cinematic industrial settings, while the presenter uses hand gestures to explain how the sequence is built, the UI emphasizes timeline arrangement and transition logic rather than one single prompt.

00:16-00:24
Move deeper into editing proof with zoomed-in timeline bars, frame strip details, and an `Artist` branded tool page, the presenter points at controls while explaining how to organize clips and transitions, generated character imagery remains consistent with black shades, slick styling, firelight, and action-film mood.

00:24-00:32
Show upload cards and tool menus for image-to-video or media-generation steps, then a text input field describing the scene or story, plus a cinematic preview card of the hero in a full-body action composition, visual message is that the workflow combines reference images, scene description, and motion generation inside one stack.

00:32-00:40
Display more interface states: asset slots, prompt fields, voice or audio settings, and waveform-based sound-design panels, while the presenter keeps an enthusiastic teacher rhythm, explain that the system adds sound, timing, and narrative pacing on top of the generated visual sequence.

00:40-00:48
Return to finished preview scenes featuring the rockstar/cyberpunk hero in fiery streets or industrial backdrops, then show message-like prompt cards and result panels, the presenter emphasizes how each tool layer builds toward a polished cinematic clip rather than a disconnected set of images.

00:48-01:06
Close with a dense mix of workflow proof: audio blocks, prompt cards, final preview frames, and platform-branded pages, ending on a complete cinematic result screen and conversion-oriented messaging, preserve the same sunglasses hero identity, timeline-first tutorial framing, and polished creator-education energy through the last second.

NEGATIVE PROMPT: character face drift between frames, broken sunglasses, warped guitar or weapon props, inconsistent jacket details, low-res fire effects, muddy timeline UI, unreadable tracks, broken waveform displays, random extra characters, noisy shadows, overexposed presenter skin, bad lip-sync on presenter, confusing interface hierarchy, washed-out cyberpunk colors, unstable industrial backgrounds, plastic skin, duplicate hands during gestures.

SHOT PROMPTS:
1. Start-frame / end-frame cinematic comparison card with rockstar lead in sunglasses.
2. Presenter explaining timeline-based build process in warm dark room.
3. Weapon pose and firelit stage close-up with same hero identity.
4. Zoomed-in timeline tracks and transition bars.
5. Artist-branded workflow screen.
6. Prompt input card and preview scene generator.
7. Audio waveform and sound-design panel.
8. Final polished cinematic result card with conversion CTA.

SPEECH PACK:
Single male presenter voice, medium-fast pace, excited tutorial energy, close-mic room sound, crisp articulation, frequent emphasis on workflow verbs like build, edit, animate, sound design, and generate. Lips are visible in most presenter shots and should sync tightly with upward pointing gestures. Core meaning across the timeline: here is how the cinematic sequence is constructed from start and end frames, here is the timeline and artist workflow, here is how prompts and images become motion, here is how audio is added, and here is the final polished result.

GLOBAL LOCK: vertical Instagram AI tutorial reel hosted by a red-haired bearded male creator speaking directly to camera from a warm wood-panel backdrop; repeated cutaways to Pollo AI interface, ChatGPT prompt windows, generated portrait grids, and face-consistent character examples; bold short text beats synchronized with each spoken step; social-media tutorial pacing; clean screen-recording inserts; no unrelated footage, no color drift, no extra hosts, no meme chaos.

00:00-00:05
The host introduces an AI face-consistency workflow in a vertical talking-head setup. Split-screen and stacked portrait examples show the same person rendered in multiple styles, while bold on-screen text emphasizes that this can be done in a few steps.

00:05-00:11
The reel cuts between the host and a ChatGPT window, explaining how to upload a selfie and ask for a full descriptive prompt or face analysis. The creator gestures while short text phrases summarize each instruction.

00:11-00:18
Screen recordings show Pollo AI and related interface panels, including prompt boxes, generation modes, and output galleries. The host explains how to paste prompts, select models, and generate high-consistency character images from the selfie input.

00:18-00:26
Generated results fill the screen: grids of portraits, stylized headshots, and character variants with similar facial identity. The host calls out benefits like cheaper generation, faster workflow, better emotional range, and more natural skin consistency.

00:26-00:33
The tutorial transitions into the editing stage, where generated images are dropped into a video editor or transformation workflow. Example outputs show the same person preserved across multiple frames and styles, reinforcing per-frame alignment and prompt reuse.

00:33-00:36
The host ends with a direct call to action, prompting viewers to comment for the AI tool or workflow details. End card style remains simple, with the host centered and example outputs floating around him.

NEGATIVE PROMPT:
horizontal video, outdoor vlog footage, unrelated gaming UI, messy desktop clutter, unreadable text overload, warped faces, inconsistent identity drift, low-resolution screen captures, extra presenters, cartoon slapstick, random stock footage, dramatic camera shake

GLOBAL LOCK: clean editorial social card in a near-square or portrait format, white background, black border, black headline text reading CASE #1, handwritten-style subheading reading Visual hook, split-image layout inside the card showing two related but contrasting frames. Left frame: a young man in a white T-shirt leaning or moving near a train doorway or window with railway tracks and industrial outdoor background visible, candid motion-oriented documentary feel. Right frame: the same young man in a cleaner portrait-like shot wearing or removing black sunglasses, face turned toward camera, brighter and more controlled fashion-UGC composition. The whole piece reads like a visual hook template card for creators, minimal, graphic, and instantly scannable.

00:00-00:01
Show the full card layout with CASE #1 at the top and Visual hook beneath it, bordered white card design centered on a white background, split image visible, left side emphasizing movement and environment, right side emphasizing face and style.

00:00:01-00:00:02
Hold the left frame long enough to read the train-side context: casual white-shirt male subject, transport or track setting, candid off-balance movement, outdoor realism, motion-oriented attention trigger.

00:00:02-00:00:03
Resolve into the right portrait frame where the same man adjusts or wears dark sunglasses and looks composed, proving the hook pattern: combine a kinetic environmental frame with a cleaner face-led style frame for a stronger social opener.

NEGATIVE PROMPT: messy layout, wrong CASE #1 text, unreadable handwritten subtitle, duplicate subjects, incorrect sunglasses shape, broken train geometry, cluttered background, extra props, mismatched person identity between left and right panels, muddy white background, distorted border lines, low-detail face, random color gradients, off-brand typography, poor card alignment.

SHOT PROMPTS:
1. Minimal white case-study card with CASE #1 headline and Visual hook subtitle.
2. Left panel showing candid train-side movement shot with railway context.
3. Right panel showing stylish sunglasses portrait of same male subject.
4. Full card hold that reads like a reusable hook template for creators.

SPEECH PACK:
No speech required. This is a silent visual card or motion-post concept. If any voiceover is used, it should be extremely brief and instructional, simply explaining that this is a visual hook formula combining movement and portrait contrast.

GLOBAL LOCK:
The subject is a young woman of South Asian descent, approximately 20-25 years old, with long, straight dark hair and a warm skin tone. She wears a black sleeveless mock-neck top. The environment is a bedroom with a "CYBORG GIRL" pink neon sign on the wall, soft purple and pink ambient lighting, and a shelf with framed photos in the background. She holds a small black Rode wireless microphone. The camera is a high-quality smartphone lens (approx. 24mm equivalent), static medium close-up. The color grade is vibrant with a focus on magentas and purples. Speech is clear, direct-to-camera, with a rhythmic, educational cadence.

[00:00–00:01]
Subject: The woman looks directly at the camera, smiling slightly, holding the mic near her mouth.
Action: She speaks the words "This is called".
Camera: Static MCU.
Lighting: Soft pink key light from the left, purple rim light.
Speech: "This is called" (High energy, introductory tone).

[00:01–00:03]
Subject: Rapid montage of the word "purpose" written on different materials.
Visuals: 
1. Torn yellow paper with "pur" in cursive on a wooden desk.
2. Red paper with "purpose" in bold black ink next to a pink fuzzy monster toy.
3. A green cutting mat with a yellow paper strip.
Camera: Top-down macro shots, centered composition.
Motion: Hard cuts every 0.2 seconds.
Speech: "Match cut."

[00:03–00:06]
Subject: Back to the woman in the pink room.
Action: She gestures with her free hand, emphasizing "without any production for free."
Camera: MCU, slight zoom-in for emphasis.
Speech: "And here's how you can do it without any production for free."

[00:06–00:10]
Visuals: Screen recording of a Google search for "nano banana" (Gemini). A mouse cursor clicks on the Gemini link.
Action: UI interaction showing the transition from search to the AI interface.
Speech: "Head to Nano Banana, type out this prompt..."

[00:10–00:15]
Visuals: Close-up of a text prompt in a white text box. The prompt describes technical camera settings and the word "purpose". Then, a long list of 30 numbered prompts appears on a dark background.
Action: Scrolling through the generated prompt list.
Speech: "...and make sure you add the word that you like. It will then generate 30 different prompts..."

[00:15–00:22]
Subject: Split screen. Left side is the woman talking; right side is a 3x3 grid of generated images showing the word "purpose" in various artistic settings (paper, metal, fabric).
Action: She points toward the grid.
Speech: "...that you can use in Nano Banana to generate all these images. Now download these images, which are your frames by the way..."

[00:22–00:27]
Visuals: Screen recording of Adobe Premiere Pro. A timeline is visible with several clips. The "Effect Controls" panel is shown, specifically "Time Remapping" and "Speed" settings.
Action: The cursor adjusts the speed curve.
Speech: "...and head to your favorite editing app. Convert your frames to videos, stitch them together, adjust the speed and dimensions..."

[00:27–00:29]
Visuals: The final match-cut animation. The word "purpose" flickers through different backgrounds (yellow paper, green mat, red paper) in a perfectly aligned loop.
Motion: Extremely fast, rhythmic cuts.
Speech: "And boom! You just made this cool video as well."

[00:29–00:35]
Subject: Back to the woman in the pink room.
Action: She gives a final tip, holding the mic. A "the CYBORG girl" logo appears at the bottom.
Speech: "I have left the prompt in the comment section, and if you like cool AI hacks as such, follow the Cyborg Girl for more."

NEGATIVE PROMPT:
Visual: Motion blur on the face, inconsistent lighting between cuts of the creator, distorted text in the AI images, low resolution, watermark, shaky camera, messy background.
Speech: Robotic voice, background noise, muffled audio, lip-sync delay, stuttering, unnatural pauses.

SPEECH PACK:
[00:00-00:01] "This is called..." (TAKE_A: Enthusiastic; TAKE_B: Mysterious; TAKE_C: Matter-of-fact)
[00:01-00:03] "...match cut." (TAKE_A: Punchy; TAKE_B: Whispered; TAKE_C: Confident)
[00:03-00:06] "And here's how you can do it without any production for free." (TAKE_A: Fast-paced; TAKE_B: Emphasizing 'free'; TAKE_C: Helpful)
[00:30-00:35] "I have left the prompt in the comment section, and if you like cool AI hacks as such, follow the Cyborg Girl for more." (TAKE_A: Friendly outro; TAKE_B: Direct and fast; TAKE_C: Warm and inviting)

A) MISE EN PLACE

Reference summary
- Duration: 00:58.26
- Format: vertical 9:16, 720x1280, 24 fps
- Structure: tutorial reel combining talking-head presentation, interface demo, output examples, and CTA
- Audio: spoken direct-to-camera narration over tutorial visuals; exact transcript partially inferred from observable text, pacing, and caption

Scene / shot segmentation
1. 00:00.00-00:04.50
   Hook section. AI-generated snowy valley / blocky stylized environment fills the background while large centered white text reads “How to do this with FREEPIK.” Presenter appears as a cutout talking head seated in a chair at the bottom of frame.
2. 00:04.50-00:10.50
   Fast examples and UI preview. The background alternates between a Freepik/Kling workflow poster and a glossy “Real Estate” example card on purple abstract waves. Presenter keeps gesturing directly to camera.
3. 00:10.50-00:26.00
   Workflow explanation. Interface screens, prompt windows, and tutorial cards dominate the frame while presenter remains pinned lower center. Visual emphasis moves between chat-like instruction blocks and editing software panels.
4. 00:26.00-00:40.50
   Technical implementation section. Close views of the prompt box, Freepik generation settings, and editing timeline appear, including readable concepts like a living-room camera glide prompt and After Effects layer names for day/night states.
5. 00:40.50-00:50.50
   Result showcase. Bright luxury living-room renders and a moving circular ring/portal effect appear while presenter continues the explanation.
6. 00:50.50-00:58.26
   CTA finish. Large text “Comment ‘AI’” fills the upper half while workflow graphics and the tutorial poster stack below it. Presenter lands the call to action.

Visual evidence keyframes
- 00:00.00: stylized snowy scene, bold white hook text, presenter bottom center
- 00:06.00: Freepik workflow card on screen with presenter gesturing
- 00:09.00: “Real Estate” result frame over glossy purple abstract background
- 00:15.00: dark UI and chat box explaining workflow steps
- 00:30.00: prompt box visible with cinematic living-room camera-glide prompt and blue Generate button
- 00:39.00: After Effects timeline with project label “Freepik Kling O1 Style Transfer” and DAYTIME / NIGHTTIME layers
- 00:48.00: interior render showcase with presenter still lower frame
- 00:55.00: bold “Comment ‘AI’” CTA card and Freepik branding

Speech evidence (best-effort)
- speaker_count: 1
- speaker A: male-presenting presenter, on-camera for most of the reel
- speech style: energetic tutorial narration, direct address, short explanatory bursts, occasional emphasis gestures matching the cuts
- likely content themes in order:
  1) hook about how to create the shown transition with Freepik
  2) quick proof that the style-transfer result works for practical use cases such as real estate
  3) walkthrough of workflow steps and prompt usage
  4) implementation notes around Kling / Freepik / After Effects
  5) closing CTA to comment “AI” for prompts, images, or resources
- lip visibility: full, presenter visible and speaking throughout many segments
- lip_sync_strictness: medium for recreation, because mouth motion is visible but precise wording is not the main retention driver

Invariants list (LOCK THESE)
- presenter identity: white-presenting man in his 20s-30s with medium brown hair, short beard and moustache, blue baseball cap with yellow front logo, muted teal/gray athletic t-shirt with cream shoulder stripes, seated in a black chair
- layout: presenter cutout anchored near the bottom center while backgrounds switch between AI outputs, UI screenshots, tutorial cards, and editing timelines
- design language: dark backdrop or interface-heavy background, bold white headline typography for hooks and CTA, high-contrast tutorial-card overlays
- product context: Freepik and Kling style-transfer workflow, prompt box, generation settings, result previews, After Effects implementation
- motion grammar: rapid jump cuts every few seconds, presenter hand gestures synced to emphasis points, no cinematic camera move inside the talking-head layer
- lighting / grade: evenly lit presenter with soft frontal light, slightly warm skin tones, clean creator-video look
- audio style: concise teaching narration, upbeat but clear, no cinematic acting, creator-education cadence

Variables list (TWEAK THESE)
- exact scenic examples used behind the presenter
- exact software screens and UI crop choices
- precise phrasing of the narration
- title copy variations, as long as the first frame still clearly states the tutorial promise
- CTA wording around “Comment AI,” while preserving the comment-driving mechanic

B) SHOTLIST

Shot 1
- shot_id: 1
- timecode_start: 00:00.00
- timecode_end: 00:04.50
- duration: 4.50s
- framing: presenter lower-third cutout over a full-screen AI landscape, text centered above him
- lens: presenter feels like webcam / phone close-medium crop
- camera movement: static presenter crop; background video may subtly move
- subject: presenter talks directly to camera with open-hand gestures
- environment: snowy stylized AI environment in background
- lighting: soft, even, creator-studio frontal light on presenter
- color grade: bright scenic background contrasted with darker presenter shadow edges
- speech/audio: Speaker A introduces the tutorial promise, roughly “how to do this with Freepik”
- must match: instant value proposition and brand/tool clarity in frame one

Shot 2
- shot_id: 2
- timecode_start: 00:04.50
- timecode_end: 00:10.50
- duration: 6.00s
- framing: stacked workflow poster and result cards with presenter pinned at bottom
- lens: presenter crop unchanged
- camera movement: brisk editorial cuts between background examples
- subject: presenter continues gesturing while visual proof of output quality appears
- environment: Freepik workflow graphic, glossy purple abstract background, “Real Estate” sample card
- lighting: presenter remains constant; backgrounds are saturated and polished
- speech/audio: Speaker A explains what kind of transition or use case is being shown
- must match: quick proof section before deep tutorial

Shot 3
- shot_id: 3
- timecode_start: 00:10.50
- timecode_end: 00:26.00
- duration: 15.50s
- framing: interface screens and text panels dominate; presenter cutout remains lower center
- lens: medium crop on presenter
- camera movement: fast cuts, no slow camera motion
- subject: presenter emphasizes workflow steps with hand motions
- environment: dark UI panels, text blocks, buttons, workflow poster
- lighting: consistent creator lighting
- speech/audio: Speaker A explains the process step by step in short sentences
- must match: tutorial credibility through actual software views

Shot 4
- shot_id: 4
- timecode_start: 00:26.00
- timecode_end: 00:40.50
- duration: 14.50s
- framing: close interface crops, prompt box, settings, editing timeline
- lens: presenter crop unchanged, background takes priority
- camera movement: screen swaps and hard cuts
- subject: presenter points and speaks; UI shows prompt engineering and compositing logic
- environment: prompt panel with generation controls, After Effects timeline, day/night layer naming
- lighting: neutral creator lighting
- speech/audio: Speaker A gets more tactical, likely naming tools and steps
- must match: explicit practical detail, not vague inspiration talk

Shot 5
- shot_id: 5
- timecode_start: 00:40.50
- timecode_end: 00:50.50
- duration: 10.00s
- framing: output preview takes over, presenter still present
- lens: medium crop on presenter, wide interior examples in background
- camera movement: brisk output showcase cuts
- subject: presenter reinforces the use case and payoff
- environment: luxury living room renders, daylight and nighttime mood variants, circular portal/ring effect
- lighting: bright interiors contrast with dark tutorial backdrop
- speech/audio: Speaker A summarizes why the workflow feels premium / dynamic
- must match: result proof after the technical section

Shot 6
- shot_id: 6
- timecode_start: 00:50.50
- timecode_end: 00:58.26
- duration: 7.76s
- framing: large CTA text in upper frame, workflow graphics below, presenter lower center
- lens: presenter crop unchanged
- camera movement: mostly static CTA hold with minor cut refreshes
- subject: presenter lands the final ask
- environment: “Comment ‘AI’” headline, Freepik poster, dark background
- lighting: consistent creator lighting
- speech/audio: Speaker A invites comments to receive prompts / images / resources
- must match: strong comment-driving CTA at the end

C) STYLE BIBLE (GLOBAL)

- visual_style: creator tutorial reel, clean UGC educator format, software-demo montage
- camera_signature: static cutout presenter layer plus rapidly changing background plates
- lighting_signature: soft frontal light on presenter with minimal drama, practical “studio desk creator” feel
- grade_signature: presenter stays warm-neutral while the backgrounds alternate between vibrant AI outputs and dark UI panels
- texture_signature: crisp app screenshots, bold text overlays, clean edges around the presenter cutout
- pacing_signature: immediate hook, proof fast, tutorial core in the middle, results near the end, CTA close
- speech_style: direct-to-camera educational narration
- speaker_profile: energetic male creator voice, conversational, confident, tutorial-first
- pronunciation_profile: relaxed but clear English, medium pace, emphasis on tool names and steps
- mic_mix_profile: dry creator audio, intelligible, lightly compressed, optimized for phone playback

D) PROMPT SYNTHESIS

MASTER PROMPT

GLOBAL LOCK: Create a vertical 9:16 creator tutorial reel. Keep one white-presenting male presenter in his late 20s to early 30s visible as a cutout near the bottom center for most of the video. He has medium brown hair, short beard, blue baseball cap with a yellow logo patch, muted teal-gray athletic t-shirt with cream stripes on the shoulders, and sits in a black office chair. He speaks directly to camera with energetic but clear tutorial cadence, frequent hand gestures, and a creator-education tone. The background changes rapidly between AI-generated example footage, Freepik / Kling workflow cards, software UI close-ups, prompt boxes, editing timelines, luxury interior outputs, and large white CTA text. Lighting on the presenter remains soft and even, like a YouTube short-form setup. The reel should feel premium, practical, and scroll-stopping, not chaotic. Keep typography bold and readable, especially in the opening hook and final CTA.

[00:00-00:04.50] Open with a dreamy stylized snowy valley or blocky cinematic environment filling the frame. Place the presenter as a bottom-center cutout, talking directly to camera with open-hand gestures. Large bold white text appears centered above him: a clear promise equivalent to “How to do this with FREEPIK.” Keep the frame immediately readable in under one second. Speaker A introduces the tutorial in a punchy sentence, upbeat, direct, and creator-friendly, lips fully visible, medium lip-sync strictness.

[00:04.50-00:10.50] Cut through a fast sequence of proof visuals while the presenter continues talking in the same lower-center position. Show a Freepik/Kling workflow poster, then a polished result card such as a real-estate style transformation over glossy purple abstract graphics. Keep the presenter gesturing to emphasize that this is a real usable workflow, not just a concept. Speaker A explains the type of transition and why it feels premium or dynamic. Maintain crisp readable branding and high contrast.

[00:10.50-00:26.00] Shift into the tutorial core. Background becomes darker UI panels, instruction cards, and software screens. The presenter keeps speaking with concise direct-teaching cadence and emphatic hand motions. Alternate between chat-like explanation boxes, workflow graphics, and screen recordings of the process. Keep every cut purposeful and easy to parse. Speaker A explains the steps in plain English, likely calling out the tool stack and the logic of layering AI visuals over video. Lips remain visible; sync important sentence accents to cut points.

[00:26.00-00:40.50] Push into the tactical detail section. Show a prompt interface with a large text box, generation controls, aspect ratio settings, and a blue generate button. Include a prompt concept like a smooth forward camera glide through a high-end living room with a floating ring and natural daylight. Then cut to an editing timeline such as After Effects with project naming around Freepik Kling style transfer and layers labeled DAYTIME and NIGHTTIME. The presenter continues speaking, now more instructional and specific, with slightly sharper emphasis on key terms. Keep the background sharp enough that viewers can read it as real software.

[00:40.50-00:50.50] Move into result showcase mode. Show bright luxury interior renders, window-heavy living rooms, daytime and nighttime examples, and a circular portal/ring motif suggesting the style-transfer effect. The presenter remains lower center, speaking with a satisfied “here is the result” energy. Cuts are brisk but less dense than the middle tutorial section so the viewer can appreciate the output quality.

[00:50.50-00:58.26] Finish with a comment CTA. Large bold white text equivalent to Comment “AI” fills the upper half of the frame while workflow graphics and the Freepik poster stack beneath it. The presenter looks into camera and lands a direct ask for viewers to comment in exchange for prompts, images, or workflow help. Keep the final frame highly screenshot-able and optimized for engagement comments. Lips visible, clear final emphasis on the call to action.

NEGATIVE PROMPT

Avoid messy cutout edges around the presenter, unreadable UI text, distorted hands, warped face identity, random wardrobe changes, off-brand tool names, muddy screen captures, cluttered overlapping graphics, weak hook typography, low-contrast captions, overdone motion graphics, cinematic shallow-depth glamour shots, robotic narration, slurred speech, lip-sync mismatch, clipped audio, heavy reverb, harsh de-essing, background noise pumping, strobing transitions, flicker, frame jitter, generic stock-office imagery, and CTA text that is too small to read on mobile.

SHOT PROMPTS

- Hook shot delta: snowy cinematic AI background, bold white tutorial text, presenter lower center
- Proof shot delta: workflow poster plus flashy real-estate sample, presenter gesturing
- Tutorial shot delta: dark UI screens, explanation boxes, practical workflow overlays
- Prompt shot delta: close prompt interface with readable cinematic living-room prompt and generate button
- Editing shot delta: After Effects timeline with DAYTIME and NIGHTTIME layer logic
- Result shot delta: high-end interior showcase and moving ring motif
- CTA shot delta: giant Comment “AI” text with branded workflow poster below

SPEECH PACK

Timecoded transcript (best-effort observable reconstruction)
- [00:00.00-00:04.50] Speaker A: “Here’s how to do this with Freepik.” Emotion: upbeat, hook-first, medium-fast pace.
- [00:04.50-00:10.50] Speaker A: “This workflow gives you a clean cinematic style-transfer transition, and it works for polished use cases.” Emotion: confident, explanatory.
- [00:10.50-00:26.00] Speaker A: “I’m showing the process step by step so you can layer AI visuals over your video inside Freepik and Kling.” Emotion: practical, tutorial-focused.
- [00:26.00-00:40.50] Speaker A: “Use a clear motion prompt, generate the shot, then bring it into your edit and organize the effect layers.” Emotion: precise, more technical, medium pace.
- [00:40.50-00:50.50] Speaker A: “This is where it starts to feel premium because the transition adds movement and visual depth.” Emotion: reinforcing payoff.
- [00:50.50-00:58.26] Speaker A: “Comment ‘AI’ if you want the prompts, images, or Freepik workflow.” Emotion: direct CTA, slightly punchier emphasis.

TAKE_A
- Keep the wording close to the lines above with confident creator-teacher cadence.

TAKE_B
- Same meaning but slightly faster and more sales-forward, with stronger emphasis on tool names and “Comment AI.”

TAKE_C
- Same meaning but slightly calmer, more instructional, and less hype-heavy.

Closest audible version
- Because the exact waveform was not transcribed word-for-word, treat the lines above as closest-observable tutorial intent anchored to on-screen text, pacing, and the caption.

Safe paraphrase version
- The reel teaches how to recreate a cinematic style-transfer transition in Freepik/Kling, shows the workflow, and ends by asking viewers to comment “AI” for the assets.

GLOBAL LOCK: vertical 9:16 comparison reel split into two stacked halves. Top half labeled `AI:` shows the transformed cinematic version of the same man. Bottom half labeled `Original:` shows the raw talking-head recording of the creator performing hand gestures against a plain indoor backdrop. The subject identity must remain the same across both halves: young adult male, short brown hair, light skin, expressive face, medium build.

MASTER INTENT: create a short before-and-after AI transformation reel where each gesture in the original footage is mirrored by a stylized cinematic conversion in the top half. The AI version should progressively change wardrobe, mood, and environment while preserving timing and body movement from the original clip. End with a comment CTA for the guide.

00:00:00-00:00:02
Open with the creator pointing to his head in the original lower half while the upper AI half presents a cleaned-up enhanced version of the same pose. Simple gray studio background below; upgraded styling above.

00:00:02-00:00:04
Shift the AI half into more dramatic wardrobe changes: open shirt styling, then black leather jacket and sunglasses, while the original lower half remains plain and casual. Keep the gesture timing synchronized between top and bottom.

00:00:04-00:00:06
Move into higher-intensity transformations. The AI half places the same man in a warmer dramatic environment, including moody background lighting and a stronger cinematic grade. The original lower half still shows the untouched performer moving through the same gesture.

00:00:06-00:00:08
Push the transformation further with a fiery action-style background in the AI half. Flames or bright orange effects appear behind the subject while he continues reacting with raised hands and animated facial expression. Overlay a bold CTA near the lower section of the AI frame: `comment "AI" for guide`.

00:00:08-00:00:09.3
End on the strongest before-and-after comparison, holding the transformed fiery look on top and the original gesture on the bottom long enough for the CTA to be read clearly.

CAMERA: static front-facing camera, medium framing, same timing across original and transformed versions.

LIGHTING: original footage uses flat indoor creator lighting; AI version upgrades this into fashion-commercial and action-movie lighting depending on the segment, including clean studio light, editorial contrast, and warm flame reflections.

GRADE: original remains natural and unpolished; AI side becomes crisp, cinematic, contrasty, and style-forward.

MOTION: gesture-synced transformation reel, no camera shake, fast jump cuts between AI styling states.

TEXT PACK: exact visible labels `AI:` and `Original:`; final CTA `comment "AI" for guide`.

NEGATIVE PROMPT: different person in AI half, broken hand sync, mismatched gestures, unstable split-screen, unreadable labels, warped sunglasses, cartoon flames, overprocessed skin, blurred original footage, extra subtitles, watermark, logo corruption.

Core format and topic lock: a vertical creator tutorial showing how to create an AI VFX shot using Kling O1 inside Higgsfield, combined with Adobe After Effects and Adobe Illustrator. The main source material is a green-screen clip of the presenter walking toward camera in a white t-shirt and dark pants. The workflow then combines that green-screen footage with generated environment imagery and a bold black-and-white geometric Illustrator graphic that becomes part of the compositing transition or reveal. A male presenter in a rounded talking-head box explains each stage.

Shot-by-shot reconstruction

0.0s-14.0s
Open on the raw green-screen performance clip of the presenter facing and walking toward camera. The lower talking-head frame introduces the idea of turning this simple source footage into a polished AI VFX shot.

14.0s-28.0s
Show the workflow combination visually: the Kling green-screen video on one side, a generated environment image on the other, and a Kling O1 Edit label or module in between. This section should make clear that AI editing is being layered onto standard source footage.

28.0s-48.0s
Switch to an Illustrator-style canvas displaying a strong black-and-white radial or angular geometric graphic. The presenter explains that this designed element becomes part of the final visual transition or reveal, adding professional polish beyond the AI output alone.

48.0s-67.3s
Show the composited result, where the green-screen subject is integrated into a stylized environment with shape-based wipes or angular reveal elements. End on the final VFX shot and a CTA inviting viewers to comment “AI” for the workflow link.

Visual style
Vertical AI VFX tutorial, clean software-demo presentation, green-screen source clip, dark interface backgrounds, geometric design overlays, creator talking-head guidance, no cinematic scene changes beyond workflow steps.

Motion notes
Motion should come from transitions between source clip, workflow cards, graphic design canvas, and final composited result. Preserve the same subject identity and green-screen clip so the audience can follow the full before-to-after pipeline.

Negative prompt
messy interface, unreadable labels, unrelated effects, extra presenters, watermark, subtitles unrelated to tutorial, random footage swaps, non-geometric graphics, broken green-screen edges, non-AI workflow sections, shaky handheld filming

Speech pack
English creator narration explaining how Kling O1 Edit in Higgsfield works with green-screen footage, generated environment images, Illustrator graphics, and After Effects compositing to produce a polished VFX shot.

GLOBAL LOCK: A short dreamlike first-person landscape reveal video that begins with a human hand reaching toward a soft blurred surface and then opens into a glowing sunset mountain lake panorama. Keep the color world warm and painterly: olive-green water or mist in the opening, then deep gold, orange, amber, and red in the sky, with dark mountain ridges and reflective lake water below. The style should feel like moving through a painted memory or oil-painted dreamscape rather than strict realism. The camera begins extremely close and abstract, then pulls back or resolves into a stable scenic vista. No speech. Treat the sequence as an ambient reveal from tactile intimacy into vast luminous nature.

[00:00-00:03] Open in first-person view with a single human hand reaching down toward a soft greenish water or mist surface. The fingers are spread, sleeve dark, and the environment is abstract and blurred, as if the viewer is touching a dream. The motion is slow and searching, with no visible horizon yet.

[00:03-00:05] The hand remains in frame as the blurred surface begins to streak and resolve, hinting at reflection and distance. The image transitions from tactile closeup into something broader, with warm orange light bleeding in from the upper right.

[00:05-00:08] Pull fully into a wide fantasy landscape: a low red sun sits near the horizon above layered mountain ridges, while a glassy lake reflects the burning sky. The painterly texture remains soft and brushed, like an oil painting brought gently to life. The hand disappears, leaving only the landscape.

[00:08-00:11] Hold on the sweeping mountain-and-lake panorama. Cloud textures in the sky ripple with orange and copper light, and the water mirrors the scene in muted streaks. The camera stays calm, allowing the color gradient and depth to dominate.

[00:11-00:12.6] End on the same wide sunset tableau, preserving the meditative mood, the low red sun, and the reflective water below the mountains. No text overlays, no people, no dialogue, no sudden motion.

NEGATIVE PROMPT: avoid photoreal documentary style, city elements, extra figures, blue midday sky, harsh modern detail, shaky camera, muddy reflections, text overlays, watermarks, speech, lip-sync, or any narrative event that breaks the dreamlike reveal.

SHOT PROMPTS:
- Shot 1 delta: first-person hand over soft greenish blurred surface with tactile, dreamlike intimacy.
- Shot 2 delta: abstract blur opens with warm orange light entering as the scene resolves.
- Shot 3 delta: wide sunset mountain lake reveal with low red sun and painterly reflections.
- Shot 4 delta: hold the glowing landscape in calm panoramic stillness.

SPEECH PACK:
- Reference audio behavior: no dialogue, no narration, no lip-sync requirement, sequence should run over soft ambient cinematic music only.
- Segment [00:00-00:05] TAKE_A: intimate ambient texture only, no vocals. TAKE_B: nonverbal dreamlike sound bed. TAKE_C: soft atmospheric intro only.
- Segment [00:05-00:12.6] TAKE_A: warm scenic ambient swell, no speech. TAKE_B: fully nonverbal landscape reveal music. TAKE_C: gentle outro ambience with no speech sync.

An educational social media tutorial video featuring a creator speaking directly to camera in a warm studio setup with a microphone, while explaining how to create ultra-realistic AI short videos using Gemini and strong prompt structure. The video alternates between the presenter’s talking-head delivery, on-screen examples of cinematic black-and-white and neon portrait references, and screen recordings of the Gemini interface where prompt steps are entered and refined. The teaching focuses on building believable results by specifying image type, realistic imperfections, natural expressions, subtle scenarios, and human behavior details, then encouraging viewers to comment for the prompt. The tone is practical and creator-focused, combining expert AI workflow advice, UI walkthroughs, and before-and-after inspiration in a concise Instagram tutorial format.

GLOBAL LOCK: Vertical 9:16 abstract audiovisual visualizer with no characters. A radiant white-pink light core sits at the center of a dark tunnel-like void while long neon beams in cyan, teal, coral, orange, and red streak inward and outward symmetrically. The camera continuously rushes through the tunnel toward the glowing center, creating a hyperspace or light-speed sensation. High contrast, glossy bloom, soft haze, clean digital texture, immersive club-visual energy, perfectly centered composition, no text or logos.

[00:00-00:02] A bright central flare anchors the frame while evenly spaced neon bars extend from the center toward the edges like a starburst tunnel. The camera begins a smooth forward push into the glowing core.

[00:00:02-00:05] The tunnel deepens as the beams lengthen and slide past faster, with alternating cyan and warm red-orange rails creating a balanced radial pattern. The light bloom breathes subtly while the center remains fixed and dominant.

[00:00:05-00:07] The motion intensifies into a stronger hyperspace glide. Some bars appear thicker and closer to camera, increasing depth and speed, while the central white-pink point burns brighter and the surrounding haze softens the transitions.

[00:00:07-00:10] The final stretch pushes hardest through the neon corridor, with beams streaking rapidly across the vertical frame and converging into the same luminous center. End still locked on the glowing core, preserving the trance-like symmetry and forward momentum.

NEGATIVE PROMPT: people, faces, objects, landscapes, text overlays, logos, glitch artifacts, muddy colors, low contrast, dirty noise, broken symmetry, matte flat lighting, cartoon outlines, watermark

SPEECH PACK: No speech. Pure abstract visualizer energy only, suitable for instrumental or beat-driven accompaniment.

GLOBAL LOCK: A group of four diverse friends (two Black women, one Caucasian woman, one Black man) in their early 20s. They are dressed in casual 90s-inspired denim outfits: denim jackets, light-wash jeans, and white t-shirts. The setting is a rooftop parking lot at sunset with a hazy city skyline in the distance. The lighting is warm "Golden Hour" with strong backlighting, creating rim light on hair and soft lens flares. The color grade is cinematic with warm oranges and deep blues. The camera has a slight handheld jitter for a realistic feel.

[00:00–00:03]
The group is leaning against the back of a dark grey hatchback car with the trunk open. The woman on the far left is throwing her head back in a deep, genuine laugh. The woman in the center is clapping her hands together joyfully. The man on the right is smiling and looking at his friends. Wide shot showing the car and the city horizon. High-fidelity motion, hair blowing slightly in the breeze.

[00:03–00:06]
Medium close-up on the three women. The central woman with curly hair is leaning forward, laughing intensely, her shoulders shaking. The woman to her left has her eyes closed in laughter. The lighting is very warm, catching the edges of their denim jackets. The camera pans slightly to the right.

[00:06–00:10]
The man on the right reaches out a hand to pat the shoulder of the woman next to him. The group continues to laugh and interact. The sun is lower now, creating a more dramatic orange glow across the scene. The city lights in the background begin to twinkle. The motion is fluid and natural, capturing the micro-expressions of joy.

NEGATIVE PROMPT: Robotic movement, frozen faces, distorted limbs, flickering lighting, blurry textures, inconsistent clothing, morphing backgrounds, low resolution, watermarks, text, cartoonish style, unnatural skin tones.

SPEECH PACK:
[00:00-00:10]
Transcript: "[Laughter] ... That is so funny! ... [Laughter]"
TAKE_A: High-pitched, energetic group laughter with a clear "That is so funny!" in the middle.
TAKE_B: More wheezing, breathless laughter with a muffled "Oh my god" instead of the main line.
TAKE_C: Relaxed, chuckling laughter with a very clear, enunciated "That is so funny!" at the 7-second mark.
Prosody: Natural pauses for breath, overlapping voices, warm and friendly tone.
Sync: High lip-sync strictness for the "That is so funny" line if the central woman is on camera.

GLOBAL LOCK: Vertical 9:16 abstract cyber-architecture visualizer with no people. A long symmetrical futuristic corridor stretches into a central vanishing point, lined with glowing blue, cyan, violet, and magenta light panels. The floor is glossy and mirror-like, reflecting the neon strips and creating a tunnel effect. The camera glides forward continuously through the hallway, maintaining perfect central alignment, sleek sci-fi polish, soft bloom, and high-contrast nightclub color separation.

[00:00-00:02] The corridor opens in deep blue-violet tones, with bright cyan ceiling and floor rails pulling the eye to the central vanishing point. The camera begins a smooth forward push down the middle of the tunnel.

[00:00:02-00:05] The forward motion continues as side-wall panels pulse between cool blue and warmer violet-magenta. Reflections on the polished floor intensify the symmetry, making the hallway feel doubled and endless.

[00:00:05-00:07] The tunnel appears to accelerate slightly. The lighting grows brighter and richer, with more magenta filling the side chambers while the cyan center line remains the dominant guide through the frame.

[00:00:07-00:09] The corridor reaches peak saturation and glow, with blue and purple strips streaking past more quickly. The centered composition stays locked, preserving a trance-like, music-visualizer rhythm.

[00:00:09-00:10] The final second blooms into a brighter pink-white wash at the far end of the tunnel, as though the camera is entering an illuminated portal. The corridor remains visible beneath the glow, ending on a luminous sci-fi crescendo.

NEGATIVE PROMPT: people, vehicles, furniture, text, logos, grime, broken geometry, asymmetry, low contrast, muddy colors, matte surfaces, cartoon rendering, watermark, exterior scenery

SPEECH PACK: No speech. Pure abstract corridor motion intended for beat-driven or ambient accompaniment only.

GLOBAL LOCK: build this as a premium AI cinema sizzle reel made of distinct but coherent high-end cinematic moments, each shot fully polished and self-contained, with no cheap transitions, no text overlays except where naturally present in the environment, and no spoken dialogue. Every segment must feel like a frame from a different finished film while still sharing a prestige studio-grade finish, sharp composition, controlled lighting, dramatic color separation, and confident camera language.

0.00-1.00 — A young man stands in profile beside a rain-streaked glass wall in a dim modern interior. Warm light glows from a room behind him while cold blue light bleeds through the wet textured glass. He stares outward, motion minimal, camera slow and contemplative.

1.00-2.00 — Warm interior dinner-table close-up of the same young man turning slightly while candlelight and soft amber practicals shape his face. A shallow-focus foreground object glows at frame bottom. Intimate dramatic lighting, subtle eye movement, no dialogue.

2.00-3.00 — A muscular Black man stands outside a transparent glass cube room in a bright futuristic gallery. Inside the cube, a woman sits still on a bench under cool white light. Clean architectural lines, high-key sci-fi minimalism, symmetrical framing.

3.00-4.00 — Neon city night close-up of a hooded young man in an orange hoodie and glasses, walking past magenta and cyan signage. Wet cyberpunk reflections, side profile, slow drift, urban future mood.

4.00-5.00 — Repeat the hooded neon character from a slightly different angle, maintaining the same magenta-blue skyline atmosphere and calm forward movement. Keep the frame elegant, not action-heavy.

5.00-6.00 — In a dense vertical bamboo forest, two figures leap and collide mid-air in a wuxia-style fight. White and blue garments streak across the green shafts of bamboo. Freeze the motion into a graceful suspended action tableau.

6.00-7.00 — A moustached man in a purple hotel-bellhop-inspired uniform strides directly toward camera in a warm luxury corridor while staff rush in the background. Strong central perspective, comic-confidence energy, cinematic hotel lighting.

7.00-8.00 — Extreme macro of a human iris with golden amber center and blue-grey outer ring. High detail eyelashes, glossy eye moisture, tiny reflections, pure ocular spectacle.

8.00-9.00 — Nighttime inside a yellow taxi: a rugged man sits in the back seat lit by city reflections and passing neon. Moody crime-drama tone, close framing through the window.

9.00-11.00 — Tight hallway fight in a dim stairwell or elevator corridor. Two people struggle in cramped greenish light, bodies slamming into the walls, handheld intensity but still legible action. Keep it gritty and physical.

11.00-12.00 — A lone cloaked figure stands in a desert facing a palace-like skyline in the distance at dawn or sunset. Sand haze, pastel sky, mythic scale, cape trailing, iconic silhouette.

12.00-13.00 — Hold the cloaked desert figure from a slightly adjusted angle to deepen the epic fantasy image. The palace should remain luminous in the background.

13.00-14.60 — Night exterior of a luxurious glass pavilion surrounded by reflective water. A ceiling of hanging green reeds or illuminated strands floats overhead while pink and teal lighting glows from the far end. Still, architectural, dreamlike closing shot that sells the future of AI cinema as visual range.

ENVIRONMENT: multi-genre cinematic anthology covering rain-soaked modern drama, warm candlelit interior drama, minimalist sci-fi architecture, cyberpunk neon street, bamboo wuxia action, hotel-comedy corridor, ocular macro, taxi crime drama, cramped fight sequence, epic desert fantasy, and luxury glass pavilion architecture.
CAMERA: slow dramatic push-ins, composed portrait frames, one suspended action shot, one macro eye insert, one cramped fight camera, one iconic wide fantasy silhouette, one architectural final hold.
LIGHTING: blue rain glow, amber candle practicals, cool white gallery light, magenta-cyan neon, diffuse green forest light, warm corridor sconces, glossy ocular catchlights, moody taxi reflections, sickly hallway top light, peach desert sky, jewel-toned architectural night lighting.
GRADE: premium festival-trailer finish, deep contrast, clean blacks, saturated but controlled color separation, each scene preserving its own genre identity.
MOTION: restrained in character shots, kinetic only in the bamboo collision and hallway fight, majestic stillness in the desert and pavilion finale.
SPEECH: no dialogue, no mouth-synced talking, purely visual sizzle reel.

NEGATIVE PROMPT: cheap montage transitions, random stock footage feel, low-resolution faces, muddy grading, inconsistent lens language, generic city timelapse, extra text overlays, subtitles, distorted anatomy, comedic slapstick in serious shots, flat corporate lighting, oversharpened CGI, cluttered frames, low-detail environments.

SPEECH PACK: silent cinematic montage, no spoken lines, no narration, no captions.

INVARIANTS TO LOCK
- Vertical 9:16 split-comparison Reel.
- Same young adult white male creator in every shot: light skin, slim build, side-swept brown hair, clean-shaven, expressive face.
- Neutral studio setup with soft gray background, clean frontal lighting, medium framing from chest to head.
- Video alternates between “Original:” and “AI:” versions of the same gesture performance.
- The AI versions keep the exact body movement and timing, but swap wardrobe, accessories, and visual effects.
- Tone is demo-first, highly legible, fast, and social-native.

SHOTLIST
1. [00:00-00:02] AI label over a dark tactical outfit, then a red-and-blue spider-inspired superhero suit, then a brown aviator jacket with patches and sunglasses. Matching “Original:” frames underneath show the presenter in a plain black shirt doing the same finger snap gesture.
2. [00:02-00:05] The comparison continues with the aviator look in a warmer room setting with vertical blinds and a plant, still mirroring the original hand choreography.
3. [00:05-00:07] Fire effects appear behind and around the AI version while the original remains clean and unstyled below.
4. [00:07-00:09] Large subtitle CTA appears over the AI version: comment “AI” for guide. Final frames push the fiery transformation while the original keeps the same open-handed pose.

STYLE BIBLE
Visual style: creator demo of motion-consistent character transformation.
Camera signature: locked tripod, eye-level medium shot, no camera movement.
Lighting signature: soft even front light on the original clip; AI variants maintain similar face lighting while changing wardrobe and environment mood.
Grade signature: clean studio neutrals in the original; richer contrast and warmer highlights in the AI versions.
Speech style: brief solo creator commentary or silent caption-driven demo; if voice is present, it should sound casual, impressed, and direct.

MASTER PROMPT
GLOBAL LOCK: Create a vertical 9:16 Instagram Reel that compares an original studio performance against AI-transformed outputs. Use the same young adult white male creator with light skin, slim build, side-swept brown hair, and clean-shaven face throughout. Keep the original clip on a soft gray studio background with the creator in a plain fitted black shirt, medium framing, frontal lighting, and simple hand gestures. Every AI version must preserve identical timing, pose, eye line, and hand motion, while changing outfit, accessories, background mood, and effects. Use bold yellow labels “AI:” and “Original:” so the comparison is instantly readable.

[00:00-00:02] Show the creator snapping or flicking his fingers in sync across paired comparison frames. In the AI version, first dress him in a dark armored tactical costume, then switch to a red-and-blue spider-inspired superhero suit, then to a brown aviator jacket with sewn patches and black sunglasses. In the original version, keep the same gesture in a plain black shirt against a gray backdrop.

[00:02-00:05] Continue the gesture-matched comparison. The AI variant now settles into the aviator look in a warmer cinematic room with vertical blinds and a leafy plant, preserving exact mouth shape and hand timing from the original clip. The original remains unchanged below, emphasizing how the motion has been transferred rather than reanimated from scratch.

[00:05-00:07] Add stylized flames behind the AI character and subtle orange light wrapping around the jacket sleeves. Keep the original clip clean and neutral for contrast. Maintain sharp alignment between both performances so viewers can read the transformation as one-to-one motion mapping.

[00:07-00:09] End with the most dramatic fiery aviator transformation while overlaying a clear CTA: comment “AI” for guide. The original clip still mirrors the same open-handed pose. Finish on a high-energy, creator-demo beat.

NEGATIVE PROMPT
Do not drift the face identity, hairstyle, body proportions, or gesture timing between original and AI versions. Avoid extra fingers, broken sunglasses, distorted jacket patches, muddy flames, inconsistent eye direction, unreadable labels, flickering backgrounds, or cartoonish facial deformation. Do not let the AI transformation lose the exact one-to-one motion match with the original clip.

SPEECH PACK
[00:00-00:04] Speaker A, direct-to-camera, meaning: this is how the same motion can be restyled with AI. Delivery: short, confident, creator-demo cadence.
TAKE_A: “Same motion, completely different character styling.”
TAKE_B: “This is the exact same performance, just transformed with AI.”
TAKE_C: “Watch how the motion stays locked while the look changes.”

[00:04-00:09] Speaker A or on-screen text, meaning: these tools save creators time and a guide is available by comment. Delivery: casual CTA.
TAKE_A: “Comment AI if you want the full guide.”
TAKE_B: “If you want the workflow, comment AI below.”
TAKE_C: “Comment AI and I will send the guide.”

GLOBAL LOCK: 
Subject is a young South Asian woman with long, wavy dark hair, wearing a dark purple/maroon sleeveless top. She holds a small black Rode wireless microphone. The environment is a cozy indoor room with a dark slatted wall, a neon "CYBORG" sign, and warm ambient lamps. The lighting is cinematic with soft key light and subtle blue/pink highlights. The color grade is saturated with a slight filmic grain and chromatic aberration. The speech is a direct-to-camera tutorial delivered with high energy and crisp articulation.

[00:00–00:02]
Close-up of a hand holding a gold iPhone. Glowing blue holographic AR text overlays surround the phone, reading "THE iPhone 17 PRO MAX", "Pro Camera System", and "Cinematic Video". The text is perfectly anchored to the phone's movement. The background is a dark, textured wall.

[00:02–00:05]
Medium close-up of the woman talking directly to the camera, holding the Rode mic. She is smiling and expressive. The background shows a blurred room with warm lights and a "CYBORG" sign.
Speech: "This effect is called the tracking effect. And here's..."

[00:05–00:08]
Point-of-view shot of a hand holding the iPhone against a dark slatted wall, moving it slightly. A yellow focus square is visible on the screen, mimicking a camera UI.
Speech: "...how you can do it under 30 seconds. Step 1: Pick up your favorite item and film it like this."

[00:08–00:20]
Screen recording of a mobile AI chat interface (labeled "Banana Pro"). A screenshot of the phone is uploaded. The user types: "turn this image into a 3d text anchored to the object. 'THE IPHONE 17 PRO MAX' 'Pro Camera System' 'Cinematic Video' 'Powered by A18 Pro'".
Speech: "Take a screenshot of the last frame and upload it to Banana Pro. Now prompt: turn this image into a 3D text anchored to the object along with the text you want to see on the screen."

[00:20–00:22]
A static image result showing the iPhone with the requested blue holographic text perfectly positioned around it.
Speech: "You will get an output like this."

[00:22–00:27]
Screen recording of the Kling AI interface. The user uploads the original video and the AI-generated image. A long technical prompt is visible in the text box.
Speech: "Step 2: Now head to Kling, upload the output and the video you just took. Prompt this, hit generate..."

[00:27–00:31]
The final video result: The hand moves the iPhone, and the blue AR text follows the motion with zero jitter, looking like a real-world holographic overlay.
Speech: "...and boom! You have this super cool effect as well."

[00:31–00:35]
Back to the medium close-up of the woman. She gestures with her hands while holding the mic.
Speech: "And for cool AI hacks as such, follow the Cyborg Girl for more."

NEGATIVE PROMPT:
Visual: Jittery tracking, text sliding off the object, blurry text, distorted hand anatomy, flickering lights, inconsistent background, low resolution, watermarks.
Speech: Robotic tone, muffled audio, background noise, lip-sync mismatch, stuttering, flat delivery.

SPEECH PACK:
[00:00-00:05] "This effect is called the tracking effect. And here's how you can do it under 30 seconds."
TAKE_A: (Energetic, fast-paced) "This effect is called the tracking effect! And here's how you can do it... under 30 seconds."
TAKE_B: (Informative, clear) "This effect is called the tracking effect. And here is how you can do it in under thirty seconds."

[00:05-00:15] "Step 1: Pick up your favorite item and film it like this. Take a screenshot of the last frame and upload it to Banana Pro."
TAKE_A: "Step 1! Pick up your favorite item and film it... just like this. Take a screenshot of that last frame and upload it to Banana Pro."

[00:15-00:25] "Now prompt: turn this image into a 3D text anchored to the object along with the text you want to see on the screen. You will get an output like this. Step 2: Now head to Kling."
TAKE_A: "Now prompt: turn this image into a 3D text... anchored to the object... along with the text you want to see. You'll get an output like this. Step 2! Head over to Kling."

[00:25-00:35] "Upload the output and the video you just took. Prompt this, hit generate and boom! You have this super cool effect as well. And for cool AI hacks as such, follow the Cyborg Girl for more."
TAKE_A: "Upload the output and the video you just took. Prompt this, hit generate... and BOOM! You have this super cool effect. For more AI hacks, follow the Cyborg Girl!"