AI Green Screen Meme

Core format and topic lock: a vertical creator tutorial about using Runway Aleph or a similar in-context AI video editor to replace background, lighting, and clothing in video clips. The video uses a bald male subject as the demonstration character, showing before/after edits, green-screen style isolation, character-image inputs, driving-video inputs, and transformed outputs in different roles and environments such as a professional kitchen and a desert setting. A male presenter in a rounded webcam frame explains the workflow beneath the examples.

Shot-by-shot reconstruction

0.0s-12.0s
Open on a stacked before-and-after example of a bald male subject seated at a table. The lower example introduces a green replacement area or edited plate to demonstrate how the background can be swapped while preserving the subject.

12.0s-24.0s
Show the editing interface where the creator adds or references the subject image. Keep the focus on how the system understands the character identity as an editable element rather than just raw footage.

24.0s-42.0s
Display a transformed output where the same bald subject appears as a chef-like figure inside a commercial kitchen. The person remains recognizable while the environment, wardrobe cues, and overall scene treatment change.

42.0s-59.7
Show a more explicit character-image plus driving-video workflow with model selection and settings. End on comparison shots proving the same identity can be remapped into multiple contexts, such as a desert scene and a kitchen scene, demonstrating combined background, lighting, and clothing edits.

Visual style
Vertical AI editing tutorial, dark app interface, talking-head explainer overlay, clear before/after examples, practical creator-workflow presentation, no cinematic scene changes beyond app windows and example swaps.

Motion notes
Motion should come from interface navigation, example swaps, and the presenter’s gestures. Keep the same subject identity throughout the clip so the audience can clearly judge how the model changes environment and wardrobe while preserving facial consistency.

Negative prompt
messy UI, unreadable settings, extra presenters, watermark, subtitles unrelated to tutorial, random unrelated footage, broken face consistency, nonhuman subjects, unstable frame crops, complex cinematic montage unrelated to the workflow

Speech pack
English tutorial narration explaining how to swap backgrounds, relight scenes, and change clothing in video by combining a source character image, a driving clip, and the Runway Aleph editing workflow.

GLOBAL LOCK:
Subject is a Caucasian male, mid-30s, with a well-groomed dark beard and mustache. In the cinematic sequence, he is wearing a full suit of polished silver medieval knight armor with intricate engravings. He wears a dark green baseball cap backwards under his helmet or as a stylistic choice. The environment is a dramatic, smoky battlefield with an overcast, moody sky and orange flames/explosions in the background. The color grade is cinematic, desaturated with high contrast and warm highlight roll-off from the fires. Camera movement is dynamic, following the subject.

[00:00–00:05]
Split-screen view. Bottom: Creator talking to camera in a white/black striped hoodie and "VANS" cap. Top: A dark digital interface showing a node-based workflow with lines connecting "Creation," "Text," and "Image Generator" boxes. The creator points down toward the microphone.

[00:05–00:10]
Top screen: A full-body photo of the male subject in a white t-shirt and striped pants against a white wall. The background of the photo then turns into a bright, solid green screen.

[00:10–00:15]
Top screen: Individual 3D-rendered silver armor pieces (gauntlet, chest plate, greaves) float around the subject on the green screen, then snap onto his body, replacing his clothes.

[00:15–00:25]
Top screen: The subject, now in full knight armor, is seated on a majestic white horse. The background is still a green screen. A white horse asset appears and he is composited onto it.

[00:25–00:45]
Top screen: A cinematic wide shot of the knight on the white horse galloping through a war-torn field. Thick grey smoke billows behind him. He holds a large red and green flag with a "GenHQ" logo that waves violently in the wind. Explosions of orange fire erupt in the background. The camera tracks the horse's movement with a slight handheld shake.

[00:45–00:51]
The cinematic knight sequence continues. Large white text "Comment 'AI'" is centered on the screen. The creator in the bottom frame continues to speak and gesture enthusiastically. The horse slows to a trot as the flag continues to wave.

NEGATIVE PROMPT:
Visual: robotic movement, distorted face, inconsistent armor textures, blurry horse legs, floating objects, cartoonish colors, low resolution, flickering lighting, extra limbs, text/logos other than specified.
Speech: robotic tone, muffled audio, background noise, lip-sync mismatch, stuttering, flat delivery.

SPEECH PACK:
[00:00–00:05]
"This new method of creating AI generated content gives us so much control over the output."
TAKE_A: (Enthusiastic, fast-paced) "This new method of creating AI generated content gives us so much control over the output!"
TAKE_B: (Authoritative, measured) "This new method... of creating AI generated content... gives us so much control over the output."
TAKE_C: (Casual, friendly) "Check this out—this new AI method gives you total control over what you're making."

[00:45–00:51]
"So if you want to try this out for yourself, type AI in the comments and I'll send you the link."
TAKE_A: (Direct, urgent) "So if you want to try this out for yourself, type AI in the comments and I'll send you the link!"
TAKE_B: (Warm, inviting) "Want the link? Just type AI in the comments and I'll send it right over."
TAKE_C: (Punchy, instructional) "Type AI below and I'll DM you the link to try this yourself."

GLOBAL LOCK:
Subject: 20-year-old South Asian woman, warm skin tone, dark hair tied in a sleek ponytail, black sleeveless tank top, minimalist aesthetic.
Environment: Consistent subject identity across all shots, but background transitions from a neutral indoor office to various cinematic outdoor locations.
Lighting: Transitions from soft indoor ambient light to environment-specific lighting (golden hour, harsh sun, neon).
Camera: Eye-level MCU, mostly static with subtle organic movement.
Speech: Warm, energetic female voice, clear articulation, direct-to-camera address.

[00:00–00:03]
Subject: Split-screen view. Top half shows the woman in a neutral indoor office. Bottom half shows her in a misty, sun-drenched forest with ferns.
Action: She looks up and to the right, then turns her head slowly.
Camera: Static split-screen, MCU.
Lighting: Top is flat indoor; Bottom is cinematic golden hour with light rays (god rays) through trees.
Grade: Bottom has a warm, earthy, high-contrast cinematic grade.
Motion: Subtle hair movement, drifting mist in the background.

[00:04–00:07]
Subject: The woman holding a small black wireless microphone close to her mouth.
Action: Speaking directly to the camera, gesturing with her free hand.
Environment: Neutral indoor background with a plant and a modern sculpture.
Camera: MCU, static.
Lighting: Soft natural light from the side.
Speech: "You can take shots without any heavy editing skills, and let me show you how."
Sync: High lip-sync strictness; cut lands on "how."

[00:08–00:14]
Subject: The woman seen through a smartphone camera UI.
Action: She holds up her own phone as if taking a selfie, looking around "silly" at the empty room.
Environment: Indoor office.
Camera: Handheld feel, looking at a phone screen.
Lighting: Standard indoor.
Speech: "Step 1: Record a video of yourself acting like you are in your desired shot. This might look a little silly."
Sync: VO over action.

[00:15–00:19]
Visual: Screen recording of the "Banana 2" web interface. A screenshot of the woman is uploaded.
Action: Cursor clicks "Generate" after a prompt is typed: "Replace indoor setting with a realistic outdoor scene... misty forest... cinematic."
Lighting: UI dark mode.

[00:20–00:28]
Visual: Screen recording of the "Kling" AI interface. The original video and the generated forest image are uploaded.
Action: Cursor clicks "Generate." The result shows the woman seamlessly integrated into the forest.
Speech: "Step 2: Now head to Kling, go to video generation option, add your video and the reference picture. Prompt this, hit generate, and wallah!"
Sync: VO over UI action.

[00:29–00:36]
Visual: Screen recording of ChatGPT.
Action: Typing a request for a "similar prompt for visiting a lively city." ChatGPT generates a new prompt.
Subject: Inset of the woman in the Times Square background, holding her phone.
Speech: "I will leave the prompt in the comments section. And if you want to change the scene, take this prompt to ChatGPT and describe what you want and you will get a brand new prompt."
Sync: VO over UI and inset video.

[00:37–00:40]
Subject: The woman speaking to the camera, holding the mic.
Action: Smiling, pointing to the screen. Text "the CYBORG girl" appears in neon pink.
Environment: Indoor office.
Speech: "Ready? And for cool AI hacks as such, follow the Cyborg Girl for more."
Sync: High lip-sync strictness.

NEGATIVE PROMPT:
Visual: Blurred face, inconsistent hair texture, extra fingers, warped background geometry, flickering lighting, low resolution, watermarks, distorted limbs, unnatural skin smoothing.
Speech: Robotic tone, muffled audio, background noise, lip-sync delay, harsh "S" sounds, inconsistent volume.

SPEECH PACK:
[00:04–00:07]
Transcript: "You can take shots without any heavy editing skills, and let me show you how."
TAKE_A: Warm, encouraging, medium pace.
TAKE_B: Fast, energetic, "hacker" vibe.
TAKE_C: Slow, deliberate, authoritative.

[00:08–00:14]
Transcript: "Step 1: Record a video of yourself acting like you are in your desired shot. This might look a little silly."
TAKE_A: Playful, slightly laughing on "silly."
TAKE_B: Instructional, clear steps.

[00:20–00:28]
Transcript: "Step 2: Now head to Kling, go to video generation option, add your video and the reference picture. Prompt this, hit generate, and wallah!"
TAKE_A: Exciting, building to the "wallah" reveal.
TAKE_B: Direct, tutorial-style.

[00:37–00:40]
Transcript: "Ready? And for cool AI hacks as such, follow the Cyborg Girl for more."
TAKE_A: Friendly, high energy, strong CTA.
TAKE_B: Professional, calm.

GLOBAL LOCK: vertical 9:16 creator-style AI demo video explaining how to turn an ordinary room recording into a high-end studio look using HeyGen digital twin / AI avatar tools. The presenter is a young adult man with beard, dark cap, black shirt, and a black microphone, speaking directly to camera in a simple indoor room. The core visual mechanic is that while he continues talking in the same pose and framing, the background and overall environment transform into different premium studio or luxury spaces. Use bold white headline text at the top such as “THIS IS WILD” with a fire emoji in repeated sections, and later a “2 minutes” overlay during the payoff section.

[00:00-00:08] Open on the presenter in a plain neutral room, seated and speaking naturally into a microphone. The composition is centered and clean, with a minimal home-office vibe. Large top text reads “THIS IS WILD” to frame the demo as a surprising tool discovery. The creator gestures with his hands while explaining the capability.

[00:08-00:18] Without changing his body position too much, swap the background into a polished luxury studio or cinematic interior. One variation should feel like an upscale pink-toned set with arches and refined lighting; another should look like a designer mountain-view backdrop with large windows or rocky scenery. The point is that the presenter remains consistent while the environment upgrades dramatically.

[00:18-00:30] Continue cycling through premium virtual environments: a modern living room with ocean or pool view, a high-end apartment, and a bright architectural interior. Keep the presenter lighting believable and integrated so it feels like he was recorded in those spaces. The creator continues speaking directly to the audience about HeyGen and the speed of creating studio-quality backgrounds.

[00:30-00:40] Emphasize the transformation speed and usefulness for creators. Show another round of polished environments while preserving the same speaking performance, framing, and microphone setup. The visual message should be: one ordinary room recording can become many professional background looks without reshooting.

[00:40-00:59] End with a stronger UI-style or promo-style payoff. Introduce a “2 minutes” top text card over a soft gradient or glow-backed composition that frames the presenter as if inside a premium AI video product ad. The last section should feel like a clean branded conclusion: high-quality AI avatar output, studio-grade backgrounds, and content-ready presentation in minutes.

VISUAL DNA:
- Same male presenter throughout, seated and speaking into microphone.
- Repeated background swaps into luxury studio, architectural, or scenic high-end environments.
- Bold top text like “THIS IS WILD” and later “2 minutes.”
- Creator-economy ad / demo energy, not cinematic fiction.
- Clean direct-to-camera delivery with practical use-case framing.

STYLE LOCK:
- Social-native creator tutorial / ad hybrid.
- Realistic background replacement rather than fantasy visual effects.
- Emphasis on consistency of the speaker while the environment changes.
- Useful for creators, educators, and marketers wanting professional video presence.

NEGATIVE PROMPT: full body avatar walking around, no microphone, gaming stream layout, cartoon avatar, low-quality green-screen edges, chaotic meme montage, political content, horror styling, dark dystopian sets, no text overlays, no background variation, noisy office clutter, dramatic action scene, crowded room, subtitles burned in, unrelated app dashboard dominating the frame.

SHOT PROMPTS:
SHOT 1: plain-room talking-head creator with “THIS IS WILD” text.
SHOT 2: same speaker composited into luxury pink arch studio and scenic mountain backdrop.
SHOT 3: modern sea-view or high-end apartment studio background while creator keeps talking.
SHOT 4: repeated premium room transformations showing HeyGen-style consistency.
SHOT 5: final “2 minutes” payoff frame with polished AI-avatar studio presentation.

SPEECH PACK:
[00:00-00:59] Natural creator commentary explaining that HeyGen can turn any regular room recording into a professional-looking studio setup and digital twin style output without needing a complex physical set.

GLOBAL LOCK:
The video features a white male creator in his mid-30s with medium-length, wavy brown hair and a groomed beard, wearing a clean white t-shirt. He is positioned in a bright home office with a professional black condenser microphone on a boom arm in the foreground. The video uses a split-screen or multi-panel layout to compare "Source Video" (the creator) with "AI Generated Results" (various celebrities and characters). The AI characters must perfectly mirror the creator's head tilt, facial expressions, lip-sync, and hand gestures. The lighting is soft, natural window light from the side. The color grade is clean and realistic.

[00:00–00:03]
The screen is split into three vertical panels. Top panel: The creator waves both hands excitedly and points to his right. Middle panel: Sabrina Carpenter in a pink feathered dress mimics the exact hand wave and pointing. Bottom panel: Billie Eilish in a black outfit and sunglasses mimics the same gestures. High-fidelity lip-sync as they all say "Hear me out."

[00:03–00:07]
The layout shifts. Top panel: Creator continues talking with expansive hand gestures. Middle panel: Taylor Swift in a red dress mimics the gestures. Bottom panel: Kim Kardashian in a black tank top mimics the gestures. The transitions between characters are sharp cuts.

[00:07–00:10]
Split screen: Creator (top) vs. Queen Elizabeth II (bottom). The creator looks to his left and then back to the camera with a skeptical expression. The Queen, wearing a crown and sash, mirrors the look perfectly.

[00:10–00:13]
Split screen: Creator (top) vs. Edna Mode from The Incredibles (bottom). The creator scratches the top of his head with his right hand. Edna Mode, with her signature bob and glasses, scratches her head in perfect sync.

[00:13–00:20]
A screen recording of a software interface (Enhancor). A cursor selects the "Wan2.2" model from a dropdown menu. The UI shows a "Source Video" of the creator and a "Character Image" of a woman. The cursor toggles "Pro Mode" on and adjusts resolution to 720p.

[00:20–00:23]
Split screen: Creator (top) vs. a woman with long brown hair in a floral dress (bottom). They are both in the same room. The creator raises his hands in a "stop" gesture; the woman mirrors him perfectly.

[00:23–00:27]
The UI returns, showing the "Photo Animate" tab being selected. A different reference photo of the same woman is used. The cursor clicks "Generate Video."

[00:27–00:35]
Final comparison. Split screen: Creator (top) vs. the woman (bottom). The creator looks around the room and then smiles at the camera while touching his hair. The woman mirrors the hair-touching and the smile, but her background is now a different indoor setting matching her reference photo. The text "AI" appears centered on the screen.

NEGATIVE PROMPT:
Visual: flickering faces, distorted limbs, extra fingers, blurry textures, face-swapping artifacts, unnatural skin smoothing, background warping, robotic movements, low resolution, watermarks.
Speech: robotic voice, mismatched lip-sync, muffled audio, background noise, unnatural pauses, clipping audio.

SPEECH PACK:
[00:00–00:07]
Transcript: "Hear me out, all of your favorite movies and animations are going to be completely acted out by someone else in the next two years."
TAKE_A: Energetic, fast-paced, direct-to-camera.
TAKE_B: Mysterious, slightly slower, emphasizing "completely."
TAKE_C: Casual, conversational, like a friend sharing a secret.

[00:07–00:13]
Transcript: "So I'm going to teach you everything you need to know about this in the next 20 seconds so that you can do this for yourself and stay ahead of the curve."
TAKE_A: Authoritative, instructional, rhythmic.
TAKE_B: Helpful, warm, encouraging.
TAKE_C: Urgent, fast-talking to fit the "20 seconds" claim.

[00:13–00:35]
Transcript: "So right now you have two options with this new AI video model called Wan 2.2. The first option is Character Swap... The second option is Photo Animate... This is absolutely mind-blowing. Comment AI for the link."
TAKE_A: Professional narrator style, clear enunciation.
TAKE_B: Enthusiastic, high energy on "mind-blowing."
TAKE_C: Calm, tech-reviewer tone, clear CTA at the end.

GLOBAL LOCK: One energetic male creator in his 20s or early 30s with light skin, blue eyes, side-parted brown hair, clean-shaven face, slim build, and expressive hand gestures. He wears a light heather-gray quarter-zip sweater over a black crew-neck shirt in the live talking-head setup, then appears in AI-generated variants that preserve the same facial identity and pose logic while changing outfit and environment. The primary environment is a dark studio with a charcoal textured backdrop, soft front key light, and a warm amber practical glow on frame right, captured in vertical 9:16 social-video framing with crisp digital sharpness and polished creator-economy reel pacing. The video alternates between direct-to-camera speaking shots and dark-mode screen recordings of the Freepik Spaces workflow, including prompt writing, list generation, export controls, and image generation results. Speech style is single-speaker direct-to-camera tutorial delivery, upbeat and persuasive, close mic podcast sound, clear articulation, medium-fast cadence, with the vocal energy matching quick edit beats and UI reveal moments.

[00:00-00:04] Split-screen comparison card fills the frame with bold labels "AI:" on top and "Original:" below. The same man appears in both panes, facing camera with both hands raised outward in a shrug-like gesture. In the AI version the background becomes a warm cinematic fire-lit room and he wears dark sunglasses and a red leather jacket; in the original he remains in the gray quarter-zip against the dark studio wall. Static vertical framing, no camera move, quick proof-of-result opener, bright contrast between black interface borders and warm highlight tones.

[00:04-00:09] Cut to a medium talking-head shot of the creator in the original studio. He speaks directly to camera with animated eyebrows and open palms, the black podcast microphone entering frame center-low on a boom arm. Lighting stays soft on his face with a subtle amber rim on the right side of the background. Cadence is enthusiastic tutorial speech introducing how easy the workflow is. Lips are clearly visible and should stay tightly synced.

[00:09-00:14] Screen recording overlays a cropped preview of the creator image inside a workspace. The viewer sees the original portrait being placed into a design or editing canvas while the creator continues voiceover or on-camera speech. UI motion is cursor-driven, smooth, and deliberate. The inserted image keeps his raised-finger pose and neutral studio background. Edits land on verbal emphasis.

[00:14-00:22] A dark chat-style prompt box fills most of the screen. Long prompt text instructs the model to analyze the attached image and create a list of prompts for changing the background and clothing without changing the person’s pose, expression, or hand position. Buttons such as export options and model selection are visible. The creator remains visible in a smaller lower panel, continuing to explain the exact workflow in an energetic, confident voice. Keep the interface text dense, dark-mode, and product-demo realistic.

[00:22-00:28] Return to a cleaner talking-head layout with the man framed medium close-up, microphone prominent, and both hands gesturing toward the viewer. He stresses that viral-looking outputs can be made with just drag-and-drop simplicity. The studio remains unchanged: dark textured wall, warm orange glow on the right, sharp digital focus, no handheld shake.

[00:28-00:34] Screen recording reveals an "Image generator" result card. The same creator identity now appears in a charcoal suit jacket and white shirt in front of a soft sunset city skyline. The original speaker continues explaining that Freepik Spaces can generate multiple polished variations from one source image. Cursor movement and UI panel transitions are clean and modern.

[00:34-00:41] Additional generated examples appear in sequence: the creator composited into a bright apartment while wearing black hat and sunglasses, then other stylish background changes that preserve body pose and face structure. The talking-head layer remains below or between inserts, with him pointing and timing gestures to the reveals. Keep the contrast between real studio footage and AI outputs very clear.

[00:41-00:47] The creator returns larger on screen, speaking directly into the mic with a persuasive call-to-action rhythm. His hands punctuate phrases as he says to comment for the link and try the workflow. Close-mic audio remains dry and intelligible, with no crowd noise or ambient distraction.

[00:47-00:53] Final UI-heavy montage shows Freepik template thumbnails and more generated scenes while the creator finishes the pitch. End with the feeling of a fast, practical product demo for creators chasing viral content: dark-mode interface, polished social edit timing, consistent identity preservation across AI outputs, and a confident single-speaker tutorial tone.

Create a vertical 9:16 futuristic AI product-promo visual centered on a hyper-realistic fashion portrait of a young woman with slicked-back hair, pale skin, blue-grey eyes, and bold matte red lipstick, wearing a reflective chrome silver high-collar outfit in a bright metallic environment filled with iridescent foil-like textures. Behind her, large bold yellow text reads Meta AI, integrated like a clean social-ad headline. The image should feel like a premium generative-AI campaign frame promoting free image generation and AI lip sync tools, combining polished beauty-editorial realism with tech branding. Keep the composition crisp, symmetrical, high contrast, and optimized for short-form creator marketing. No extra clutter, no subtitles, no cartoon styling, no unrelated props.

MASTER PROMPT
GLOBAL LOCK: Vertical 9:16 creator-education reel, photoreal direct-to-camera host in a warm amber studio. One Caucasian man in his late 20s to early 30s, fair skin with a neutral-cool undertone, blue eyes, side-swept medium brown hair, slim build, animated posture, wearing a cream overshirt jacket over a black crew-neck shirt, speaking into a large black desktop microphone centered in the foreground. Keep the same tan-to-brown seamless backdrop, soft frontal key light with warm practical glow behind him, clean digital sharpness, high social-video contrast, subtle skin smoothing, and punchy creator-ad pacing. The whole piece alternates between host talking-head footage and dark-background mobile screen-recording demos. Speech style is one male speaker, energetic but controlled, fast creator-coach cadence, crisp articulation, close mic sound, very dry room tone, cuts landing on emphasis words and CTA beats.

[00:00-00:03] Tight medium close-up of the host leaning toward the camera and pointing directly at the viewer from both sides of frame, microphone large in the center foreground with a small sticker on it. Warm brown background, soft key from camera front-left, shallow depth of field, high facial detail. He opens with a direct CTA equivalent to “comment product and I’ll send the full guide,” delivered with upbeat urgency, lips fully visible, cut timed to his finger-point emphasis.

[00:03-00:06] Quick glitch-style transformation montage over the same talking-head setup. The host rapidly cycles through alternate personas while the microphone and framing stay constant: a blue sci-fi alien warrior with braided hair and glowing skin, then other stylized cinematic character swaps. RGB split, digital tearing, and frame-skipping transition effects sell the transformation concept. Speech continues as one uninterrupted explanation about the power of AI video generation.

[00:06-00:11] Switch to a dark app-style vertical layout showing stacked before/after examples on a charcoal background. Three panels display the same standing man transformed into different characters outdoors: a clean-cut man in a gray suit, a casual adventurer in a blue shirt and brown vest, and a rugged explorer in a weathered brown outfit and hat. Static screen capture look, flat UI lighting, no camera shake. Host voiceover explains that you can step into different characters, but likeness use is demonstration only.

[00:11-00:14] Another sample card appears on the same dark interface: an older businessman resembling a boardroom spokesperson holds up a bottled product in a wood-paneled office. Large white subtitle text near the top includes the phrase “to promote.” The host voice emphasizes product marketing use cases while warning about ethics and consent.

[00:14-00:18] Return to a demo timer screen. Bright yellow digital numerals reading “00:30” sit above two stacked clips: the transformed character on top and the original host below. A neon yellow-green button labeled “Replace” anchors the center. Keep the dark gray UI background, rounded cards, and clean mobile-product aesthetic. The speaker stresses speed, describing how quickly the replacement can happen.

[00:18-00:23] Show a phone mockup with the edited vertical clip playing full-screen inside the device frame, while the live host remains visible underneath in a smaller talking-head strip. The phone UI shows a playback timeline and circular skip controls. The host explains workflow practicality and how the result still feels natural. Audio remains dry and synced tightly to his mouth when visible in the lower strip.

[00:23-00:28] Display a ChatGPT-style prompt window on a dark interface with the host image attached in the upper-left of the prompt box. The typed instruction asks for a detailed NanoBanana Pro prompt that transforms the person into a chosen character while preserving the same body position, pose, proportions, camera frame, clothing, facial features, and original background. The host voice becomes more instructional, spelling out that prompt specificity preserves realism.

[00:28-00:33] Cut to branded product UI with a black background and high-contrast lime branding. “Higgsfield” appears large at the top, followed by “NANO BANANA PRO,” with the exact transformation prompt visible in a rounded prompt field and a bright lime action button at right. Keep the host in a lower picture-in-picture talking-head window. He states that this is the tool he is using and frames it as a repeatable workflow.

[00:33-00:41] Scroll through the edit interface of the tool. Tabs near the top read like “Create Video,” “Edit Video,” and “Motion Control.” Large upload modules invite the user to upload a video and up to four images or elements, followed by a prompt field and auto settings toggle. The host continues explaining the steps in a fast tutorial cadence: upload the source clip, add reference images, enter the transformation prompt, and let the model handle the swap.

[00:41-00:47] More dark UI screens continue with prompt panels, output previews, and account or feed-style layouts. The picture-in-picture host remains in the lower portion, gesturing with both hands while reinforcing the business angle: build original digital ambassadors rather than imitate real people without permission. Keep edit rhythm brisk, roughly one UI state every one to two seconds.

[00:47-00:50] End on a final before/after hero card split vertically. Left side: original host labeled “BEFORE.” Right side: transformed version of the same man as a Black Formula 1 driver in a black Mercedes-AMG Petronas racing suit, labeled “AFTER.” Large gold text below reads COMMENT “PRODUCT”. The host lands the CTA with strong emphasis on the last word, full lip visibility, hard stop at the end.

NEGATIVE PROMPT
Avoid plastic skin, identity drift between shots, warped ears, broken hands near the microphone, floating microphone position, mismatched jawline during transformations, unstable eye color, incorrect clothing continuity in the studio shots, muddy brown background, overblown highlights on the face, overdone AI glow, temporal jitter, subtitle flicker, broken phone UI, unreadable product interface text, extra fingers, duplicate props, lip-sync lag, robotic cadence, slurred consonants, harsh sibilance, clipped peaks, roomy echo, pumping compression, and glitch artifacts outside the intentional transformation moments.

SPEECH PACK
[00:00-00:03]
Closest audible: “Comment product and I’ll send you the full guide.”
Safe paraphrase: Ask viewers to comment a keyword so the guide can be delivered.
TAKE_A: “Comment PRODUCT... and I’ll send you the full guide.” [confident, punchy]
TAKE_B: “Drop ‘product’ below and I’ll send the guide over.” [friendly, fast]
TAKE_C: “Type product in the comments, I’ll send the full walkthrough.” [clear, slightly calmer]

[00:03-00:14]
Closest audible: He introduces the power of AI video generation and adds a major rule that likeness is for demonstration only.
Safe paraphrase: He says the tool is powerful, but using real faces or voices without consent is illegal and unethical.
TAKE_A: “This shows how powerful AI video is, but likeness is for demo only.” [serious, cautionary]
TAKE_B: “AI video can do this now, but don’t use someone’s face or voice without consent.” [direct]
TAKE_C: “The tech is wild, but the rule is simple: create, don’t imitate real people without permission.” [teacherly]

[00:14-00:23]
Closest audible: He highlights that the replacement can happen in around thirty seconds and demonstrates the playback.
Safe paraphrase: He says the workflow is fast and the result stays seamless.
TAKE_A: “In about thirty seconds, you can replace the character and keep the shot working.” [excited]
TAKE_B: “This is the part that makes it practical: the swap happens fast.” [matter-of-fact]
TAKE_C: “You can move from source clip to transformed result in under a minute.” [sales-demo tone]

[00:23-00:41]
Closest audible: He explains the prompt recipe and the Higgsfield Nano Banana Pro workflow.
Safe paraphrase: Upload the video, define the replacement character precisely, preserve pose and background, then generate.
TAKE_A: “Write a detailed replacement prompt, keep the pose and background locked, then run it in Higgsfield.” [instructional]
TAKE_B: “Upload the clip, add your references, tell the model exactly what changes and what stays the same.” [clear]
TAKE_C: “The trick is specificity: same framing, same body, same environment, new character.” [coach cadence]

[00:41-00:50]
Closest audible: He reframes the use case as building original digital ambassadors and closes by repeating the “comment product” CTA.
Safe paraphrase: Use the workflow for owned characters, not imitation, and comment for the guide.
TAKE_A: “Build original digital ambassadors that you own... comment PRODUCT for the full guide.” [firm, closing emphasis]
TAKE_B: “Use this to create your own characters, not copy real people. Comment PRODUCT if you want the guide.” [balanced]
TAKE_C: “Create something original, and if you want the full process, comment PRODUCT below.” [warm CTA]

GLOBAL LOCK: Vertical 9:16 creator tutorial reel about AI relighting and environment replacement for existing video footage, framed as a social-first software demo. The visual structure uses stacked comparison panels and interface walkthroughs in the upper portion, while the creator appears in a rounded-corner talking-head window in the lower portion for much of the back half. The creator is a white male in his late 20s to mid 30s, medium-length wavy brown hair, short beard, average build, casual creator look. In the main source clip he sits on a pale sofa in a bright modern living room, holding a small handheld microphone or remote in one hand and gesturing upward with the other. Wardrobe in the source footage is a light beige T-shirt, light pants, and cream cap. In the later talking-head overlay he wears a black sweater with a large cream heart-like line motif and a blue cap with a yellow patch, seated in a dark chair beside a warm table lamp. The tutorial should clearly show three layers when relevant: a white alpha mask silhouette on black, a transformed relit scene labeled as the switched result, and the original video at the bottom. The reel demonstrates that the person’s motion can stay while lighting, mood, and environment change dramatically. Overall look: modern AI tool demo, high contrast UI, fast but readable pacing, social proof examples, green Generate button accents, direct response CTA energy. Speech style is single-speaker tutorial English, enthusiastic and persuasive, close-mic, dry room tone, clean compression, with emphasis on "re-light", "change the lighting", and "comment AI".

[00:00-00:06.50] Open with a three-tier comparison stack. The top panel shows a black background with a white human silhouette labeled "Alpha Mask", isolating the seated creator’s body shape and raised finger gesture. The middle panel shows a switched scene where the same pose now appears on a bright city street sitting in a red armchair, with London-style red bus and red phone booths behind him, labeled "Switch X" or similar. The bottom panel shows the original source footage in a sunlit room on a pale sofa labeled "Original Video". The creator is not yet in the lower commentary window; the comparison itself is the hook. Audio begins as direct spoken explanation about this being the best way to relight videos right now.

[00:06.50-00:13.00] Continue cycling through more comparison examples while preserving the same original body performance. The alpha mask remains on top, while the switched result changes to a vivid tropical poolside scene with palm trees, mountains, blue water, and a cocktail on the ledge. The bottom original sofa footage remains constant. Keep the relit version brighter, warmer, and more cinematic than the source. The viewer should immediately understand that the subject’s movement is being transplanted into new lighting conditions without reshooting.

[00:13.00-00:20.00] Introduce additional switched environments: a colorful, hyper-saturated abstract or neon backdrop, then a sunny beach setting, then a packed movie theater with viewers in 3D glasses and popcorn. Each time, the creator’s pose and timing stay recognizable while the environment, key light direction, and mood change. Keep the alpha mask as proof that the subject extraction is driving the effect. The pacing is brisk, with each example serving as visual evidence for relighting plus environment swap.

[00:20.00-00:27.00] Transition into a more conventional creator-demo layout. The upper portion shows the tool’s home screen or project dashboard on a light grid-paper background, with recent creations featuring the creator seated on the sofa in different scenes. In the lower rounded-corner commentary window, the creator now appears wearing the black sweater and blue cap, speaking directly to camera from a dim indoor setup with a warm lamp behind him. He explains the workflow and why the tool is powerful for filmmakers and creators.

[00:27.00-00:34.50] Show a closer interface walkthrough. The upper layer reveals a dark UI with panels for video relighting or scene switching, model/tool names, preview windows, and controls. A highlighted sample shows the creator on a beach near wooden crates. Another moment shows a preview frame with a crosshair over the wooden crates, suggesting point selection or scene/light control. The lower speaker window continues uninterrupted, his lips fully visible, gestures compact, tone confident and tutorial-focused.

[00:34.50-00:41.50] Zoom further into the interface. Keep the upper frame focused on prompt and parameter sections, preview thumbnails, and a large bright green "Generate" button. The creator explains that the platform can change the lighting of a scene after it is filmed, giving control over mood, shadows, and cinematic lighting in post. The room tone in his talking-head remains dry and intimate, with no background music overpowering the voice.

[00:41.50-00:47.09] End on one or two final output examples, including the beach-with-wooden-crates scene and another relit environmental switch, while the lower talking head lands a clear CTA for viewers to comment "AI" to try it. The final feeling should be practical and conversion-oriented rather than abstractly artistic. Keep the result examples bright, attractive, and obviously different from the original couch footage, reinforcing post-production relighting control.

NEGATIVE PROMPT: broken alpha mask edges, missing limbs, bad matte cutout, haloing around hair, inconsistent body pose between panels, lighting that does not match environment, flat relighting with no shadow logic, warped furniture, duplicated hands, deformed fingers, unreadable UI labels, muddy text, wrong product branding, overprocessed HDR glow, plastic skin, inconsistent sofa shape, glitching background swaps, flicker between switched results, robotic speech, slurred words, harsh sibilance, clipped audio, echoey room tone, oversized captions blocking the demo, laggy lip sync.

SHOT PROMPTS:
SHOT_1 [00:00-00:06.50]: Alpha mask on top, transformed city-street seated scene in middle, original sofa clip on bottom, direct spoken hook about AI relighting.
SHOT_2 [00:06.50-00:13.00]: Poolside tropical switched result paired with same original performance, alpha mask remains as proof.
SHOT_3 [00:13.00-00:20.00]: Rapid succession of alternate environments including colorful abstract look, beach scene, and crowded movie theater, all preserving the same subject motion.
SHOT_4 [00:20.00-00:27.00]: Tool homepage/dashboard on grid background, creator talking-head overlay in black sweater and blue cap explains the workflow.
SHOT_5 [00:27.00-00:34.50]: Dark UI walkthrough with beach crate sample and control previews, speaker window continues.
SHOT_6 [00:34.50-00:41.50]: Prompt/parameter section and large green Generate button, explanation of post-production lighting control.
SHOT_7 [00:41.50-00:47.09]: Final output examples and CTA to comment AI to try the tool.

SPEECH PACK:
Timecoded transcript (best-effort, inferred from caption and on-screen demo structure):

[00:00-00:06.50]
TAKE_A: "This AI tool is the best method to relight videos right now."
TAKE_B: "If you want to relight your footage after filming, this is the best tool I have found."
TAKE_C: "This is the strongest AI workflow for changing the lighting in a video right now."
Prosody: quick authority hook, confident, persuasive.

[00:06.50-00:13.00]
TAKE_A: "It can isolate the subject and place the same performance into completely different lighting setups."
TAKE_B: "You keep the motion from the original clip, but the lighting and scene can change dramatically."
TAKE_C: "The subject stays the same while the mood, shadows, and environment all shift around it."
Prosody: explanatory, impressed, creator-focused.

[00:13.00-00:20.00]
TAKE_A: "That means you can test multiple looks without re-shooting the video."
TAKE_B: "Instead of filming again, you can push the same clip into totally different cinematic setups."
TAKE_C: "This is why it is so useful for creators who want more options in post."
Prosody: practical value, slightly slower for emphasis.

[00:20.00-00:27.00]
TAKE_A: "Inside the tool, you can see your previous generations and start building new relighting scenes from there."
TAKE_B: "This is what the interface looks like, and it is a lot easier to use than most people expect."
TAKE_C: "Once you are in the dashboard, you can start iterating on different relighting concepts fast."
Prosody: tutorial mode, direct and clear.

[00:27.00-00:34.50]
TAKE_A: "You can switch locations, adjust the scene, and guide how the lighting behaves around the subject."
TAKE_B: "From here you choose the shot, change the scene, and dial in the result."
TAKE_C: "This is where the tool gives you control over the new environment and the lighting feel."
Prosody: matter-of-fact, instructional.

[00:34.50-00:41.50]
TAKE_A: "Beeble lets you change the lighting of a scene after it is filmed, so you can control mood and shadows in post."
TAKE_B: "The big win here is post-production control. You can reshape the look without going back on set."
TAKE_C: "For filmmakers and editors, this is powerful because it gives you lighting flexibility after capture."
Prosody: authoritative, value-focused.

[00:41.50-00:47.09]
TAKE_A: "Comment AI if you want to try it yourself."
TAKE_B: "If you want the link, comment AI."
TAKE_C: "Comment AI to try it."
Prosody: direct CTA, upbeat, strong emphasis on "AI".

GLOBAL LOCK:
The subject is a young Indian woman with a warm skin tone, long dark wavy hair parted in the middle, wearing a simple black crew-neck t-shirt. She is in a brightly lit indoor room with a soft, blurred background featuring framed pictures and a neon sign that says "BORG...". The lighting is soft and flattering, coming from the front-left. The camera is a high-quality smartphone or mirrorless camera, MCU framing, static. The speech is energetic, clear, and instructional.

[00:00–00:04]
A rapid montage of split-screen transitions. On the left, a blurry, low-resolution video clip (e.g., a cricket player in a red/blue jersey, Ross from Friends in a dark jacket). On the right, the same clip transformed into a sharp, high-definition cinematic portrait with realistic skin textures and vibrant colors. The transition is a sharp vertical wipe.

[00:04–00:06]
The creator appears in a Medium Close-Up, holding a small black Rode wireless microphone. She looks directly at the camera, smiling and speaking. Text overlay: "how you can do it too" in pink and white rounded font.

[00:06–00:13]
The creator continues speaking. Overlaid on her are various low-quality images: Joey from Friends, a scene from Titanic, a cricket match. The images are framed with rounded corners. Text overlays change: "Step 1", "Find a picture", "that you would", "want to upgrade".

[00:13–00:20]
Screen recording of a mobile phone interface. The user navigates to the Google Gemini website. A cursor clicks "Create image". A prompt is typed into the text box: "artifacts and noise while retaining authenticity... Facial features must remain consistent and clean, stable edges. Negative constraints: no warping, no faking anatomy...". An image of Ariana Grande is uploaded and then transformed into a high-quality version.

[00:20–00:26]
Screen recording of a video editing timeline (Premiere Pro or CapCut). The user is seen dragging and stitching two clips together—the low-quality original and the high-quality AI generation. The playhead moves across the transition point.

[00:26–00:30]
Back to the creator in MCU. She gestures with her hands while finishing her explanation. Final text overlay: "the CYBORG girl" with a follow icon. The background remains consistent.

NEGATIVE PROMPT:
Visual: blurry, low resolution (except for the 'before' examples), distorted faces, extra fingers, flickering lights, inconsistent hair texture, robotic movement, watermarks, messy background.
Speech: robotic cadence, monotone delivery, background noise, muffled audio, lip-sync mismatch, stuttering.

SPEECH PACK:
[00:00–00:04] (No speech, just upbeat music)
[00:04–00:06] "And here's how you can do it too."
[00:06–00:13] "Step one: Find a picture that you would want to upgrade. You can use videos or old pictures as well."
[00:13–00:20] "Step two: Head to Gemini. Choose 'Banana Upload', upload your image, type out this prompt, hit generate, and boom!"
[00:20–00:26] "PS: You can use your favorite editing app to stitch the clips together to get this."
[00:26–00:30] "And for cool AI hacks as such, follow The Cyborg Girl for more."

TAKE_A (Energetic): "And here's how YOU can do it too!"
TAKE_B (Helpful): "Here is the exact way you can do this yourself."
TAKE_C (Fast): "Here's how to do it."

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: Male subject, mid-30s, brown hair and beard, wearing a white "Vans" custom classic baseball cap. The video style is a mix of raw UGC (User Generated Content) and high-end cinematic AI renders. Pacing is fast with cuts every 2-3 seconds. The color grade for AI shots is cinematic with high contrast and saturated tones. Speech is direct-to-camera, energetic, and instructional.

[00:00–00:02]
Subject: Male in black t-shirt and white cap.
Environment: Top half is a green screen studio; bottom half is a cinematic dark stone hallway (Harry Potter style).
Action: Subject points a wooden wand toward the camera. In the AI version, the wand tip glows with a bright blue light and he wears a Gryffindor-style robe.
Camera: Medium shot, static.
Lighting: Flat studio light (top), moody torchlight with blue accents (bottom).
Speech: "This AI update has changed visual effects forever."

[00:03–00:05]
Subject: Male, shirtless (top), wearing a 1920s wool suit and flat cap (bottom).
Environment: Top is a desert with a white RV; bottom is a dimly lit vintage room with a lamp.
Action: A makeup artist's hand applies powder to his face.
Camera: Close-up on the face.
Lighting: Harsh sunlight (top), warm, soft interior lighting (bottom).
Speech: "Because you can now create Hollywood level visual effects..."

[00:06–00:08]
Subject: Male in an orange and blue martial arts gi (Goku style).
Environment: Top is green screen; bottom is a rocky canyon under a starry night sky with two moons.
Action: Subject performs a "Kamehameha" pose, a glowing white energy ball forming between his hands.
Camera: Medium wide shot.
Lighting: Vibrant blue glow from the energy ball reflecting on the subject's face.
Speech: "...with one simple source video and a basic prompt."

[00:09–00:12]
Subject: Male in a white t-shirt and white cap.
Environment: A modern bedroom with a wooden wardrobe and a bed.
Action: Subject sits at a desk with a microphone, gesturing with his hands. The camera cuts between a front view and a "behind the shoulder" view of the same scene.
Camera: Medium shot, alternating angles.
Lighting: Natural window light.
Speech: "You can even create multiple camera angles from any scene now."

[00:13–00:16]
Environment: A winding road through a forest.
Action: A white SUV drives down the road. The scene seamlessly transitions from a lush green summer forest to a heavy snow-covered winter forest, then to a futuristic neon city at night.
Camera: High-angle tracking shot behind the car.
Lighting: Bright daylight to cool blue night with neon reflections.
Speech: "Not only that, but you can change the weather and environment..."

[00:17–00:19]
Subject: Male in a black tuxedo (James Bond style).
Environment: Top is green screen; bottom is a luxury modern villa overlooking the ocean at sunset.
Action: Subject holds a handgun, aiming it slightly off-camera with a serious expression.
Camera: Close-up, side profile.
Lighting: Warm golden hour light.
Speech: "...all in 1080p and 10 seconds long. So here's how you can do it too."

[00:20–00:40]
Visual: UI walkthrough of the Kling AI website. A cursor navigates through "Kling O1", "Video Generation", and "Transformation" tabs. It shows the process of uploading a video of a man hanging upside down and a reference image of Spider-Man.
Speech: Instructional narration explaining the steps: "Go to Kling, select O1 model, go to video generation, upload input video and reference image..."

[00:41–00:45]
Visual: Rapid montage of AI transformations: Subject as Obi-Wan Kenobi with a lightsaber, Jon Snow in the snow, Indiana Jones with a whip, and AI images of the subject with Billie Eilish, Taylor Swift, and The Rock.
Camera: Various medium and close-up shots.
Speech: "Kling's new update also comes with a brand new AI image model..."

[00:46–00:50]
Subject: Male in a white t-shirt and white cap.
Environment: A tropical beach at sunset with palm trees.
Action: Subject holds a movie clapperboard that says "TYPE AI IN THE COMMENTS". He snaps the clapperboard shut.
Camera: Medium shot.
Lighting: Warm, orange sunset glow.
Speech: "If you want to try it out for yourself, type AI in the comments and I'll send you the link."

NEGATIVE PROMPT: Unstable facial features, flickering clothing textures, distorted hands or fingers, blurry background elements in AI renders, robotic or desynchronized lip movements, low-resolution artifacts, unnatural lighting jumps between cuts, watermarks on AI generated segments.

SPEECH PACK:
[00:00–00:08]
TAKE_A: "This AI update has changed visual effects forever. Because you can now create Hollywood level visual effects with one simple source video and a basic prompt." (Energetic, fast-paced)
TAKE_B: "VFX just got a massive upgrade. You're looking at Hollywood quality results from just a simple phone video and a prompt." (Confident, slightly slower)

[00:46–00:50]
TAKE_A: "If you want to try it out for yourself, type AI in the comments and I'll send you the link." (Friendly, direct)
TAKE_B: "Want the link? Just comment 'AI' below and I'll drop it in your DMs." (Casual, punchy)

GLOBAL LOCK: A 9:16 vertical creator tutorial video showing how to build cinematic AI videos inside Freepik Spaces using Kling 3.0. The structure alternates between a casual male creator talking directly to camera, screen-like workflow panels, and polished AI-generated example sequences. The speaker is a white male in his 20s or 30s with beard, cap, and casual streetwear, filmed in a warm apartment or studio environment. He should feel approachable, creator-native, and energetic rather than corporate. Keep the edit fast and legible, with repeated “How to do this” framing, visual examples of cinematic shots, and interface scenes that imply prompt building, scene sequencing, and generation controls. Audio is speech-first and educational, with the creator explaining the workflow in concise steps.

[00:00-00:05] Open on a catchy example visual or lifestyle shot with bold tutorial framing like “How to do this,” immediately pairing aspirational output with educational intent.

[00:05-00:10] Cut to the creator talking directly to camera in a casual indoor setup, hands gesturing upward as he introduces the workflow and hooks viewers with the promise of showing the full process.

[00:10-00:18] Alternate between creator face-cam, finished AI shots, and screen-style panels showing thumbnails or interface blocks, making it clear that multiple scenes are being built inside one pipeline.

[00:18-00:28] Include more practical inserts: example frames, real-world pose or filming inspiration, and workflow interface layouts that suggest prompt control, shot planning, and visual refinement.

[00:28-00:40] Keep cycling between explanation and proof, with the creator speaking in short, punchy segments while the examples show the quality ceiling of the method.

[00:40-00:56] End with a clearer recap feel: more screen panels, more finished outputs, and a final face-cam summary that reinforces this as a repeatable Freepik Spaces plus Kling production workflow.

NEGATIVE PROMPT: dry webinar, plain slideshow only, no example outputs, stiff face-cam, dark podcast studio, random office footage, unreadable UI, over-designed captions everywhere, broken hands, uncanny face, robotic speech, disconnected examples, generic stock footage, text-heavy PowerPoint feel, poor pacing, muddy screen inserts, lip-sync errors, low-quality AI art, unrelated memes.

SHOT PROMPT DELTAS:
1) Aspirational example frame with tutorial hook text treatment.
2) Casual creator face-cam explaining workflow.
3) Screen-style interface panels and scene thumbnails.
4) Example cinematic outputs paired with explanation.
5) Final recap with tools, outputs, and creator closeout.

SPEECH PACK:
[00:00-00:56] One male speaker throughout. Tone should be concise, confident, and creator-educational, explaining how to structure prompts, build shots, and use Freepik Spaces with Kling 3.0 to generate cinematic AI videos. Medium lip-sync strictness when on-camera.

GLOBAL LOCK: A vertical 9:16 social video featuring one white European-looking man in his late 20s to early 30s with fair neutral skin, blue eyes, dark brown side-swept hair, athletic build, clean-shaven face, and fitted black t-shirt, always presented as the same creator across every shot. Keep his identity, facial proportions, hairstyle, shirt, black watch, and confident tutorial energy locked. The visual world alternates between a warm tungsten bedroom-office with textured walls, shelf decor, practical lamp glow, and shallow depth of field, and clean dark UI demo layouts with rounded white software panels floating above black backgrounds. Camera language is creator-economy cinematic UGC: medium close-ups, chest-up framings, slight handheld energy, occasional push-ins, and crisp eye-level talking-head setups. Lighting stays motivated and contrasty, with orange practical light on one side and cooler fill on the opposite side during the “after” setup. Grade is rich, warm, polished, slightly contrasty, with soft highlight rolloff and subtle skin texture. One male speaker only, on-camera and off-camera from the same person, speaking energetic tutorial English with quick cadence, punchy emphasis, clean studio-style voice, close microphone presence in the second half, and tight lip sync whenever his mouth is visible.

[00:00-00:03] In a dim, warm, low-budget looking setup, frame the creator seated against a textured gray wall, lit by a harsh orange practical glow. He gestures with both hands while looking directly into the lens. Large bold white words appear one beat at a time over his chest, matching the spoken hook: “you go from this”. Keep the frame slightly cramped, the background plain, and the mood intentionally mediocre to set up contrast.

[00:03-00:00:07] Smash cut to a cleaner, brighter version of the same creator in a polished bedroom-office. Use a centered medium shot with soft warm lamp light behind him, shelf decor and trailing green plant on camera left, and a vertical tube light on camera right. Continue the chest-level kinetic subtitles: “to this, or this”. Keep his black t-shirt and posture consistent while the room looks instantly more premium.

[00:07-00:10] Show another talking-head angle in the polished room, then briefly cut to a behind-the-scenes view with a large softbox, chair, phone, and wall, revealing the practical filming setup. Bold subtitle words continue timing with speech: “AI”, “a key”, “45 degrees”, “of you”, “pocket”, “background”. Preserve the tutorial rhythm and creator hand gestures.

[00:10-00:15] Cut to smartphone recording interface views and the creator framed vertically on a phone screen. Emphasize that a screenshot of the clip is taken. Show the recording button, the portrait frame, and a quick screen capture moment. Transition into dark UI layouts branded around ElevenLabs, keeping the creator visible in a picture-in-picture talking-head box at the bottom.

[00:15-00:24] On a dark background, display rounded white software panels with image upload areas and labels such as “Image refs” and “Nano Banana Pro.” The creator appears in a small lower talking-head box speaking directly into a large black microphone. He points upward and times his gestures to each UI step. Show his portrait reference being uploaded, then the generated clean headshot-style reference. Keep the mic close, the room tone dry, and the delivery crisp.

[00:24-00:33] Reveal multiple generated stills of the same creator in slightly different rooms and lighting conditions, including warm interiors and cool-blue accented backgrounds. Show a blue “Download” button on one version. Then move into a “Kling 2.6 Motion Control” interface with two slots labeled for a character image and a motion video. The creator keeps explaining while pointing up toward the interface, maintaining fast tutorial cadence.

[00:33-00:39] Fill the motion-control interface step by step: first add the clean portrait as the character reference, then add the motion source video, then display the prompt text instructing the tool to transfer the motion of the first attached video into the attached image perfectly. Show the cursor moving to the upload arrow. Keep the software card large, centered, and readable, with the presenter anchored below.

[00:39-00:46] Cut back to vertical result examples of the same creator composited into new backgrounds while preserving body motion and framing. Show one scene with a dark studio doorway and plants, another with a warm shelf-lit interior. The creator continues speaking into the mic from the lower frame, emphasizing that the method preserves motion while swapping environment.

[00:46-00:52] Switch to the ElevenLabs Creative Platform UI. Show the creator clip inside the workspace, then navigate into audio features. Surface labels like “Sound effects” and “Studio quality voice,” plus a dropdown list of available voices. Keep the UI white and minimal, floating on a black canvas, while the creator explains how to finish the polish.

[00:52-00:57] Display a detailed equipment/setup page with headings like camera and lens suggestions, price examples, and notes about depth of field and aperture. Then cut back to a dark layout where the motion-transfer prompt card is visible alongside stacked vertical examples of the creator in different backgrounds. The creator maintains an urgent, confident CTA tone.

[00:57-00:59] End on a strong conversion frame: oversized yellow and white text reads Comment “Setup” while the creator points upward with one finger from the bottom talking-head box. Keep the black background clean, the examples stacked above, and the CTA unmistakable, optimized for saves and comments.

NEGATIVE PROMPT: do not change the presenter’s face, hairstyle, age range, build, shirt color, or watch between shots; avoid extra fingers, warped arms, asymmetrical eyes, rubbery skin, unstable jawline, drifting hairline, or mismatched ear shape; avoid random wardrobe swaps, logo changes, or added accessories; no flicker, temporal jitter, morphing backgrounds, UI text corruption, duplicated limbs, or inconsistent room geometry; no muddy compression, over-sharpening, clipped highlights, strange shadow directions, or cartoon skin smoothing; do not let the microphone appear in shots where it should be absent; avoid robotic speech, flat cadence, clipped plosives, harsh sibilance, room echo, bad lip sync, or subtitles that lag the spoken emphasis.

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.”

MASTER PROMPT
GLOBAL LOCK: Vertical 9:16 creator tutorial reel combining talking-head explanation with dark product UI walkthroughs for image generation. One Caucasian male creator in his late 20s to early 30s, fair skin, blue eyes, medium brown side-parted hair, slim build, expressive hands, wearing a black crew-neck shirt and speaking into a centered black podcast microphone. Studio background stays dark and warm with soft amber edge light. The upper portion of the frame alternates between Freepik/Seedream 5.0 screens, image grids, cinematic fantasy character outputs, prompt panels, reference-image layouts, and result galleries. Keep the overall mood polished, software-demo heavy, fast-cut but legible, with clear product branding, one energetic male narrator, close-mic dry audio, and emphasis on prompt accuracy, 4K detail, and multi-reference consistency.

[00:00-00:05] Open with cinematic generated imagery occupying the top half of the screen: rugged adventurer-style characters, gorilla-like fantasy creature shots, and sunlit outdoor action stills. The host below talks directly to camera with lively gestures, introducing a workflow and promising to send the full process if viewers comment “AI.” The frame is vertically split, with the result images immediately establishing visual quality.

[00:05-00:12] Continue alternating between the host and more generated images, including multiple frames of the same characters across slightly different actions and compositions. The consistency between outputs is the point: same world, same characters, different shots. Audio shifts into explanation mode, highlighting Seedream 5.0 and the level of prompt understanding.

[00:12-00:20] Show dark UI panels with brand text for Freepik/Seedream 5.0, plus grids of reference images and outputs arranged in columns. The host remains in the lower portion while the upper portion displays how references and prompts are structured. He explains that up to 14 references and structured Spaces workflows make large visual systems more cohesive and scalable.

[00:20-00:28] Cut to a prominent dark prompt window with bright text labels and a clean form layout. Nearby, more image pairs and output grids show the same adventurer and creature motifs repeated across multiple variations. The creator speaks faster here, framing the workflow as practical for repeatable creative pipelines rather than one-off pretty images.

[00:28-00:36] Show a fuller Freepik interface with side panels, prompt box areas, and sequences of output thumbnails. The presenter below emphasizes that the best use is inside Spaces, where models and references can be combined into a structured system. Keep the host’s mic centered, amber-lit studio look unchanged, and the UI crisp against a dark charcoal background.

[00:36-00:44] Display more result grids and larger hero images, including duo compositions of a human adventurer and giant gorilla-like companion in bright grassy outdoor scenes. The images remain photoreal with cinematic sunlight, detailed fur, weathered clothing, and adventure-movie composition. Speech focuses on cohesive worldbuilding and how the outputs can stay on-brand across many generations.

[00:44-00:52] Move back into prompt and settings screens, then return to the host with broader gestures. The screen rhythm alternates between showing the system architecture and showing proof shots. He underscores that this is fun, scalable, and free to try inside the featured workflow.

[00:52-00:57] End on strong generated examples and a simple CTA. The host looks directly into camera and lands the line equivalent to “Comment AI and I’ll send you the full workflow on Freepik for free,” with the keyword and free-offer emphasis timed to the last cut.

NEGATIVE PROMPT
Avoid muddy outdoor detail, low-resolution textures, broken anatomy on the human or creature characters, inconsistent costume continuity, fur flicker, unreadable UI labels, cluttered layouts, washed-out skies, over-smoothed faces, floating microphone position, jittery host insert, robotic voice cadence, reverb-heavy audio, clipped consonants, and any result images that fail to feel like one consistent visual system.

SPEECH PACK
[00:00-00:05]
Closest audible: “Comment AI and I’ll send you the full workflow on Freepik for free.”
Safe paraphrase: Start with a keyword CTA tied to a free workflow resource.
TAKE_A: “Comment AI and I’ll send you the full workflow on Freepik for free.” [bright, direct]
TAKE_B: “Drop AI below and I’ll send you the full workflow for free.” [friendly]
TAKE_C: “Type AI in the comments if you want the full process.” [simple CTA]

[00:05-00:20]
Closest audible: He says Seedream 5.0 delivers native 4K visuals, strong prompt understanding, and support for many references.
Safe paraphrase: He frames the tool as powerful for accurate prompting and multi-reference image systems.
TAKE_A: “Seedream 5.0 gives you native 4K visuals, strong prompt understanding, and support for up to fourteen references.” [teacherly]
TAKE_B: “This is why the outputs stay so cohesive: the model understands the prompt and the references.” [clear]
TAKE_C: “You’re not just getting pretty images, you’re getting a repeatable system.” [firm]

[00:20-00:44]
Closest audible: He explains that Spaces gives you structured workflows, model combinations, and scalable creative pipelines.
Safe paraphrase: The best use case is building a repeatable pipeline rather than generating isolated images.
TAKE_A: “The real power is inside Spaces, where you can structure the workflow and combine models properly.” [instructional]
TAKE_B: “This works best when you treat it like a pipeline, not a one-off prompt.” [coach tone]
TAKE_C: “References plus structure are what turn good generations into a scalable visual system.” [emphatic]

[00:44-00:57]
Closest audible: He says he is having fun with it and repeats the CTA to comment AI for the workflow.
Safe paraphrase: Close by mixing enthusiasm with a low-friction resource offer.
TAKE_A: “I’m having so much fun with this... comment AI and I’ll send you the workflow.” [warm close]
TAKE_B: “If you want the exact setup, comment AI below.” [short]
TAKE_C: “Comment AI and I’ll send over the full workflow.” [clean CTA]