Ai Meme From Text

GLOBAL LOCK: A vertical 9:16 creator tutorial reel teaching how to make first-person time-travel vlogs with AI. The lower half of the video holds a young male creator speaking directly to camera in a dark studio with red side lighting, black hoodie or jacket, and a backward cap. The upper half alternates between social-proof examples, smartphone search screens, browser pages, prompt-writing documents, and final generated historical selfie videos. The core output style is a realistic vlog shot where a modern creator appears to be filming himself inside major historical moments such as Viking England, the Wild West, or D-Day. The entire reel should feel practical and system-driven, built for viewers who want repeatable viral history content.

[00:00-00:12] Open on two successful example clips above the speaker: one where a young woman appears to selfie-vlog among Vikings in England in 865 AD, and another where she appears in a Wild West town in 1880. Both examples should look like genuine first-person historical vlogs with modern camera behavior but era-correct surroundings. View counts or social-proof markers should be visible to show that this content format already works.

[00:12-00:28] Move into the workflow entry step through a smartphone UI. Show a phone search screen with “Time Travel” typed in, then a Google-like result page for “Higgsfield AI.” The creator below explains the process in clear terms, making the tutorial feel accessible. The emphasis is on how surprisingly simple the setup is once the right tools are known.

[00:28-00:46] Show prompt-building and script-generation stages. Display a prompt document or text page labeled for text-to-video prompts, with entries for historical scenarios like landing craft before a beach assault or other era-specific vlog scripts. The interface should feel like a practical creator workflow rather than a polished marketing demo. The point is that the output begins with scripting the right first-person historical situation.

[00:46-01:01] End on a dramatic finished example where the creator appears to be selfie-vlogging during a World War II beach landing, with smoke, soldiers, landing craft, and battlefield chaos behind him. Overlay a small thumbnail or packaging element suggesting how the final video can be turned into a clickable social or YouTube asset. The result should feel both absurd and convincing: modern vlog behavior dropped into a massive historical event.

NEGATIVE PROMPT: static history painting look, third-person documentary framing, no selfie perspective, bland phone UI, generic prompts, inconsistent main character face, casual modern backgrounds, low-detail crowds, weak historical setting, no social-proof packaging.

SHOT PROMPTS: Viking time-travel selfie vlog; Wild West selfie vlog; phone search Time Travel; Higgsfield AI search result; ChatGPT prompt document; text-to-video historical script; D-Day beach selfie vlog; viral history series tutorial.

SPEECH PACK: One male speaker only. Tone is practical and energetic, emphasizing simplicity, virality, and repeatability. Stress “time travel vlogs,” “Higgsfield AI,” “ChatGPT prompts,” and the historical selfie angle.

GLOBAL LOCK:
- Format: vertical 9:16 short-form tutorial reel, creator-education pacing, black background UI inserts, high contrast social video polish.
- Keep one consistent male creator for all talking-head shots: young adult male, light skin, black backwards baseball cap, black hoodie/jacket, seated at desk, direct-to-camera framing, confident tutorial delivery.
- Keep one consistent demo subject inside the generated example image/video: a plush panda lying on a worn circular rug in a dim rustic room with warm overhead spotlight, scattered objects around the floor, soft moody shadows.
- No character drift, no costume drift, no sudden age changes, no extra presenters, no unrelated cutaways.

SHOT TIMELINE:

[00:00-00:03]
Talking-head intro. Creator sits centered against dark background and speaks straight to camera with energetic tutorial tone. Large editorial text overlays summarize the hook: make cinematic scenes from your phone. Insert fast teaser flashes of social posts showing the panda image/video result and yellow headline blocks.

[00:03-00:06]
Phone close-up UI. Vertical smartphone screen fills frame. A circularly framed panda image appears inside a social-style composition. Overlaid kinetic words emphasize the concept of turning a phone photo into a scene. Screen recording aesthetic should remain crisp and legible.

[00:06-00:09]
Back to talking head. Creator gestures lightly while saying the workflow starts by opening the app. Tight chest-up framing, direct eye contact, subtle head movement, clean synced speech.

[00:09-00:12]
Phone settings interface. User taps through app menu and settings-like pages to reach AI generation tools. Interface is dark mode, minimal, modern, with distinct list items and icons.

[00:12-00:16]
Prompt-building section on phone. Search field, model selection, and text-entry screens appear. User searches for GPT/prompt helper style tools, selects options, and opens a text area. On-screen rhythm should clearly communicate “build the prompt first.”

[00:16-00:20]
Text drafting flow on phone. Long paragraph prompt appears in a dark text box. User chooses/copies prompt text, then taps through action buttons. Highlight the exact motions: choose, copy, click, and go. The UI should feel like a real mobile workflow, not abstract fake panels.

[00:20-00:24]
Model/generation interface. User pastes the prompt into an AI image/video generation tool, selects the correct model or preset, and taps generate. Show dark-mode tool UI with image prompt area, buttons, and tabs.

[00:24-00:28]
Example asset preview returns. The panda scene appears again as a generated image/video preview. The phone screen cycles from prompt entry to generated result. Add supporting overlay words that reinforce the logic of generating the scene from a single photo.

[00:28-00:32]
Phone-to-output transition. The generated panda shot becomes larger and more immersive, as if stepping out of the interface into the final cinematic frame. Keep the panda, rug, spotlight, and room layout consistent with the reference image.

[00:32-00:35]
Talking-head recap. Creator returns on camera and explains the final step or CTA. He maintains same wardrobe and setup, speaking with persuasive, practical creator-teacher energy.

[00:35-00:39]
Final CTA and social proof. Talking-head remains center frame while comment-style overlays and platform UI elements appear below, suggesting engagement and repeatability. End on a clean, punchy tutorial finish.

VISUAL STYLE:
- Social tutorial reel, fast but readable editing.
- Mix talking-head shots with direct phone-screen recordings.
- Dark UI, white text, occasional high-contrast yellow hook text.
- Clean mobile creator aesthetic with authentic app interaction.

CAMERA AND EDITING:
- Talking-head: locked tripod or subtle digital push-in.
- Phone segments: full-screen mobile capture with smooth taps and transitions.
- Fast snap cuts between explanation, interface, and result.
- Keep chronological clarity so the viewer can follow the workflow in order.

SPEECH PACK:
- Spoken language: English.
- Creator voice: young male creator educator, confident, concise, practical, slightly hyped but not cheesy.
- Delivery style: short tutorial phrases, clear CTA emphasis, social-video pacing.
- Lip sync must stay natural and tightly aligned during talking-head shots.

NEGATIVE PROMPT:
- No extra hands floating over the phone.
- No unreadable UI gibberish replacing app text.
- No switching creator identity between talking-head shots.
- No panda changing species, color, pose logic, or room layout between preview and final output.
- No random additional animals or fantasy objects appearing in the room.
- No horizontal framing, no cinematic letterboxing, no documentary cutaways.
- No blurred phone screens, broken typography, or unusable interface text.

GLOBAL LOCK: 
Subject: A young woman in her mid-20s, light skin with warm undertones, long wavy dark brown hair parted in the middle. She wears a white ribbed turtleneck sweater and a silver watch on her left wrist. 
Environment: A clean studio with a soft purple and pink gradient background. A dark desk and the edge of a laptop are visible in the foreground.
Style: High-definition UGC tech tutorial, clean lighting, vibrant colors.
AI Animation Style: High-fidelity 3D cartoon animation (saturated colors, smooth motion) and cinematic photorealistic action.
Speech: Female voice, enthusiastic and clear, medium pace, professional mic quality with slight room resonance.

[00:00–00:02]
Subject: Host looking directly at camera, speaking.
B-roll Overlay: A cinematic, high-speed desert buggy racing through sand dunes, massive dust clouds billowing behind it. High-contrast, bright sunlight.
Action: Host gestures slightly with hands. Buggy moves rapidly from left to right.
Speech: "There's a website where you can create"
Sync: High lip-sync strictness.

[00:02–00:04]
Subject: Host speaking.
B-roll Overlay: Close-up of the buggy's wheels churning sand, intense motion blur. Text "Consistent AI Videos" appears in bold yellow.
Action: Fast-paced action shot.
Speech: "consistent AI videos like Higgsfield AI"
Sync: Cut lands on "Higgsfield".

[00:04–00:06]
Subject: Host speaking, smiling.
B-roll Overlay: Higgsfield AI logo (green square with a black squiggle).
Speech: "and it's completely free."
Sync: High lip-sync strictness.

[00:06–00:09]
Subject: Host speaking.
B-roll Overlay: Screen recording of the Higgsfield interface. A panda is shown in a video preview. Text "Just paste or prompt" appears.
Action: Mouse cursor hovers over the "Create Video" button.
Speech: "Just paste your image or prompt and the platform"

[00:09–00:13]
Subject: Host speaking.
B-roll Overlay: A scrolling list of AI models (Claude, Gemini, Grok) followed by a grid of AI video tool logos.
Action: Rapid scrolling motion.
Speech: "generates the video for you. Now you might think every AI video tool can do that,"

[00:13–00:17]
Subject: Host speaking, leaning forward slightly.
B-roll Overlay: Screen recording of a 3D cartoon cat chasing a mouse. A right-click menu appears over the video.
Action: Mouse selects "Copy Video Frame".
Speech: "but here's what makes this one special. After the video is generated,"

[00:17–00:20]
Subject: Host speaking.
B-roll Overlay: The copied frame is pasted into the prompt box.
Action: UI interaction showing the image being uploaded.
Speech: "you can right-click and copy the last frame, then paste that frame"

[00:20–00:26]
Subject: Host speaking (small window) / Full-screen animation.
Visual: The 3D cartoon cat continues the chase, running through a hole in the wall. The mouse is seen inside the wall with a piece of cheese.
Action: Smooth, high-speed character animation. The cat looks frustrated.
Speech: "back into the tool and continue the prompt. The AI will continue the story exactly where the first video ended,"

[00:26–00:31]
Subject: Host speaking.
B-roll Overlay: A new animation of a stylized 3D family (father, mother, two children) standing outside a house. A yellow school bus drives into the frame.
Action: The bus stops, the camera pans slightly.
Speech: "keeping the same characters and visual style. So instead of random clips, you can create consistent story-based videos"

[00:31–00:34]
Subject: Host speaking directly to camera, friendly expression.
Visual: Text "Comment Video" and "send you Video" appears in yellow.
Action: Host clasps hands on the desk.
Speech: "scene after scene. Want to try it yourself? Comment 'Video' and I'll send you over."
Sync: High lip-sync strictness on CTA.

NEGATIVE PROMPT: Visual artifacts, distorted faces, flickering backgrounds, inconsistent clothing colors, robotic mouth movements, blurry UI text, harsh shadows on the host, unnatural hair physics in animation, audio clipping, background noise, muffled speech.

SPEECH PACK:
[00:00-00:04] "There's a website where you can create consistent AI videos like Higgsfield AI"
TAKE_A: (Enthusiastic, fast) "There's a website where you can create consistent AI videos like Higgsfield AI"
TAKE_B: (Informative, steady) "There's a website... where you can create consistent AI videos... like Higgsfield AI"

[00:04-00:13] "and it's completely free. Just paste your image or prompt and the platform generates the video for you. Now you might think every AI video tool can do that,"
TAKE_A: (Emphasizing 'free' and 'every') "and it's completely FREE. Just paste your image or prompt and the platform generates the video for you. Now you might think EVERY AI video tool can do that,"

[00:13-00:20] "but here's what makes this one special. After the video is generated, you can right-click and copy the last frame, then paste that frame"
TAKE_A: (Intriguing tone) "but here's what makes THIS one special. After the video is generated, you can right-click and copy the last frame, then paste that frame"

[00:20-00:34] "back into the tool and continue the prompt. The AI will continue the story exactly where the first video ended, keeping the same characters and visual style. So instead of random clips, you can create consistent story-based videos scene after scene. Want to try it yourself? Comment 'Video' and I'll send you over."
TAKE_A: (Helpful and encouraging) "back into the tool and continue the prompt. The AI will continue the story EXACTLY where the first video ended... keeping the same characters and visual style. So instead of random clips, you can create consistent story-based videos scene after scene. Want to try it yourself? Comment 'Video' and I'll send you over!"

Create a short-form creator tutorial video about how to make cinematic AI clips from simple ideas. The piece should feel like an Instagram Reel or TikTok posted by an AI filmmaking educator, combining direct-to-camera instruction with polished cinematic sample shots and interface cutaways. Use a confident creator host in a dark studio or moody workspace, speaking naturally to camera while explaining a repeatable workflow for generating cinematic AI videos. The pacing should be fast, sharp, and social-first, with frequent visual resets to keep attention high.

Open with a strong hook where the creator talks directly to camera and promises to show viewers how to make cinematic AI clips that feel dramatic, polished, and scroll-stopping. Then cut into multiple example shots that look like finished outputs: moody action moments, dramatic close-ups, atmospheric character scenes, and premium-looking cinematic frames. Intercut those examples with prompt panels, tool UI, timeline views, or settings screens so the workflow feels grounded in real AI video creation rather than abstract inspiration.

The host should stay visually consistent across talking segments: same person, same wardrobe, same lighting setup, same direct creator-teacher tone. Their performance should feel natural and creator-native, not overly scripted. They should gesture casually, point toward on-screen examples, and deliver the lesson with energetic clarity, like someone used to teaching AI video tricks on social media.

The visual design should alternate between two clear modes. Mode one is the tutorial studio setup: dark background, controlled lighting, crisp face detail, shallow depth of field, subtle color accents, and a premium creator-desk atmosphere. Mode two is the cinematic demo footage: dramatic compositions, intentional movement, filmic contrast, moody lighting, and stronger environmental storytelling. Keep cutting between those modes so the audience always sees both the result and the process.

Keep the entire piece optimized for vertical video. For talking-head sections, use close-ups and medium close-ups with subtle push-ins or light handheld energy. For the cinematic examples, vary the framing with wides, dramatic close-ups, push-ins, tracking shots, and controlled motion that sells the idea of “cinematic” without becoming chaotic. Everything should feel curated and premium.

Lighting is important. The host footage should use flattering key light with soft falloff and a clean but moody creator-studio look. The cinematic sample shots should lean harder into contrast, rim light, atmosphere, practicals, and dramatic highlight control. The overall grade should feel modern, contrasty, and polished, with rich blacks, sharp visual separation, and subtle filmic texture.

Include insert shots of prompts, settings, or example workflow screens to reinforce the educational angle. These moments can show how ideas become prompts, how cinematic references are structured, or how the creator chooses scenes and visual style. The UI should feel real and useful, not decorative.

The edit should stay fast and social-first: hook, creator explanation, cinematic example, interface proof, another teaching beat, then more examples. Use cuts, punch-ins, overlays, and visual comparison moments so the viewer always feels momentum. The final result should feel like a practical creator tutorial that teaches viewers how to make cinematic AI clips while also showcasing enough premium output to inspire them to try the workflow themselves.

GLOBAL LOCK:
Subject is Thomas, a middle-aged Caucasian male with a thick, well-groomed brown beard and mustache, messy brown hair. He wears a light-colored tropical floral print shirt under a navy blue unbuttoned casual jacket. The primary environment is a modern, bright "Creative Hub" office with glass partitions, indoor plants, and desks. A recurring prop is a large, round red "Easy" style button on a wooden desk. Lighting is high-key and natural in the office, shifting to dramatic, low-key, top-down lighting in the "process" scenes. The color grade is warm and saturated in the office, and cool/teal in the process montage. Speech is direct-to-camera, confident, and slightly satirical.

[00:00–00:10]
Thomas walks confidently through a bright, modern glass-walled office toward the camera. A white fluffy alpaca walks beside him on his left. Thomas has a brown leather messenger bag over his shoulder. Tracking medium shot. Lighting is bright and even. Thomas says, "Honestly, it's pretty simple to make films with AI."

[00:10–00:20]
Thomas sits at a wooden desk in the office. In front of him is a large red button and a white mug that says "I'm an Artist Mum." He smiles broadly at the camera and says, "You just press a button. That's it." He reaches out and presses the red button. Yellow bold text "THE AI ARTIST" overlays the screen.

[00:20–00:30]
Thomas leans back in his office chair, hands behind his head, looking smug. He says, "I'm Thomas. I'm an AI artist. Whatever that means." The camera zooms in slightly on his face as he gives a knowing smirk.

[00:30–00:41]
Thomas stands in the doorway of a "Social Media Department." He points to a young woman, Lisa, sitting in a colorful ball pit with a laptop. He says, "Lisa here handles all our LinkedIn stuff." Cut to a close-up of a LinkedIn post on a monitor that reads "So proud that we pressed a button today! The future of storytelling is HERE."

[00:42–00:56]
Thomas gestures to a cluttered room filled with cardboard boxes, gold Oscar statues, and Grammy awards. He says, "Here's our prize room. We throw in everything." Cut to Thomas back at his desk, leaning forward intensely. He says, "Anyone can do this. Even my mom." Cut to an elderly woman with grey hair and glasses sitting at a desk, sipping tea and pressing the red button.

[00:57–01:11]
Thomas walks through the office eating from a bag of chips, the alpaca still following him. He says, "Clients are always like, 'Is this legally okay?'" Cut to a large, heavy-set man in a dark suit (the lawyer) sitting in a moody, dark office, fanning a stack of Euro bills. The lawyer says, "It's very safe. I checked everything. 100% safe."

[01:12–01:20]
The lighting shifts to pitch black. Thomas sits at the desk, illuminated by a single bright light from above. A glowing lightbulb appears over his head. He says, "So here's how I do it. First, I lift this finger... and then..." He lifts his index finger dramatically. A glowing blue holographic typewriter appears.

[01:21–01:30]
Rapid-fire montage. Thomas's face in extreme close-up, eyes wide and frantic. A yellow banana floats in the dark space. Thomas pulls at his hair in frustration. Glowing blue holographic hands with seven fingers appear. A glowing blue Photoshop "Ps" logo floats between his hands as he makes "masking" gestures.

[01:31–01:38]
Thomas is surrounded by a massive wall of hundreds of small video screens, all flickering. He points frantically at one. He says, "You generate 400 different clips and only one is working!" The lighting is chaotic and colorful.

[01:39–01:45]
Back to the bright office. Thomas is sitting at the desk, looking exhausted and disheveled. He looks at the camera and whispers, "And then... you just press this button." He slowly presses the red button. Fade to a white screen with the logo "Promptr: We press buttons."

NEGATIVE PROMPT:
Visual: Robotic movements, inconsistent beard shape, flickering background office lights, distorted hands (except when intentional in the montage), blurry textures, low resolution, watermarks, morphing clothing patterns.
Speech: Monotone delivery, robotic cadence, lip-sync mismatch, background noise in the "process" montage, muffled audio, unnatural pauses.

SPEECH PACK:
[00:00-00:10] "Honestly, it's pretty simple to make films with AI."
TAKE_A: (Confident, breezy) "Honestly, it's pretty simple to make films with AI."
TAKE_B: (Smug, dismissive) "Honestly... it's *pretty* simple to make films with AI."

[01:12-01:18] "So here's how I do it. First, I lift this finger... and then..."
TAKE_A: (Intense, instructional) "So here's how I do it. First... I lift this finger... [pause] ...and then..."
TAKE_B: (Whispered, conspiratorial) "So here's how I do it. First, I lift this finger... and then..."

[01:34-01:38] "You generate 400 different clips and only one is working!"
TAKE_A: (Frantic, shouting) "You generate 400 different clips and only ONE is working!"
TAKE_B: (Desperate, high-pitched) "You generate four-hundred different clips... and only one... is working!"

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.

A) MISE EN PLACE

Reference summary
- Duration: 00:57.79
- Format: vertical 9:16, 720x1280, 24 fps
- Structure: talking-head tutorial reel demonstrating HeyGen AI Agent for UGC-style content creation
- Audio: direct-to-camera creator narration; exact words inferred best-effort from caption, visible UI, and pacing

Scene / shot segmentation
1. 00:00.00-00:10.00
   Hook section with phone-shot UGC example footage on screen, presenter lower center. A female creator-style vertical clip is shown as the practical target output while the host frames the feature as a new way to make UGC content.
2. 00:10.00-00:22.00
   More UGC examples and social-style before/after proof, including a hand pointing at the screen to emphasize generated results and mobile-native output.
3. 00:22.00-00:38.00
   HeyGen product interface section. Dark dashboard and setup screens take over, showing AI Agent-related controls, workflow panels, and configuration blocks while presenter keeps explaining.
4. 00:38.00-00:49.00
   Deeper editor / media management section. Grid-based asset views and back-office screens appear, suggesting avatar, scene, or media orchestration.
5. 00:49.00-00:57.79
   Presenter-forward close with strong CTA energy, likely asking viewers to comment “AI” for the link.

Visual evidence keyframes
- 00:00.00: UGC-style female selfie/creator shot framed on a phone screen, presenter lower center
- 00:08.00: finger pointing at screen, emphasizing mobile-native proof
- 00:16.00: second UGC-style clip with presenter continuing explanation
- 00:24.00: dark HeyGen interface with AI Agent-style workflow card and controls
- 00:32.00: dashboard-like panels and configuration widgets
- 00:40.00: media grid / project management view
- 00:52.00: presenter larger in frame with CTA close energy

Speech evidence (best-effort)
- speaker_count: 1
- speaker A: male-presenting creator speaking on-camera throughout
- speech style: upbeat tutorial narration, positioning the new HeyGen AI Agent feature as a way to produce UGC-style ad/social content
- likely content themes in order:
  1) how to create UGC-style content using HeyGen’s new AI Agent feature
  2) quick proof that the format works for social-style output
  3) walkthrough of the HeyGen setup / dashboard / workflow
  4) explanation of how the tool helps generate content faster
  5) comment “AI” for the link
- lip visibility: full for most presenter segments
- lip_sync_strictness: medium

Invariants list (LOCK THESE)
- presenter identity: male creator in casual cap, beard, light t-shirt, speaking directly to camera from a seated setup
- layout: presenter near bottom center while examples and interface screens rotate above and behind him
- product context: HeyGen AI Agent, UGC-style content creation, social media / ad creative workflow
- design language: creator tutorial, mobile-first, dark dashboard UI, concrete examples before tool explanation
- motion grammar: hard cuts between example clips and dashboard screens, no elaborate cinematic camera move
- lighting / grade: presenter evenly lit, warm-neutral skin tones, dark interface background, bright phone-screen examples
- audio style: concise, creator-education voice optimized for shorts/reels

Variables list (TWEAK THESE)
- exact UGC example faces and scenes
- exact dashboard panels and wording on HeyGen screens
- precise narration phrasing
- exact CTA wording beyond the comment-for-link mechanic

B) SHOTLIST

Shot 1
- shot_id: 1
- timecode_start: 00:00.00
- timecode_end: 00:10.00
- duration: 10.00s
- framing: presenter lower center beneath a large mobile-video example
- lens: presenter webcam/phone-style medium crop
- camera movement: static presenter crop, brisk background swaps
- subject: presenter introduces the HeyGen AI Agent use case for UGC content
- environment: female selfie-style UGC clip filling the upper frame, social-media-native layout
- speech/audio: Speaker A hook line about creating UGC-style content using the new feature

Shot 2
- shot_id: 2
- timecode_start: 00:10.00
- timecode_end: 00:22.00
- duration: 12.00s
- framing: more UGC proof clips and touch/point emphasis on screen
- camera movement: quick cuts and proof refreshes
- subject: presenter reinforces that the output looks like social-native creator content
- environment: phone-screen examples, finger pointing, comparative proof frames
- speech/audio: Speaker A highlights the outcome and use case

Shot 3
- shot_id: 3
- timecode_start: 00:22.00
- timecode_end: 00:38.00
- duration: 16.00s
- framing: HeyGen dashboard fills most of the frame, presenter remains lower center
- camera movement: rapid UI cuts
- subject: presenter explains AI Agent setup / workflow
- environment: dark product interface, cards, toggles, and pipeline sections
- speech/audio: Speaker A turns practical and tool-specific

Shot 4
- shot_id: 4
- timecode_start: 00:38.00
- timecode_end: 00:49.00
- duration: 11.00s
- framing: deeper project/media management screens
- camera movement: hard cuts through interface states
- subject: presenter explains scaling or organizing content generation
- environment: asset grid, project thumbnails, management view
- speech/audio: Speaker A continues the workflow explanation

Shot 5
- shot_id: 5
- timecode_start: 00:49.00
- timecode_end: 00:57.79
- duration: 8.79s
- framing: presenter-forward close with remaining dashboard context behind him
- camera movement: mostly static close
- subject: presenter lands the CTA and link offer
- environment: dark interface or blurred dashboard backdrop
- speech/audio: Speaker A asks viewers to comment “AI” for the link

C) STYLE BIBLE (GLOBAL)

- visual_style: AI creator tutorial reel, UGC marketing workflow breakdown
- camera_signature: persistent talking-head lower-third with changing proof and interface backgrounds
- lighting_signature: soft creator lighting on presenter; bright mobile examples contrasted with dark software UI
- grade_signature: warm-neutral presenter, darker dashboard, high-contrast phone-screen inserts
- texture_signature: crisp app interface, handheld/phone-look proof clips, creator desk setup feel
- pacing_signature: quick promise, quick proof, practical workflow, CTA
- speech_style: direct-to-camera tutorial narration
- speaker_profile: enthusiastic, practical, creator-marketer tone
- pronunciation_profile: casual English, medium-fast, emphasis on tool name and outcome
- mic_mix_profile: dry, clear creator audio with light compression

D) PROMPT SYNTHESIS

MASTER PROMPT

GLOBAL LOCK: Create a vertical 9:16 creator tutorial reel about using HeyGen’s new AI Agent feature to make UGC-style content. Keep one male creator presenter seated near the bottom center for most of the video. He has a short beard, baseball cap, casual light t-shirt, and speaks directly to camera with energetic but practical tutorial cadence. The background rotates between UGC-style phone footage, mobile-screen examples, dark HeyGen dashboard screens, AI Agent workflow panels, media-management views, and a final comment CTA. Preserve a mobile-first, scroll-stopping structure: proof first, interface next, conversion close. Lighting on the presenter stays soft and even, with a clean creator-desk feel.

[00:00-00:10.00] Open with a realistic UGC-style female selfie or creator clip filling the upper frame, as if viewed on a phone screen, while the presenter appears lower center and introduces how to create this kind of content using HeyGen’s new AI Agent feature. Keep the frame immediately legible for social media: the viewer should instantly understand that the end goal is ad-ready, creator-native short-form content. Speaker A is upbeat and explanatory, lips visible, medium lip-sync strictness.

[00:10.00-00:22.00] Continue with more proof-driven UGC examples and mobile-native frames. Include finger-pointing or screen-emphasis moments to make the tutorial feel tactile and practical rather than abstract. The presenter keeps speaking and gesturing while showing that the output can pass as social-ready creator content. Use quick cuts with clear result-first momentum.

[00:22.00-00:38.00] Transition into the HeyGen product interface. Show a dark dashboard with AI Agent workflow blocks, setup cards, toggles, and configuration panels. Keep the presenter lower center and have him explain how the feature works in practice. The background should clearly read as real software, not a mockup. Sync sentence accents to UI changes.

[00:38.00-00:49.00] Show deeper operational screens such as a media grid, project organization view, content assets, or an editor-style management panel. The presenter continues with a practical explanation about building, organizing, or scaling UGC outputs through the tool. Maintain a creator-tutorial pace with clean hard cuts and readable interface detail.

[00:49.00-00:57.79] Close with the presenter more dominant in the frame while HeyGen context remains visible behind him. End with a direct CTA asking viewers to comment “AI” for the link. Make the final frame readable, conversion-oriented, and clearly tied to the value already demonstrated.

NEGATIVE PROMPT

Avoid warped phone screens, unreadable dashboard text, messy cutout edges around the presenter, drifting face identity, fake-looking UGC footage, over-animated transitions, robotic narration, slurred speech, lip-sync mismatch, clipping, room echo, low-contrast CTA text, random wardrobe changes, muddy UI panels, flicker, frame jitter, and generic ad visuals that do not feel native to social feeds.

SHOT PROMPTS

- Hook delta: mobile-native UGC proof clip with presenter lower center
- Proof delta: more creator-style examples and finger-point emphasis
- Dashboard delta: dark HeyGen AI Agent setup interface
- Management delta: media grid / project organization view
- CTA delta: presenter-forward finish with comment-for-link ask

SPEECH PACK

Timecoded transcript (best-effort observable reconstruction)
- [00:00.00-00:10.00] Speaker A: “Here’s how to create UGC-style content using HeyGen’s new AI Agent feature.” Emotion: upbeat, hook-first.
- [00:10.00-00:22.00] Speaker A: “This lets you generate social-native creator content much faster while keeping the output usable for marketing.” Emotion: confident, proof-oriented.
- [00:22.00-00:38.00] Speaker A: “Let me show you the HeyGen workflow and how the AI Agent part fits in.” Emotion: practical, tutorial-focused.
- [00:38.00-00:49.00] Speaker A: “From here you can manage the content, examples, or project setup inside the dashboard.” Emotion: tactical, steady pace.
- [00:49.00-00:57.79] Speaker A: “Comment ‘AI’ for the link.” Emotion: punchy CTA close.

TAKE_A
- Keep the wording close to the lines above with creator-marketing energy.

TAKE_B
- Same meaning, slightly faster and more ad-operator focused.

TAKE_C
- Same meaning, calmer and more educational.

Closest audible version
- Exact speech was not transcribed verbatim, so the lines above represent closest observable tutorial intent supported by caption, UI context, and pacing.

Safe paraphrase version
- The reel explains how to use HeyGen AI Agent to create UGC-style content and ends by asking viewers to comment “AI” for the link.

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.

Vertical comedic office mockumentary about being an “AI artist,” set in a bright open-plan creative workplace. A bearded man in casual office clothes walks through the hallway carrying work materials, then sits at a desk and deadpans to camera that making films with AI is extremely simple, as if all you have to do is press a big red button. The reel cuts between him speaking confidently in interview-style framing, bold oversized on-screen text calling him “THE AI ARTIST,” shots of thick paper briefs and office tasks, an elderly colleague handing over documents, and absurd visual metaphors where everyday chores or output volume become part of the joke. The tone should be satirical and self-aware, poking fun at the idea that AI filmmaking is effortless while also showcasing the studio environment and creative process. Clean commercial lighting, office comedy pacing, direct-to-camera delivery, punchy captions, and workplace absurdity rather than dramatic storytelling.

GLOBAL LOCK: A vertical 9:16 creator-education reel about Kling Motion Control, built as a fast software explainer with the creator speaking to camera while visual demos, split-screen comparisons, and UI walkthroughs appear above or behind him. Keep the presenter stable throughout: male creator in a cream t-shirt and tan cap seated in a dark chair setup, casual but confident tutorial delivery, direct-to-camera speech, and small picture-in-picture anchor framing. The visual language should mix creator commentary with proof-driven software demonstrations: side-by-side labels such as Original and Kling AI, the Kling interface showing Motion Control options, and striking examples of transferred gesture performance into new characters or stylized subjects. The key product message is precise motion direction, gesture replication, and expression control inside AI-generated videos, not just basic animation. Lighting for the presenter remains consistent and controlled, while demo clips vary by scene. Audio is narration-led, fast, excited, and creator-native. The reel should feel like a serious workflow upgrade presented in a high-performing social format.

[00:00-00:05.0] Open with the creator speaking in picture-in-picture while a bold demo example fills the upper frame. The pace should feel immediate and surprising, matching the caption’s “Holy sh*t” energy. Establish that Kling Motion can precisely control how characters move.

[00:05.0-00:11.0] Show split-screen Original versus Kling AI examples that make performance transfer easy to understand. Use dancers, actors, or strong gesture clips where the movement mapping is visually obvious. Labels must make the comparison instantly readable.

[00:11.0-00:16.5] Cut to the Kling interface with an Edit Video workflow and Motion Control panel visible. This segment should feel practical, proving that the feature is an actual user-controlled setting and not a black-box magic result.

[00:16.5-00:21.0] Move into a more visually memorable demo, such as a blue Na’vi-like or stylized character copying a real human facial or hand gesture. Emphasize expression transfer and nuanced face-driven motion, not only body movement.

[00:21.0-00:24.66] Close with the creator’s anchor shot and a concise CTA. The final beat should leave viewers with the sense that Kling Motion makes AI storytelling, ads, and film-style animation more controllable than previous workflows.

NEGATIVE PROMPT: generic AI avatar ad, static talking head only, no split-screen proof, no visible interface, unreadable labels, stiff robotic motion, broken gesture transfer, wrong presenter wardrobe, bright white SaaS layout, no creator anchor shot, no motion control panel, low-detail character examples, random dance footage with no comparison logic, no lip sync, overlong captions, cluttered UI, weak before/after contrast, floating hands, warped faces, cheap meme editing, no CTA.

SHOT PROMPTS:
SHOT 1: Creator in small on-screen box reacting while dramatic Kling Motion demo plays in the main frame.
SHOT 2: Split-screen Original vs Kling AI performance transfer examples with clear motion comparison.
SHOT 3: Kling interface showing Edit Video and Motion Control controls in a practical workflow screen.
SHOT 4: Stylized blue character or alternate identity copying a real human gesture with strong expression fidelity.
SHOT 5: Final creator recap and CTA focused on storytelling, ads, and high-end AI animation control.

SPEECH PACK: Spoken narration is required. Delivery should be energetic, impressed, and creator-educational, with quick pacing and short emphatic sentences. Keep audio clear, punchy, and synced to the creator’s anchor performance while demo clips roll above.

GLOBAL LOCK: horizontal-to-vertical cropped cinematic AI promo reel, hyperreal astronaut-capsule visual motif used as the recurring hero asset, one blond curly-haired white male astronaut in a white EVA suit seated inside a spacecraft cabin beside a second astronaut, muted teal-and-cream cinematic grade, soft filmic contrast, shallow depth of field, premium startup-promo edit style, alternating between talking-point text cards on warm beige backgrounds, floating UI/product mockups, and dark feature boards showing automations and model stacks. Voiceover is implied by subtitle-led pacing rather than visible speaker-to-camera footage, with confident founder-demo cadence and high-end product-marketing clarity.

[00:00-00:05] Open inside a spacecraft cabin on a close cinematic shot of a blond male astronaut in a white suit, lit by soft practicals and teal cabin reflections. Subtitle-led narration states that time was spent building an AI system that creates the most realistic assets. Keep the camera intimate and the environment premium, like a film still rather than generic sci-fi art.

[00:00-00:05] Intercut quick flashes of a second astronaut in the same capsule and text-led beats on minimalist beige title cards, reinforcing the idea that the workflow can be explained in under a minute. The pacing should feel deliberate and persuasive, not frantic.

[00:05-00:12] Cut to spacecraft window and workstation angles, then to the astronaut working at a side panel, while subtitles explain the problem with traditional AI pipelines: too much manual work spread across multiple steps. Preserve the same cinematic asset identity so the audience understands this one astronaut scene is the hero example being discussed.

[00:12-00:20] Introduce clean product and automation visuals on dark boards, showing clusters of image generations and labeled tool ecosystems. Subtitle-led narration explains that instead of doing everything at once, the system focuses on one asset and improves the process through automations. Show brand or tool references like Midjourney, Nano Banana, TapNow, and related creative tools as part of a stacked workflow.

[00:20-00:28] Display the astronaut asset embedded inside UI mockups and variation cards. The same scene appears in multiple frames, implying automated iteration, refinement, and derivative outputs from a single source asset. The edit should make the system feel modular: one cinematic input, many downstream outputs.

[00:28-00:36] Transition to feature-board sequences and gallery walls of generated outputs, then briefly show a challenge or contest card with a prize headline. The visuals should communicate that the workflow is not just for one image but for scalable campaign, content, or challenge production across a broader creative system.

[00:36-00:43] Return to the astronaut close-up, now clearer and more emotionally direct, with the capsule background softened behind the visor. Subtitle-led narration shifts into CTA mode, telling viewers to comment a keyword to receive the workflow. The premium cinematic scene remains the proof asset for the entire pitch.

NEGATIVE PROMPT: cheap sci-fi costume, broken astronaut helmet reflections, warped faces, inconsistent blond hair, generic stock footage look, unreadable UI, cluttered dashboards, oversaturated colors, harsh shadows, flicker, low-detail spacecraft cabin, robotic timing, noisy typography, watermark, temporal jitter.

SPEECH PACK:
- Hook: I spent the last couple of days building an AI system that creates the most realistic assets.
- Beat 1: Traditional AI takes time because you’re doing too many manual steps yourself.
- Beat 2: Instead of doing everything at once, this workflow focuses on one asset and uses automations to improve it.
- Beat 3: It works across tools like Midjourney, Nano Banana, TapNow, and more.
- CTA: Comment TAP and I’ll send you the workflow to try yourself.

GLOBAL LOCK: Horizontal creator-demo video set in a minimalist white studio built around a glossy retro-futurist red terminal or kiosk branded as an AI creation device. The cast includes a young blonde man with curly hair and casual-cool styling, plus a brunette woman in a black camisole or simple fitted top. The red terminal has a built-in screen that first shows a crude stick-figure face, then transitions into a modern AI interface associated with Hedra Agent. The style blends real-life creator demo energy with clean commercial staging: white cyclorama backdrop, bold red hardware centerpiece, yellow subtitle captions, and fast transitions into generated outputs. The core promise is that casual natural-language requests can be turned into structured prompts, AI tool recommendations, and finished visuals.

[00:00-00:08] Open on a cinematic shot of the blonde man sitting in or beside a vintage car with bold yellow subtitle text. The mood feels like a lifestyle ad or stylized short film. The brunette woman appears in adjacent car shots, creating the impression of a polished generated scene.

[00:08-00:14] A pink title card or interstitial appears, then the video cuts into the white studio setup with the retro red terminal. The brunette woman stands beside it while the blonde man faces the screen. Yellow subtitle captions carry the spoken explanation.

[00:14-00:22] The terminal screen shows a simple stick figure, then switches to a Hedra-like interface asking what should be made today. This establishes the joke and the product capability at the same time: conversational input becomes creative output.

[00:22-00:32] Show the interface more clearly. A prompt field, asset options, and example thumbnails appear as the system loads. The presenter explains that the agent can understand casual requests, structure prompts, and route them toward the right generation tools and settings.

[00:32-00:42] Cut to the visual payoff: multiple styled versions of the same man appear side by side in different looks and outfits, demonstrating reference control and character transformation. The clean white background keeps attention on the generated variations and the tool logic above them.

[00:42-00:54] End with more polished studio shots of the brunette woman beside the red terminal while the narration frames Hedra Agent as an easier way to generate strong AI visuals. The overall tone should feel like a product demo wrapped in a playful, high-concept studio vignette.

GLOBAL LOCK:
The video maintains a consistent environment: a brightly lit indoor office/room. In the background, a white dry-erase board is mounted on a light grey wall. The whiteboard features the text "AI'S TO-DO LIST:" followed by numbered items and a small robot doodle. To the right of the whiteboard, a framed black-and-white quote poster is visible. The camera is a static medium shot (MS) at eye level. The lighting is soft, frontal, and even. The color grade is natural with a slight warmth. All characters share a similar facial structure to maintain a "family resemblance" or identity consistency.

[00:00–00:03]
Subject: A young Caucasian woman in her 20s with long, wavy light brown hair. She is wearing a textured grey knitted crewneck sweater.
Action: She looks directly at the camera with a neutral expression, then points her right index finger upward toward a text overlay.
Environment: Office background as described in Global Lock.
Camera: Static Medium Shot.
Speech: No speech, but rhythmic electronic music is playing.

[00:04–00:06]
Subject: A young Caucasian child, approximately 8-10 years old, completely bald. The child wears a simple, coarse brown linen tunic with a V-neck.
Action: The child looks slightly down and to the left, then turns their gaze to the camera. Their hands are held together at waist level.
Environment: Same office background. The whiteboard text remains consistent.
Camera: Static Medium Shot.
Motion: Subtle head movement and blinking.

[00:07–00:09]
Subject: A Caucasian man in his 30s with short, slightly messy reddish-brown hair. He is wearing detailed medieval knight armor, including a chainmail coif and a polished steel gorget/breastplate.
Action: He looks to his right, then slowly turns his head to face the camera with a serious, stoic expression.
Environment: Same office background.
Camera: Static Medium Shot.
Motion: Natural head turn, metallic reflections on the armor.

[00:10–00:12]
Subject: A Caucasian man in his 30s with long, straight platinum blonde hair (Daemon Targaryen style). He wears dark reddish-brown leather armor with intricate dragon-scale patterns and a high collar.
Action: He starts by looking to his left, then turns his head sharply to the camera, maintaining a brooding, intense gaze.
Environment: Same office background.
Camera: Static Medium Shot.
Motion: Smooth hair movement during the head turn.

[00:13–00:16]
Subject: A young Caucasian woman in her 20s with platinum blonde hair styled in intricate, thick braids (Daenerys Targaryen style). She wears a regal blue dress with a textured, scaly pattern.
Action: She looks at the camera with a slight, confident smile and points her right index finger upward toward a "Comment 'AI'" text overlay.
Environment: Same office background.
Camera: Static Medium Shot.
Motion: Subtle hand gesture and facial expression shift.

NEGATIVE PROMPT:
Visual: Blurred background, changing environment, flickering lights, distorted whiteboard text, extra fingers, unnatural hair movement, low resolution, cinematic grain (keep it clean UGC style), morphing facial features between cuts.
Speech/Audio: Distorted music, background noise, muffled audio.

SPEECH PACK:
(Note: This video is purely visual/music-driven with no spoken dialogue.)
Music Profile: Rhythmic, bass-heavy electronic beat with sharp "snap" or "clap" sounds on the transitions.
Sync Requirements: Each character transformation must land exactly on the primary beat/snap of the audio track.
Take A (Visual Pacing): 3-second intervals per character.
Take B (Visual Pacing): Faster 1.5-second cuts for higher energy.
Take C (Visual Pacing): Slow-motion transitions between the final two characters.

WORKFLOW
A) MISE EN PLACE
1) Segment the video into scenes/shots:
- [00:00–00:05] Single continuous shot (A composite split-screen showing two distinct scenes simultaneously).

2) Extract visual evidence:
- Keyframes: 0s, 2s, 4s.
- Left Panel: Caucasian woman, early 30s, blonde hair in a messy ponytail, wearing a mustard-yellow zip-up bomber jacket over a black top. Sitting outdoors at a cafe, daylight, string lights in the blurred background. She is laughing.
- Right Panel: Same woman, identical hair and wardrobe. Sitting indoors at a bar, warm directional lighting, amber bokeh in the background. She is holding a pint glass of beer and taking a sip.
- Overlays: White sans-serif text at the top and bottom.

3) Extract speech evidence:
- No speech. Audio is likely a trending BGM track.

4) Create an "invariants list" (LOCK THESE):
- visuals: The split-screen layout (left/right). The exact appearance of the woman (facial features, blonde ponytail, mustard jacket, black shirt). The static camera framing (MCU) on both sides. The text overlays.
- speech: N/A.

5) Create a "variables list" (TWEAK THESE):
- visuals: The micro-expressions of the laugh on the left. The liquid movement inside the beer glass on the right. The subtle background motion (patrons, bokeh shimmer).

B) SHOTLIST
- shot_id: 1
- timecode_start: 00:00
- timecode_end: 00:05
- duration: 5s
- framing: Split-screen. Both sides are Medium Close-Up (MCU), eye-level camera.
- lens: 50mm equivalent feel, shallow depth of field, creamy bokeh on both sides.
- camera movement: Static on both sides.
- subject: Left: Laughing naturally, slight shoulder movement. Right: Bringing a beer glass to her lips, taking a sip, maintaining eye contact.
- environment: Left: Outdoor cafe, daytime. Right: Indoor bar, evening.
- lighting: Left: Soft, overcast natural daylight. Right: Warm, moody practical lights, directional key light on the face.
- color grade: Warm overall tint, high contrast between the cool/neutral left and the amber/orange right.
- motion cues: Left: Subtle hair movement in the breeze. Right: Liquid dynamics in the glass.
- SPEECH / AUDIO:
  - speech_present: false

C) STYLE BIBLE
- visual_style: Cinematic UGC / High-end lifestyle B-roll.
- camera_signature: Locked-off tripod feel, shallow depth of field to isolate the subject.
- lighting_signature: Motivated lighting (natural outdoors vs. practical indoors).
- grade_signature: Warm, filmic, rich skin tones, vibrant mustard yellow.
- texture_signature: Photorealistic, sharp subject with soft, pleasing background blur.
- pacing_signature: Slow, deliberate motion suitable for looping.

D) PROMPT SYNTHESIS

MASTER PROMPT
GLOBAL LOCK: A vertical 9:16 split-screen video divided exactly down the middle. On both sides, the exact same subject is featured: a 30-year-old Caucasian woman with blonde hair pulled back into a messy ponytail, wearing a distinctive mustard-yellow zip-up bomber jacket over a black t-shirt. The camera is static on both sides, framed as a Medium Close-Up (MCU) with a shallow depth of field. The top of the video features bold white sans-serif text: "STEP 5: ANIMATE YOUR VIDEOS AS B-ROLL OR TALKING HEAD VIDEOS". The bottom features text: "Animate using Google Veo 3.1 for perfect lip sync or Kling 2.6 Pro for smooth cinematic clips."

[00:00–00:05] The video plays as a continuous 5-second loop. 
ON THE LEFT SIDE: The woman is sitting at an outdoor cafe table during the day. The lighting is soft, natural daylight. The background is blurred, showing outdoor seating and string lights. She is looking directly at the camera, smiling broadly and laughing naturally, with subtle, realistic head and shoulder movements. 
ON THE RIGHT SIDE: The woman is sitting at an indoor bar. The lighting is warm, moody, and directional, casting a soft glow on her face. The background features rich, amber bokeh from pendant lights. She is holding a clear pint glass filled with beer. She slowly brings the glass to her mouth, takes a sip, and lowers it slightly, maintaining steady eye contact with the camera throughout the motion. The liquid in the glass moves realistically. Both sides play simultaneously in a photorealistic, cinematic style.

NEGATIVE PROMPT
morphing, warping, inconsistent facial features, changing clothes, different person on left and right, bad anatomy, extra fingers, distorted glass, floating objects, unnatural lighting, plastic skin texture, jittery motion, flickering text, spelling errors in text overlays.

SPEECH PACK
No speech present in the reference video.

GLOBAL LOCK: A vertical 9:16 creator-economy tutorial reel that alternates between one male presenter speaking directly to camera and rounded-corner cinematic demo clips or dark-mode screen recordings above him. The presenter is a light-skinned man in his 20s or early 30s with side-parted brown hair, clean-shaven face, slim build, expressive hands, and a friendly but high-energy delivery style. He wears a cream textured overshirt or knit jacket over a black crew-neck shirt and speaks into a black podcast microphone positioned centrally in front of him. The base environment is a dark charcoal studio with soft frontal key light, warm amber background glow, crisp digital sharpness, and social-first edit pacing. The insert window above him cycles through realistic AI film shots, portrait references, and Higgsfield/Kling 3.0 interface screens. Speech should feel like an enthusiastic tutorial and sales-demo hybrid: one speaker, close-mic audio, clean articulation, medium-fast cadence, excited emphasis on realism, workflow ease, and the CTA to comment for the guide.

[00:00-00:07] Open on a dark vertical layout with bold white headline text reading “100% Made with AI” across the top. In the upper rounded insert window, show moody green-and-gold cinematic scenes with shallow depth of field, including a dim interior and an extreme close-up of a burning match or cigarette ember touching the floor. In the lower rounded talking-head panel, the creator points upward and speaks directly into the microphone with animated eyebrows and raised finger, introducing how realistic the AI results now look. Keep the lighting warm on his face and the lip-sync fairly tight.

[00:07-00:14] Accelerate into a realism montage in the upper insert: a boxing-ring close-up with a glove pushing into lens, a sharply lit city-street action shot of a man smashing glass with a bat, and a vintage car interior with a suited man driving through daylight streets. In the lower panel the same presenter keeps talking continuously, hands moving in small punches that match edit accents. Preserve clean, close podcast audio and energetic tutorial cadence.

[00:14-00:20] Cut to a portrait-reference stage. In the upper portion, show a full-body male character standing barefoot in a Japanese-style tatami room under a paper lantern, with the word “PORTRAIT” visible above. The man has dark hair, a dark hoodie, and light sweatpants, arms folded, used as the identity anchor for later generations. The presenter below explains this is the starting character image or reference needed for consistent output. Lighting in the reference image is neutral indoor daylight with soft warm wood trim.

[00:20-00:26] Transition to a dark-mode Higgsfield interface screen recording. The cursor scrolls past model cards where “Kling AI 3.0” is clearly visible, along with other video-generation options. The creator remains in the lower panel, still speaking in a persuasive, teacher-like tone about using the newest model and current offer. UI motion is smooth and cursor-driven; edits land on emphasized words.

[00:26-00:35] Move deeper into the workflow. Show upload panels, prompt fields, and example cinematic stills in the upper insert while the creator explains how to set up the generation. One prompt card references a character smoking and another visible text prompt describes the person getting frustrated while drawing, tearing up the page, and throwing it away. Keep the interface dark, minimal, and product-demo realistic. The presenter below gestures with one hand while staying centered in the lower frame.

[00:35-00:45] Display the generated sketching sequence in the upper insert: the same male character sits in a workshop or cluttered room with a cigarette in his mouth, sketching intensely on paper under greenish tungsten lighting. Follow with a close-up of the pencil drawing a car, then show a start-frame and end-frame layout above a bright yellow “Generate” button, making the interpolation workflow obvious. Speech continues as a single uninterrupted explanation about how to prompt scenes and transitions while preserving realism and identity.

[00:45-00:54] Finish with a rapid cinematic payoff montage. The upper insert cycles through fireworks reflecting in a man’s sunglasses, a pink balloon near an older man’s face, a fiery explosion in the sky, a plane-window travel shot, and finally a suited man by the airplane window. Over the top, bold CTA text appears: “Comment ‘AI’”. The presenter below raises his finger again and delivers the closing call to action for the guide and links. Audio remains one-speaker, close-mic, confident, slightly urgent, with no crowd noise and with the final CTA synced to the on-screen text.

NEGATIVE PROMPT: inconsistent face shape between shots, different hair color, extra fingers, broken glasses reflections, rubber skin, flat UI screenshots, unreadable prompt boxes, cheap green-screen compositing, low-detail backgrounds, jittery motion, robotic lips, muddy audio, crowd ambience, subtitles, watermarks, duplicated props, oversaturated neon color cast.

SHOT PROMPTS: dark studio creator tutorial; rounded-corner insert window; 100 percent made with AI hook; cinematic realism montage; boxing insert; glass-smash action shot; vintage car driver; portrait reference in tatami room; Higgsfield dark-mode UI; Kling 3.0 model card; upload-image workflow; prompt field; frustrated drawing prompt; cigarette sketching scene; start-frame end-frame generation; fireworks reflected in glasses; plane-window final montage; comment AI CTA.

SPEECH PACK: Single male speaker only. Tone should be excited, persuasive, and instructional, like a creator sharing a breakthrough workflow and an exclusive offer. Keep close-mic podcast texture, medium-fast pace, clear consonants, and strong emphasis on “Kling 3.0,” “realism,” and the final “comment AI” call to action.

GLOBAL LOCK: The subject is a Caucasian male in his early 30s with medium-length, wavy brown hair and a full, well-groomed brown beard. He consistently wears a dark forest-green crewneck sweatshirt and a cream-colored trucker hat with a black "VANS" logo on the front. The lighting is bright, professional studio lighting. The video style is a high-energy montage of photorealistic AI-generated scenes mixed with a UI walkthrough.

[00:00–00:01]
Subject: Matthew McConaughey lookalike in a blue Dodgers jersey, holding a plastic cup of beer and a hot dog.
Environment: A sunny, crowded baseball stadium (Dodger Stadium) with "DODGERS WIN" on the big screen.
Action: Smiling broadly at the camera.
Camera: Medium shot, static.
Lighting: Bright, direct afternoon sunlight.
Grade: Saturated, vibrant colors.

[00:01–00:02]
Subject: Kai Cenat (Black male with dreadlocks) and Steve Jobs (older Caucasian male with glasses and black turtleneck).
Environment: A modern podcast studio with professional microphones and soundproofing.
Action: Kai is pointing and laughing; Steve Jobs is smiling and looking at a monitor.
Camera: Medium shot, side-by-side composition.
Lighting: Soft studio lighting with green LED accents in the background.

[00:02–00:04]
Subject: A basketball player in a white Lakers jersey being interviewed by a female reporter. A person in a giant yellow banana mascot suit stands behind them.
Environment: An indoor basketball arena (Crypto.com Arena) with "LAKERS WIN" on the screens.
Action: The reporter holds an ESPN microphone; the banana mascot waves.
Camera: Medium wide shot, broadcast TV style.
Lighting: Bright arena floodlights.

[00:04–00:06]
Subject: The GLOBAL LOCK subject (creator) wearing a teal-green "Squid Game" tracksuit with the number "456".
Environment: The glass bridge from Squid Game, high above a dark abyss.
Action: The subject is lying flat on a glass pane, looking down with a terrified expression.
Camera: High-angle shot looking down, then a low-angle shot looking up at him.
Lighting: Moody, dramatic, with cool blue and green tones.

[00:06–00:08]
Subject: The GLOBAL LOCK subject in the Squid Game tracksuit.
Environment: A CNN-style news studio with a "BREAKING NEWS" ticker that says "SQUID GAME 'SURVIVOR' SPEAKS OUT".
Action: The subject is being interviewed by a news anchor, gesturing with his hands while speaking.
Camera: Medium shot, over-the-shoulder of the anchor.
Lighting: Flat, bright newsroom lighting.

[00:08–00:10]
Subject: The GLOBAL LOCK subject and an older male commentator.
Environment: An F1 commentary booth overlooking a race track with cars speeding by in the rain.
Action: The subject is shouting into a headset, giving a "thumbs up" and looking ecstatic.
Camera: Medium shot inside the booth.
Lighting: Natural overcast light from the track mixed with warm interior booth lights.

[00:10–00:13]
Environment: A large, empty, modern white living room with light wood floors and large windows.
Action: Furniture (sofas, rugs, chairs, lamps) appears in a "pop-in" animation, fully furnishing the room.
Camera: Wide shot, static.
Lighting: Bright, airy, natural daylight.

[00:13–00:16]
Visual: A hand with a yellow pencil drawing a 6-panel storyboard.
Action: The sketches transform into finished, colored comic-book style panels showing a man drinking a Red Bull and gaining wings to run a race.
Camera: Top-down view of the paper.

[00:16–00:19]
Visual: A blue architectural blueprint of a two-story house.
Action: The blueprint seamlessly transitions into a photorealistic 3D render of the finished house with a green lawn and stone path.
Camera: Front elevation view.

[00:19–00:22]
Subject: The GLOBAL LOCK subject.
Action: An extreme close-up of his face, focusing on the eye and skin texture.
Camera: Extreme close-up (ECU).
Lighting: Soft, directional light highlighting skin pores and beard detail.
Text: "4K Resolution" overlays the screen.

[00:22–00:35]
Visual: Screen recording of the Higgsfield AI interface.
Action: A cursor navigates through "Explore", "Image", and selects "Nano Banana Pro". A face photo of the subject is uploaded. A prompt is typed into the box: "the bachelor tv show, with the tv ui interface around it". The "1k" quality button is clicked, showing a dropdown for "4k". The "Generate" button is pressed.

[00:35–00:40]
Subject: The GLOBAL LOCK subject in a white t-shirt and his "Vans" hat.
Environment: The set of "The Bachelor" finale, with a host and several female contestants in evening gowns on couches.
Action: The subject is sitting on the couch, looking slightly awkward but smiling, clapping his hands.
Camera: Wide shot of the set, then a medium shot of the subject.
Lighting: Warm, high-key romantic studio lighting.

NEGATIVE PROMPT: robotic movement, distorted faces, inconsistent beard growth, blurry textures, low resolution, flickering lights, extra fingers, warped background architecture, unnatural lip-sync, watermarks, text logos on clothing (except VANS), jittery camera motion.

SPEECH PACK:
[00:00–00:01] "Holy sh*t, Google's done it again." (TAKE_A: High energy, shocked. TAKE_B: Fast, breathless. TAKE_C: Deep, impressed.)
[00:01–00:04] "You can now create AI imagery that is so realistic, that it's indistinguishable from reality." (TAKE_A: Authoritative, clear. TAKE_B: Enthusiastic, rhythmic. TAKE_C: Slow, emphasizing 'indistinguishable'.)
[00:04–00:10] "And you can even be the main character in any scene that you can dream of." (TAKE_A: Personal, inviting. TAKE_B: Fast-paced, exciting. TAKE_C: Warm, storytelling tone.)
[00:10–00:19] "You can upload six reference images and combine it into one scene. And the creative application that people are using this for right now is genuinely mind-blowing." (TAKE_A: Informative, steady. TAKE_B: Punchy on 'mind-blowing'. TAKE_C: Professional, instructional.)
[00:19–00:22] "The crazy part is is that you can generate images in 4k resolution." (TAKE_A: Whispered excitement. TAKE_B: Direct to camera, confident. TAKE_C: Emphasizing '4k'.)
[00:22–00:35] "To access it, go to Higgsfield and go to image and select Nano Banana Pro. From here, upload a reference image of your face and put in a basic prompt. Select this button and you can generate images in 4k resolution and it's unlimited with 65% off right now." (TAKE_A: Fast tutorial pace. TAKE_B: Clear, step-by-step. TAKE_C: Sales-oriented, energetic.)
[00:35–00:40] "So if you want to try it out, type AI in the comments and I'll send you the link." (TAKE_A: Direct CTA, friendly. TAKE_B: Pointing up, engaging. TAKE_C: Casual, helpful.)