AI Icon Generator

GLOBAL LOCK:
Subject is a Caucasian male, mid-20s, with short brown hair and a light beard, wearing a tan "VANS" trucker hat and a plain white t-shirt. He is positioned in the bottom third of the frame in a talking-head format. The top two-thirds of the frame is a digital workspace. The environment for the subject is a cozy room with warm, out-of-focus background lighting. The digital workspace is a clean, modern software UI with a white background. The video has a high-energy, fast-paced UGC tutorial style. Speech is enthusiastic, clear, and direct-to-camera.

[00:00–00:03]
The top 2/3 shows a rapid succession of Taylor Swift posters. First, a red and black vintage-style poster with "TAYLOR" in large block letters. Then, a collage-style poster with denim textures and "TAYLOR SWIFT" in a stylized font. The subject at the bottom is talking excitedly, gesturing with his hands.

[00:04–00:06]
The top 2/3 switches to Post Malone posters. One is a gritty, black-and-white screen-print with a red star over his eye and "POST" in red spray-paint font. The next is a profile shot with "F-1 Trillion" text in pink. The subject continues his energetic narration.

[00:07–00:14]
The top 2/3 shows a breakdown of a Leonardo DiCaprio poster. A portrait of DiCaprio appears on the left, a text prompt on the right. A progress bar fills, and a "Wolf of Wall Street" poster is revealed, featuring a screen-print texture and yellow/black color scheme. The subject points upwards toward the visuals.

[00:15–00:25]
The top 2/3 shows the "Lovart" website interface. A cursor clicks "New Project." The subject explains the tool. The cursor types "Create me a poster for Ed Sheeran" into a chat box. A model selection menu pops up, and "Nano Banana Pro" is selected.

[00:26–00:37]
The top 2/3 shows an Ed Sheeran poster being generated. It features him with a guitar against a sunset background. The subject demonstrates iterations: the text at the bottom changes to "NEW YEAR'S EVE" and "LAS VEGAS SPHERE." The style then shifts to a high-contrast green and black screen-print.

[00:38–00:42]
The entire frame transitions to a real-world scene. A man in a tan jumpsuit, seen from behind, is taping a large white poster onto a red brick wall. The poster features a black circular logo and the text "COMMENT AI." The subject appears in a small bubble at the bottom, saying "type AI in the comments."

NEGATIVE PROMPT:
Visual: blurry face, distorted hands, flickering UI elements, inconsistent hat logo, low resolution, messy background, unnatural eye movements.
Speech: robotic tone, monotone delivery, background noise, muffled audio, lip-sync mismatch, stuttering, long pauses.

SPEECH PACK:
[00:00–00:06]
TAKE_A: "Google Nano Banana Pro is mind-blowing when it comes to creating graphic design work. You can take any character and create any poster design."
TAKE_B: "Nano Banana Pro is a total game-changer for design. Take any celeb, any style, and boom—instant professional posters."
TAKE_C: "This new AI model is insane for graphics. One reference photo is all you need to make these incredible celebrity posters."

[00:07–00:14]
TAKE_A: "With one reference image of their face and a basic prompt. So I'm going to show you exactly how you can get the best results."
TAKE_B: "Just one photo and a simple sentence. I'll show you the secret to getting these high-end results every single time."
TAKE_C: "Reference photo plus a basic prompt equals this. Let me walk you through the process for the best output."

[00:15–00:25]
TAKE_A: "To get started you want to go to Lovart, which is a dedicated AI design tool. You can now write in a basic prompt, then select Google Nano Banana Pro."
TAKE_B: "Head over to Lovart—it's built for designers. Type your idea, pick the Nano Banana Pro model, and you're ready."
TAKE_C: "Step one: open Lovart. It’s an AI design powerhouse. Enter your prompt, choose the Google model, and watch the magic."

[00:26–00:42]
TAKE_A: "Once you hit generate, it will use its own prompt enhancer. Now you can iterate, change text or backgrounds. Type AI in the comments for the link!"
TAKE_B: "Hit generate and let the AI enhance your prompt. Tweak the text, swap the background, it's that easy. Comment AI for access!"
TAKE_C: "Generate, iterate, and perfect. Change anything you want in seconds. If you want to try this, just type AI below!"

A vertical talking-head tutorial reel hosted by a young white male creator seated against a solid warm orange studio backdrop. Large kinetic captions introduce a test of multiple AI image and video tools for generating professional-looking avatars. The edit alternates between direct-to-camera explanation, moody retro-tech B-roll of the host at a vintage CRT computer in a dim teal-and-amber room, stylized example portraits arranged in tiled grids, and cinematic concept scenes featuring human characters, analog screens, and fashion-editorial lighting. One standout shot shows a television-headed figure standing beside a woman in a patterned dress, labeled “Midjourney.” Other segments show portrait matrices and tool comparisons, with the overall visual language leaning cinematic, grainy, nostalgic, and premium rather than clean SaaS tutorial aesthetics.

GLOBAL LOCK: vertical 9:16 creator tutorial reel, one consistent young adult male host with light skin, slim build, black backwards baseball cap, black hoodie, seated at a desk with a black microphone accented by red lighting, dark studio background with magenta-blue rim light, clean social-media talking-head aesthetic, frequent cutaways to iPhone screen recordings and desktop UI captures, crisp contrast, sharp subtitles, direct-to-camera educational delivery, fast pacing, screen-demo workflow energy, voice remains the same confident male speaker throughout, close-mic sound with dry room tone and clear consonants.

[00:00-00:03] Open with a high-speed hook collage: several glossy AI-generated coin or medallion-style motion-graphic examples appear at the top while bold thumbnail text promises viewers they can make this from their phone. Cut immediately into an iPhone screen showing a text field and app navigation, establishing a mobile-first tutorial workflow.

[00:03-00:06] Continue with phone screen recordings of typing into ChatGPT or a GPT search interface. Show keyword searches for the right assistant or GPT tool while subtitle words land one by one. The host is not always visible, but his narration stays continuous, fast, and instructional, with cuts landing on emphasized phrases.

[00:06-00:10] Alternate between the host’s face and mobile UI screens. The host looks directly at camera with a neutral but focused expression, speaking in a concise “here’s the exact process” tone. The phone screen shows menus, search results, and a selected motion-graphics-related GPT or helper.

[00:10-00:14] Move into a message-composition phase on the phone. A long, detailed prompt is typed or pasted into a chat interface requesting motion-graphic image generation with clear visual constraints. Keep the UI legible and the pacing brisk, with punch-ins on key words like image, detailed, or copy.

[00:14-00:18] Show the generated or referenced output and transition into desktop or browser captures featuring AI video or motion tools. Include interfaces associated with cinematic generation platforms like Higgsfield or Kling, with green-accent UI panels and creator-plan messaging visible. The host continues narrating over the demo, explaining what to do next.

[00:18-00:23] Demonstrate the next workflow step inside editing or generation panels: toggling options, selecting presets, setting a background or text layer, and preparing a motion graphics sequence. Intercut brief returns to the host in the studio so the viewer stays anchored to a single teacher guiding the process.

[00:23-00:28] Show more UI interactions that build the final result: adding text, adjusting layout, or exporting motion elements. The host remains seated in the same setup, speaking clearly into the desk microphone, with subtitles emphasizing functional words like background, text, yourself, and links.

[00:28-00:32] End on the host full-screen in the studio, centered and speaking directly to camera with a strong CTA tone. He gestures minimally, stays upright behind the microphone, and closes by telling viewers where to get the links or workflow resources. The final beat should feel like a practical creator tutorial, not a cinematic montage.

NEGATIVE PROMPT: broken smartphone UI, unreadable text, warped hands, inconsistent host identity, changing wardrobe, duplicate microphones, messy desk clutter, random overlays, flickering screen recordings, fake app interfaces, low-resolution subtitles, robotic lip sync, slurred narration, echoey room sound, harsh sibilance, clipping, jittery cuts, watermark, logo corruption.

SPEECH PACK:
- Hook: You can make motion graphics like this straight from your phone.
- Beat 1: Start inside ChatGPT and find the right GPT or helper for motion-graphics prompts.
- Beat 2: Ask it for a detailed image prompt first, then move that output into your video-generation workflow.
- Beat 3: Use tools like Kling or Higgsfield to animate the asset, then add your background and text treatment.
- CTA: I’ve got the links and setup in the caption, so save this and try it yourself.

GLOBAL LOCK: A high-definition screen recording of a web browser. The interface is the Freepik website in dark mode. The cursor is a standard white arrow. The subject identity is a consistent AI-generated character: a blonde woman with a friendly, professional appearance, light skin tone, and casual-chic wardrobe. The environment is the Freepik AI Image Generator workspace. The lighting is the digital glow of the UI. The color grade is clean, high-contrast, and modern. The speech is a warm, enthusiastic female voiceover, recorded with a close-mic, dry studio signature.

[00:00–00:02]
The browser is on the Freepik homepage. The cursor moves smoothly toward the "AI Suite" menu item in the top navigation bar.
Speech: "This is Nano Banana Pro."
Lip-sync: N/A (Screen recording)

[00:02–00:05]
The cursor clicks "AI Suite" and then selects "AI Image Generator." The page transitions quickly to the generator workspace.
Speech: "I spent the last two days testing it."

[00:05–00:08]
The user clicks the model selection dropdown. The list scrolls down to reveal "Google Nano Banana Pro." The cursor selects it.
Speech: "It is mind-blowing."

[00:08–00:10]
The user clicks the "Character" tab. A grid of faces appears. The cursor selects the first character, a blonde woman labeled "@johanne."
Speech: "Look at how it handles character consistency."

[00:10–00:13]
The cursor clicks into the prompt box. Text appears rapidly as if pasted: "@johanne - Hyper-realistic studio podcast scene featuring the man sitting across from a bearded neuroscientist in a dim, moody podcast studio..." The user then clicks the "9:16" aspect ratio icon.
Speech: "You just drop in your prompt, pick your ratio..."

[00:13–00:15]
The "Generate" button is clicked. After a brief loading animation, a 2x2 grid of four cinematic, high-quality images appears, showing the character in a professional podcast setting with warm, moody lighting.
Speech: "...and the results are professional grade. Comment 'AI' to try it."

NEGATIVE PROMPT: Visual artifacts, blurry UI text, shaky camera, external glare on screen, messy browser tabs, slow loading times, robotic voiceover, harsh sibilance, background noise, inconsistent character features, low-resolution AI results.

SPEECH PACK:
[00:00–00:05]
TAKE_A: "This is Nano Banana Pro. I spent the last two days testing it." (Enthusiastic, fast-paced)
TAKE_B: "Check out Nano Banana Pro. I've been playing with this for two days straight." (Casual, conversational)
TAKE_C: "You need to see Nano Banana Pro. Two days of testing and I'm hooked." (Authoritative, punchy)

[00:05–00:15]
TAKE_A: "It is mind-blowing. The character consistency is perfect. Just paste your prompt and hit generate. Comment AI for the link." (Clear, instructional)
TAKE_B: "It's honestly mind-blowing. Look at that consistency! Set your ratio, hit generate, and boom. Comment AI to get access." (Excited, high energy)
TAKE_C: "Mind-blowing results. It keeps the character perfectly. One click and you're done. Comment AI and I'll send it over." (Direct, CTA-focused)

GLOBAL LOCK: Vertical 9:16 UGC tutorial reel with a persistent two-layer presentation style: the upper 60 to 70 percent of the frame shows demonstrations, screenshots, typed prompts, and generated image results; the lower portion shows the same male creator speaking directly to camera in a rounded-corner selfie window for most of the video. The creator is a white male in his late 20s to mid 30s, medium-length wavy dark brown hair, short beard and mustache, expressive eyebrows, average build, casual creator aesthetic. Keep his delivery energetic, friendly, and persuasive. Wardrobe changes are intentional by section: white tee and cream Vans cap at the opening studio desk, blue polo and backward cap for the main explainer section, yellow suit jacket and black top hat for the final gag CTA. Upper-frame design alternates between a white studio opening, black presentation slides branded "Google Nano Banana" with a banana emoji, product-demo image canvases, and dark Freepik interface screens on a soft orange-blue gradient background. The reel should feel like an AI creator tutorial ad: quick but readable, clean text overlays, obvious prompt boxes, high contrast UI, fast social pacing, light jump cuts, and consistent bottom talking-head commentary. Speech style is single-speaker direct-to-camera tutorial English with crisp articulation, upbeat cadence, short persuasive sentences, and creator-economy CTA energy. Audio should sound like a close phone or lav mic in a quiet room, lightly compressed, dry, intelligible, and synced to the speaker window.

[00:00-00:04.50] Open on a bright white studio setup. The upper frame shows the colorful Google wordmark above the title "Nano Banana" with a banana emoji. Centered below it, the creator sits behind a white table in a cream Vans cap and light shirt, leaning toward a turquoise striped cup-shaped microphone or tumbler. Softbox lights are visible on both sides, making the setup feel like a casual creator studio. In the lower portion of frame, a separate rounded-corner selfie video of the same man begins speaking directly to camera. He introduces the tool with immediate enthusiasm. Lips are fully visible in the lower video; lip-sync strictness high for the first spoken hook.

[00:04.50-00:10.00] Cut to a black presentation layout branded "Google Nano Banana" at the top. The upper demo area shows a bright outdoor image of the creator on a Grand Canyon style cliff-edge walkway, arms stretched, backpack on, huge sky and canyon behind him. A prompt box appears under the image and begins typing "Make it into a youtube thumbnail". The lower selfie speaker remains on screen in the blue polo and backward cap, gesturing with one hand while explaining the edit. The tone is excited, helpful, and a little amazed. Keep the typed prompt animation readable and central.

[00:10.00-00:14.50] The same canyon image updates into a louder thumbnail treatment with giant curved yellow "GRAND CANYON" text behind the creator’s head. Emphasize the before-and-after value clearly: same base photo, more clickable YouTube-style packaging. The lower speaker continues talking in sync with hand gestures. Audio remains a crisp tutorial voice, no music overpowering the speech.

[00:14.50-00:20.50] Transition to a luxury product-edit example. In the upper frame, a prompt card reads "Replace the bottle" with a small reference thumbnail, then the output becomes a glossy Dior Sauvage-style perfume bottle on swirling golden light trails over a dark brown-black studio background. Maintain premium ad aesthetics, reflective glass, centered bottle, and luminous streaks. The lower talking-head explains the edit use case, likely referencing product replacement or image transformation. Speech stays fast, punchy, and creator-friendly.

[00:20.50-00:24.00] Briefly show another generated image example in the upper area, including a polished portrait-style output that demonstrates broader image editing capability beyond product swaps. Keep the cut quick and social-first, serving as visual proof rather than a full tutorial pause. The bottom speaker window continues uninterrupted, preserving continuity.

[00:24.00-00:31.50] Move into the software walkthrough. The upper frame now shows the Freepik dark UI over a soft gradient backdrop, starting with an AI Suite menu containing categories like image tools, video tools, audio tools, and design tools. Then zoom into the model panel where "Google Nano Banana" is selected, with image reference slots, style/composition/effects/character/object controls, and a beta disclaimer about aspect ratio. The creator in the lower window counts features with his fingers while describing how to access the workflow. Keep the UI readable enough for social tutorial viewing, but still fast-paced.

[00:31.50-00:36.50] Continue the interface demo with more dark UI panels, prompt fields, thumbnails, and settings sections scrolling or cutting through the workflow. The creator keeps speaking in direct, practical language, as if walking viewers through where to click and how to upload references. Camera on the lower speaker remains static, head-and-shoulders, neutral indoor room with door and wall behind him.

[00:36.50-00:43.00] End with a comedic CTA transformation. The upper frame shows a prompt reading "Give him a sign to hold" while the creator appears dressed like a theatrical ringmaster or showman in a yellow jacket and tall black top hat on a sunlit balcony. He holds a handmade cardboard sign that reads "Comment AI and I'll send you the link!" The lower talking-head still speaks beneath, landing the call to action. The final beat should feel playful, persuasive, and optimized for comments. Lip-sync remains visible in the lower window; key sync accents should land on the CTA words "comment AI" and "send you the link".

NEGATIVE PROMPT: extra fingers, warped hands during gesturing, drifting facial hair, inconsistent eye color, duplicated selfie windows, unreadable UI, misspelled "Google Nano Banana", broken prompt boxes, random logos, muddy text, incorrect YouTube thumbnail lettering, deformed perfume bottle glass, floating product shadows, overexposed softboxes, messy background clutter, cinematic bokeh that hides the tutorial content, abrupt framing jumps, desynced speech, robotic cadence, slurred consonants, harsh sibilance, echoey room tone, loud background music, clipping, pumping compression, lip-sync mismatch, subtitle blocks covering the demo.

SHOT PROMPTS:
SHOT_1 [00:00-00:04.50]: White studio opener, Google Nano Banana title, creator at desk with Vans cap and turquoise cup, bottom selfie explainer starts.
SHOT_2 [00:04.50-00:10.00]: Black branded demo screen, Grand Canyon reference photo, typed prompt box for YouTube thumbnail conversion, bottom speaker explains.
SHOT_3 [00:10.00-00:14.50]: Thumbnail result reveal with giant GRAND CANYON text, same split-screen layout, energetic creator commentary.
SHOT_4 [00:14.50-00:20.50]: Product-edit demo, perfume bottle replacement prompt, luxury golden-light result, bottom speaker continues.
SHOT_5 [00:20.50-00:24.00]: Quick alternate polished image result proving editing range.
SHOT_6 [00:24.00-00:31.50]: Freepik AI Suite walkthrough, dark UI menus, Google Nano Banana model selected, image reference slots and controls visible.
SHOT_7 [00:31.50-00:36.50]: More UI steps, prompt/settings panels, creator explains workflow and uploads.
SHOT_8 [00:36.50-00:43.00]: Final joke CTA, top hat outfit, cardboard sign asking viewers to comment AI for the link, bottom talking-head closes the pitch.

SPEECH PACK:
Timecoded transcript (best-effort, inferred from visible overlays and tutorial cadence):

[00:00-00:04.50]
TAKE_A: "Please use this if you have not already. It is a game changer."
TAKE_B: "If you are not using this yet, you need to. It is a total game changer."
TAKE_C: "This tool is a game changer, and you should absolutely be using it already."
Prosody: fast hook, confident, slightly urgent, friendly creator tone.

[00:04.50-00:10.00]
TAKE_A: "You can take an image like this and ask Nano Banana to turn it into something more clickable."
TAKE_B: "Watch this. I can upload a photo and prompt Nano Banana to make it into a YouTube thumbnail."
TAKE_C: "Here is a simple example. Drop in an image and tell it to make a YouTube-ready thumbnail."
Prosody: explanatory, upbeat, demonstration-first.

[00:10.00-00:14.50]
TAKE_A: "It keeps the subject but gives you a much stronger thumbnail treatment."
TAKE_B: "Same image, better packaging. That is why this is so useful for creators."
TAKE_C: "This is the kind of upgrade that makes basic content feel publish-ready."
Prosody: impressed, selling practical value.

[00:14.50-00:20.50]
TAKE_A: "You can also do product swaps, like replacing the bottle and turning it into a premium ad."
TAKE_B: "It is not just thumbnails. You can replace products and restyle the entire scene."
TAKE_C: "This works for product creatives too. Swap the object and it rebuilds the shot around it."
Prosody: persuasive, slightly faster, feature-stack delivery.

[00:20.50-00:24.00]
TAKE_A: "And it is not limited to one type of image either."
TAKE_B: "You can use the same workflow across different visual styles."
TAKE_C: "That flexibility is what makes the tool stand out."
Prosody: transitional, concise.

[00:24.00-00:31.50]
TAKE_A: "Inside Freepik, open the AI Suite, choose Google Nano Banana, and upload your image references."
TAKE_B: "If you want to try it, go into AI Suite, pick the Nano Banana model, then add your reference image here."
TAKE_C: "This is where it lives in Freepik. Select the model, drop your images in, and start prompting."
Prosody: instructional, practical, clear enunciation.

[00:31.50-00:36.50]
TAKE_A: "Then you can use the style, composition, effects, character, and object controls to shape the result."
TAKE_B: "From here you fine-tune the edit with the controls and prompt box."
TAKE_C: "Once the image is in, the rest is just directing the model with these tools."
Prosody: matter-of-fact, tutorial rhythm.

[00:36.50-00:43.00]
TAKE_A: "Want to try it? Comment AI and I will send you the link with unlimited generations on Freepik."
TAKE_B: "If you want access, comment AI and I will send you the link."
TAKE_C: "Comment AI for the link and I will send it over."
Prosody: bright CTA, direct ask, strong emphasis on "comment AI".

MASTER PROMPT
GLOBAL LOCK: Vertical 9:16 AI-tool explainer reel with a single male creator presenter anchored in the bottom portion of frame while app-building interfaces and phone mockups take over the upper portion. The host is a Caucasian man in his late 20s to early 30s with fair skin, blue eyes, medium brown side-swept hair, slim build, energetic facial expressions, wearing a dark crew-neck top, speaking into a black desktop microphone. Keep the host framed in a warm, dim studio with soft amber-brown lighting and high contrast, while the software visuals use dark navy and charcoal UI, white cards, purple accent buttons, and bright mobile previews. The overall rhythm is fast, product-demo heavy, with one continuous enthusiastic male voice, close-mic, dry audio, and short creator-education phrasing. Maintain a clean social-video style, crisp UI text, and frequent hard cuts timed to claims and interface reveals.

[00:00-00:04] Open on a tall phone UI mockup showing a modern consumer app feed with rounded cards, small circular avatars, image-heavy modules, and purple buttons in the top-right area. The host appears below, gesturing while explaining that entire apps can now be built from a single line of text. Tight vertical layout, no camera movement, dark background around the phone mockup, warm presenter lighting below.

[00:04-00:08] Switch to a dark interface screen with a centered prompt box. White text examples appear inside the box, including short instructions similar to “Create me a tinder-like app” and “from idea to app instantly.” The cursor and modal style suggest a prompt-to-product builder. The host continues in an excited, incredulous tone about how quickly this technology has changed.

[00:08-00:12] Return to interface previews and app screens on a navy backdrop. The upper portion cycles through generated layouts while the presenter remains visible beneath, keeping eye contact with the camera and punctuating key words with his hands. Cuts are fast but readable, emphasizing that the app is being assembled automatically from a short instruction.

[00:12-00:16] Show a generated mobile screen with a pet-themed interface featuring a large cat image card and simple action controls, demonstrating the range of app styles the tool can output. The host’s talking-head window stays anchored below, maintaining personality and trust while the software result occupies most of the screen.

[00:16-00:20] Cut to a moody cinematic insert of a person working at a computer in a dim room, then back to charts, dashboards, and wireframe-like productivity screens. The edit broadens the message from “cool toy” to “serious product-building workflow.” Audio remains one uninterrupted narration, delivered with fast creator-demo cadence.

[00:20-00:24] Display a more practical mobile flow with chat-style UI, utility cards, and a phone preview. A small bottom label mentions changing the main screen image or a similar UI adjustment, implying editable customization after generation. The host stresses that this is no longer hypothetical and that normal creators can use it.

[00:24-00:28] Show a dark prompt/result interface with a purple gradient progress or action bar near the bottom, then a sequence of phone preview screens with more polished layouts. The presenter leans slightly toward the mic and emphasizes the speed and ease of creating an app from plain language.

[00:28-00:32] End on bright mobile mockups featuring bold red and green content cards and rounded interface blocks, suggesting a finished consumer app concept. The host lands a simple CTA equivalent to “comment AI for the link,” with lips fully visible and a clear closing emphasis on the keyword.

NEGATIVE PROMPT
Avoid blurry UI text, broken phone bezels, warped interface alignment, unreadable buttons, duplicated cards, floating icons, inconsistent presenter identity between cuts, muddy studio lighting, over-sharpened face detail, robotic hand gestures, lip-sync drift, noisy room reverb, clipped audio, pumping compression, stuttery screen transitions, and any fake app screens that feel unfinished or visually incoherent.

SPEECH PACK
[00:00-00:04]
Closest audible: “Comment AI for the link.”
Safe paraphrase: Ask viewers to comment a simple keyword to get the resource.
TAKE_A: “Comment AI for the link.” [punchy, direct]
TAKE_B: “Drop AI in the comments and I’ll send the link.” [friendly]
TAKE_C: “Type AI below if you want the link.” [light CTA]

[00:04-00:12]
Closest audible: He says it is wild that entire apps can now be built from one line of text.
Safe paraphrase: He frames prompt-to-app creation as a shocking shift in what creators can do.
TAKE_A: “What a time we’re living in... you can build an entire app from a single line of text.” [amazed]
TAKE_B: “It’s crazy that one sentence can now turn into a full app.” [energetic]
TAKE_C: “This used to sound impossible, and now it’s normal.” [incredulous]

[00:12-00:24]
Closest audible: He keeps describing how the tool turns ideas into usable app layouts and screens.
Safe paraphrase: He explains that the product can generate and customize app interfaces quickly from prompts.
TAKE_A: “You describe the idea, and it starts building the screens for you.” [instructional]
TAKE_B: “This is prompt-to-app, not just mockups.” [emphatic]
TAKE_C: “You can go from concept to interface almost instantly.” [coach tone]

[00:24-00:32]
Closest audible: He closes by telling viewers to comment AI for the link.
Safe paraphrase: Finish with a low-friction keyword CTA tied to curiosity and access.
TAKE_A: “You have to check this out... comment AI for the link.” [closing emphasis]
TAKE_B: “If you want the link, comment AI below.” [short close]
TAKE_C: “Comment AI and I’ll send it over.” [simple CTA]

GLOBAL LOCK: vertical talking-head social commentary reel, smart female tech creator speaking directly to camera from a home desk setup, warm indoor lighting, laptop screen inserts, close-up smartphone-style framing, clear Indian woman in her twenties with long dark hair, articulate founder-energy delivery, occasional cutaways to AI website builder interfaces, search results, example landing pages, and quote screenshots, informative Instagram creator style, punchy opinion-led structure, clean creator-economy editing, no fake office set, no unrelated B-roll, keep the video focused on AI website generation, product quality, and why full-stack automation still breaks down.

[00:00-00:06] Open on the creator facing camera and asking whether AI can already build a website end to end, immediately framing the reel as a personal verdict rather than a neutral tutorial.
[00:06-00:14] Cut to laptop close-ups showing AI website builders, generated landing pages, and product mockups while the creator explains that the tools look promising at first glance but fall apart in real detail.
[00:14-00:24] Return to talking-head delivery while overlays of search results and tool names appear, establishing the landscape of emerging AI website agents and builder products people are currently testing.
[00:24-00:34] Show example posts, founder tweets, and community screenshots as visual evidence while the creator argues that most demos are impressive in isolation but weak once you look at structure, polish, and usability.
[00:34-00:44] Move into the core criticism: AI can generate a visual shell or rough landing page, but it still struggles with nuanced product decisions, information hierarchy, and making a site feel intentionally designed instead of statistically assembled.
[00:44-00:53] Use more screenshots and laptop inserts to support points about hallucinations, brittle interactions, and debugging pain, with the creator explaining that changing one thing often breaks something else downstream.
[00:53-01:00] Bring up the bigger product question: building software is not just writing screens, it is also business logic, tradeoffs, edge cases, and understanding who the product is actually for.
[01:00-01:05] End back on the creator in close-up, delivering a concise takeaway that AI website tools are useful accelerators today but are not yet reliable replacements for real product thinking and hands-on building.

NEGATIVE PROMPT: generic corporate presenter, podcast studio microphones, irrelevant coding montage, futuristic holograms, male spokesperson, fake conference stage, cyberpunk interfaces, random startup office B-roll, distorted laptop screens, unreadable UI, broken hands, extra fingers, plastic skin, overproduced news graphics, unrelated charts, fantasy UI elements.

SPEECH PACK:
- Tone: opinionated, clear, analytical, conversational.
- Delivery: fast creator commentary with emphasis on practical product experience.
- Key ideas: AI site builders are promising but shallow, layout and detail still break, product thinking matters more than one-click generation.

GLOBAL LOCK: 
Subject is a young woman with long, wavy dark brown hair, fair skin with warm undertones. She wears a white ribbed turtleneck sweater and a delicate gold necklace. The environment is a professional studio with a soft, out-of-focus purple and pink gradient background. Lighting is soft three-point studio lighting with a subtle purple rim light on the subject's hair. Camera is a high-quality 4k sensor, 35mm lens feel, shallow depth of field. Speech is direct-to-camera, energetic, clear, and authoritative.

[00:00–00:01]
Split screen composition. Top half: A glossy 3D app icon featuring a stylized white face with glowing neon visor and the text "UNCENSORED" in a red banner. Bottom half: The subject speaking directly to the camera, smiling slightly. Camera is static, MCU.
Speech: "If you go to this"

[00:01–00:03]
Full screen graphic overlay. A 2x3 grid of popular AI tool logos (Runway, Sora, Midjourney, etc.) on black rounded-square backgrounds. The logos appear with a slight pop-in animation.
Speech: "website you get unlimited video"

[00:03–00:04]
The grid of logos changes to a new set of icons including the OpenAI logo and others. Text overlay "generation," appears in yellow.
Speech: "and image generation,"

[00:04–00:07]
Screen recording of a mobile UI. A dark-themed list of AI models scrolls vertically. Models include "Gemini 3 Uncensored," "Model T 2.0 Extended," and "Claude Opus 4.6." Some are marked "CENSORED" in grey, others "UNCENSORED" in blue. Text overlay "AI tools Completely Free all in One place" appears in bold white and yellow.
Speech: "and you can use all premium AI tools completely free all in one place."

[00:08–00:09]
Close-up of the UI. A finger (or cursor) selects "Nano Banana Pro" from a dropdown menu. A text input box says "Describe the image you want to generate in detail."
Speech: "Simply choose your AI model, write"

[00:09–00:10]
The word "your" is typed into the prompt box.
Speech: "your prompt"

[00:10–00:11]
Cinematic AI-generated image: A close-up portrait of a beautiful woman with wind-swept brown hair, golden hour lighting, extremely detailed skin texture, and expressive green eyes.
Speech: "and within just one minute"

[00:11–00:12]
Cinematic AI-generated image: A woman in a yellow vintage outfit and hat, surrounded by yellow flowers, soft cinematic lighting, 35mm film aesthetic.
Speech: "it will create high"

[00:12–00:13]
Cinematic AI-generated video: A woman in a navy tracksuit running happily on a beach with a brown dog jumping beside her. Overcast sky, realistic waves, handheld camera movement.
Speech: "quality images and videos"

[00:14–00:15]
UI demonstration: A cursor clicks a green "Download" icon on a dark interface.
Speech: "that you can customize and download."

[00:16–00:18]
Return to the subject in the studio. MCU, static. She gestures with her hands while speaking. Text overlay "comment Tool" and "send it" appears.
Speech: "Want the link? Comment 'Tool' and I'll send it to you."

NEGATIVE PROMPT:
Visual: blurry face, distorted logos, low resolution, messy background, harsh shadows, unnatural skin texture, flickering overlays.
Speech: robotic voice, monotone delivery, background noise, muffled audio, lip-sync mismatch, stuttering, long silences.

SPEECH PACK:
[00:00-00:01] "If you go to this"
TAKE_A: (Rising intonation, high energy) "If you go to this..."
TAKE_B: (Direct, pointing gesture) "If you go to THIS..."
TAKE_C: (Whisper-like, secretive) "If you go to this..."

[00:01-00:07] "website you get unlimited video and image generation, and you can use all premium AI tools completely free all in one place."
TAKE_A: (Fast-paced, emphasizing "unlimited" and "free")
TAKE_B: (Rhythmic, pausing after "generation")
TAKE_C: (Excited, high pitch on "all in one place")

[00:08-00:15] "Simply choose your AI model, write your prompt and within just one minute it will create high quality images and videos that you can customize and download."
TAKE_A: (Instructional, calm but steady)
TAKE_B: (Fast, emphasizing "one minute")
TAKE_C: (Awe-struck tone during "high quality")

[00:16-00:18] "Want the link? Comment 'Tool' and I'll send it to you."
TAKE_A: (Friendly, inviting, direct eye contact)
TAKE_B: (Urgent, pointing at the camera)
TAKE_C: (Casual, smiling)

MASTER PROMPT
GLOBAL LOCK: Vertical 9:16 creator-style AI image generation tutorial reel. Keep the visual structure consistent: dark background, stacked demo windows, rounded-corner presenter overlay near the lower half, and product screenshots or generated outputs occupying the upper area. The presenter is a bearded man in a beige baseball cap and brown hoodie speaking directly to camera with expressive hand gestures. The tutorial should open with a polished luxury ad-style image, then transition into a dark Generate Image interface with prompt and reference controls, and finish with generated lifestyle portraits and result examples. Preserve fast creator-educator pacing, practical workflow clarity, and social-media-friendly text hierarchy.

[00:00-00:10.00] Open with a strong proof-first visual: a luxury perfume bottle ad image against a rich purple satin-like backdrop. Place the presenter in a rounded picture-in-picture window at the bottom, speaking energetically to camera. The hook should feel like, "here is the kind of polished ad-style result you can create," with the upper image doing most of the persuasive work.

[00:10.00-00:28.00] Shift into the process section. Show a dark image-generation interface labeled around concepts like Generate Image, prompt box, reference styles, remix, auto prompt, or similar controls. Keep the presenter visible in the lower area while he explains how the workflow works. Include reference image boards, prompt panels, or app modules that make the system feel practical and reproducible.

[00:28.00-00:48.92] Move into the results and proof section. Show polished generated portraits or fashion-style outputs, app previews, and example result screens, including a casually dressed bearded man in a city street portrait. The presenter continues narrating while the upper content cycles through outputs, reinforcing that the workflow produces believable, commercially useful visuals. End on the strongest lifestyle result.

NEGATIVE PROMPT
Avoid cluttered multi-window chaos, unreadable UI, generic office stock footage, weak hook visuals, random unrelated outputs, corporate webinar styling, tiny text, dark muddy colors, or a tutorial sequence that explains too much before showing a compelling result.

SHOT PROMPTS
[00:00-00:10.00] Luxury perfume ad visual with presenter overlay.
[00:10.00-00:28.00] Dark Generate Image UI, prompt controls, reference boards, presenter explanation.
[00:28.00-00:48.92] Generated lifestyle portraits and result previews with presenter continuing narration.

SPEECH PACK
Timecoded transcript:
[00:00-00:48.92] Single-speaker tutorial explaining an AI image-generation workflow from polished ad example to interface steps to final outputs. Exact wording unclear; preserve concise creator-teacher delivery.

TAKE_A
[00:00-00:48.92] Fast creator-demo explanation with proof-first opening and simple step-by-step UI walkthrough.

TAKE_B
[00:00-00:48.92] Calm but confident tutorial tone emphasizing how to get polished commercial-looking results.

TAKE_C
[00:00-00:48.92] Slightly more enthusiastic creator cadence focused on workflow usefulness and output quality.

GLOBAL LOCK: A vertical 9:16 creator tutorial reel that demonstrates a hybrid AI-image workflow by pairing one model for aesthetic direction and another for realism. The reel alternates between cinematic desert scenes, chemistry-lab inserts, oversized statement text, and a product-style interface showing model selection. The main cinematic world is a sunbaked desert trailer setting with retro Americana energy: a dusty camper trailer, dry shrubs, mountain backdrop, golden-hour or hard daylight, and two attractive young adults wearing coordinated yellow outfits. The mood should feel like a premium AI film still sequence. The tutorial point is that Midjourney builds the aesthetic, Nano Banana adds realism, and Syntx AI provides access to both under one subscription.

[00:00-00:12] Open on a crisp cinematic desert setup featuring a young woman sitting outside a weathered trailer in a bright yellow jumpsuit or matching yellow outfit. Large text overlays tease that “nobody” is telling viewers the real trick. The frame should feel polished and editorial, with dry desert mountains, a pale old camper, folding chairs, and harsh clean sunlight. Then cut to a young blond man in a similar yellow outfit turning near the same trailer, reinforcing the shared visual universe.

[00:12-00:22] Shift into a montage that visually explains the combination principle. Show chemistry-lab close-ups with gloved hands pouring colored liquids into beakers and test tubes, then layer or collage those inserts with close-up portraits of the desert characters. The point is metaphorical and structural: one ingredient contributes style, the other contributes realism. Keep the typography bold and the edits quick enough to feel like a creator revealing a secret formula.

[00:22-00:30] Reveal the operational proof. Show a dark interface with a “Model selection” dropdown open and Nano Banana highlighted, alongside MidJourney, Seedream, Sora, Flux, Runway Frames, Imagen 4, and more. This is the credibility moment: viewers can see the exact tool stack and understand that the workflow depends on selecting and combining different models inside one platform.

[00:30-00:35] Return to the finished desert footage with the woman in yellow outside the trailer, now with closing CTA text promising the link and prompts for anyone who comments. The final feeling should be that the cinematic result is not the output of one model alone, but of a deliberate pairing between style engine and realism engine.

NEGATIVE PROMPT: generic one-model output, muddy trailer park visuals, inconsistent wardrobe between characters, overprocessed skin, sterile lab images, weak desert lighting, unreadable interface, random color grading, low-detail realism, boring tutorial pacing.

SHOT PROMPTS: desert trailer cinematic scene; woman in yellow jumpsuit outside camper; man in matching yellow outfit; chemistry beaker montage; combine them together concept; model selection dropdown; Nano Banana and MidJourney workflow; Syntx AI multi-tool access; comment AI CTA.

SPEECH PACK: Spoken delivery should feel like a creator exposing a hidden system. Tone is confident, slightly conspiratorial, and conversion-focused, emphasizing “Midjourney for aesthetic,” “Nano Banana for realism,” and “comment AI.”

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."

Create a vertical 9:16 premium AI model promo visual featuring an ultra-realistic close-up portrait of a young woman facing directly into camera against a dark teal background. She has fair skin, dark hair pulled back, subtle natural makeup, and translucent amber-orange eyeglasses catching a precise highlight across the frame. The lighting should be soft but dramatic, sculpting the face with studio precision and emphasizing realistic skin texture, calm eyes, and balanced symmetry. In the composition, glowing yellow ImagineArt 1.0 text appears in the upper right, while Most Realistic AI Model is set large at the bottom like bold creator-marketing typography. The overall feeling should be a polished product ad announcing a highly realistic character-generation model for creators and brands. No clutter, no subtitles, no cartoon styling.

MASTER PROMPT

Create a vertical 9:16 creator reel that rounds up useful AI tools for image and creative-media generation. A male host appears in a lower-frame talking-head window and rapidly walks through different examples above him: dreamy cloud-and-cliff fantasy artwork, a lifestyle portrait sitting above the clouds, beauty-product ad imagery, fashion mockups, tool brand cards such as Hautech.ai and Hugging Face, and large thumbnail grids that suggest broader tool libraries. The tone should be energetic, opinionated, and built for creators looking for new AI resources.

GLOBAL LOCK

- Format: 9:16 AI-tools roundup reel with persistent host commentary.
- Host anchor: bearded male creator in a cap, speaking directly to camera from a lower cutout.
- Topic anchor: curated list of AI tools for image generation, stylized concepts, ad mockups, and creative workflows.
- Visual anchor: each tool or example gets a clean showcase card or full-screen sample image above the host.
- Pace: fast but readable, with each new tool feeling like a fresh recommendation or proof point.

TIMELINE

0.0s - 8.0s
Open with the broad theme of AI tools and a strong visual example such as a giant floating cliff in the clouds. Let the host introduce the roundup while a cinematic fantasy image above him sets the aspirational tone.

8.0s - 18.0s
Move into more polished generative examples: a seated man above the clouds, a beauty or beverage ad image, and clean commercial-style renders. This section should establish that the tools are useful for both artful concepts and marketing visuals.

18.0s - 30.0s
Show specific tool references and interface-adjacent cards, including names like Hautech.ai. Use fashion imagery, lifestyle product scenes, and creative thumbnails to suggest what each tool is good for without becoming a full software walkthrough.

30.0s - 43.0s
End with broader ecosystem references such as Hugging Face or large grids of options, implying deeper exploration beyond the first few tools. The host should close with the sense that this is a curated stack for creators who want practical AI image resources and inspiration.

NEGATIVE PROMPT

No coding-terminal deep dive, no dry enterprise software demo, no overly technical machine-learning jargon on screen, no horror imagery, no unrelated gaming footage, no chaotic meme editing. Keep it creator-focused, visual, and recommendation-driven.

SHOT PROMPTS

- Vertical creator-roundup shot with a male host in a lower commentary box and a floating-cliff fantasy image labeled AI Tools above him.
- Lifestyle concept art example of a man sitting on white steps above the clouds, used as proof of generative image quality.
- Beauty or beverage ad mockup with polished commercial lighting and product-in-hand framing, shown as an AI creative use case.
- Tool recommendation card featuring Hautech.ai with fashion-style imagery and clean presentation.
- Broader ecosystem reference frame featuring Hugging Face and other tool or thumbnail grids to suggest a larger creative AI stack.

SPEECH PACK

- Spoken delivery should sound like a concise creator recommendation reel highlighting which AI tools are worth trying and what kinds of visuals they help produce.
- Audio should prioritize the host with a light, modern background track.

GLOBAL LOCK:
The video features a split-screen layout. The bottom 30% contains a consistent male creator: Caucasian, mid-30s, brown beard, wearing a tan "Vans" trucker hat and a black quilted vest over a white t-shirt. He is in a home office/studio setting with soft indoor lighting. The top 70% features AI-generated cinematic footage. The AI footage must maintain high subject consistency, specifically a character resembling Leonardo DiCaprio in "The Wolf of Wall Street" (short brown hair, blue pinstripe suit, red polka dot tie). The environment is a luxury office with wood paneling. Lighting is cinematic, warm, and professional.

[00:00–00:03]
Subject: A man resembling Leonardo DiCaprio in a blue pinstripe suit and red polka dot tie.
Action: He holds a crisp one-dollar bill horizontally with both hands, looking directly into the camera with a slight, confident smile.
Camera: Medium close-up, static.
Lighting: Warm, high-key office lighting, soft shadows.
Speech: Creator says "It has never been easier to create multiple camera angles..."
Sync: Creator's lips visible in the bottom frame, high sync.

[00:03–00:07]
Visual: A 3x3 grid appears showing the same man from 9 different angles (overhead, profile, low angle, etc.). Then transitions to a Nike windbreaker jacket (black, red, white) floating in a surreal dark environment filled with glowing blue and purple crystals.
Action: The jacket rotates slowly.
Camera: Close-up on the jacket texture and Nike logo.
Lighting: Dramatic, neon-blue and purple rim lighting.
Speech: "...with consistency from a single reference image."

[00:08–00:13]
Subject: Three characters: a man (DiCaprio-lookalike), a blonde woman (Margot Robbie-lookalike in a black dress), and a muscular man with a goatee (Jon Bernthal-lookalike, shirtless with a gold chain).
Action: They stand together in a modern room with wooden doors and bookshelves. They look toward the camera.
Camera: Medium wide shot, slight handheld jitter for realism.
Lighting: Naturalistic indoor light from the side.
Speech: "So in today's video, I'm going to show you the best method..."

[00:14–00:20]
Visual: Screen recording of the Higgsfield "Shots" app interface. A cursor selects an image of a woman in a black dress and clicks a yellow "Generate" button.
Action: The UI transitions to show a grid of 9 generated black-and-white images of the woman.
Camera: Screen capture.
Speech: "Let's dive in. To get started, you can upload your image into Shots..."

[00:21–00:28]
Subject: A beautiful woman with dark hair in a flowing black dress.
Action: A montage of artistic shots: her looking at the camera, her back to the camera with hair blowing, her dancing with fabric flowing around her.
Camera: Various angles (CU, MCU, Profile), slow motion.
Lighting: High-contrast black and white, dramatic shadows, bright white background.
Text Overlay: "Comment AI" in bold white letters.
Speech: "So if you want to try this out for yourself, type AI in the comments and I'll send you a link."

NEGATIVE PROMPT:
Visual: Distorted faces, extra fingers, flickering background, blurry textures, inconsistent clothing colors, morphing objects, robotic movement, low resolution, watermark.
Speech: Robotic tone, muffled audio, background noise, lip-sync delay, stuttering, unnatural pauses.

SPEECH PACK:
[00:00-00:07]
Transcript: "It has never been easier to create multiple camera angles with consistency from a single reference image."
TAKE_A: (Enthusiastic, fast-paced) "It's NEVER been easier to create multiple camera angles... with total consistency... from just ONE image."
TAKE_B: (Educational, steady) "It has never been easier to create multiple camera angles with consistency... starting from a single reference image."

[00:21-00:28]
Transcript: "So if you want to try this out for yourself, type AI in the comments and I'll send you a link."
TAKE_A: (Direct, CTA-focused) "Want to try this? Type AI in the comments and I'll DM you the link right now."
TAKE_B: (Friendly, helpful) "If you want to try this out for yourself, just comment AI below and I'll send that link over."

GOAL
Maximize similarity to the reference tutorial-style creator video by preserving the same split layout: a host speaking to camera in the lower portion while a white-background AI design-agent workspace occupies the upper portion and demonstrates how to create animated imagery and poster-style visuals. Prioritize the monochrome floral poster examples, the clean UI with left-side tool icons and right-side chat or prompt panel, the host's black cap and dark sweatshirt, the desk microphone in the foreground, and the later transition into product-style mockups and a CTA asking viewers to comment “AI.” The clip should feel like a practical workflow tutorial for creators, not a pure product announcement.

MISE EN PLACE
- Format: 9:16 vertical tutorial explainer, approximately 29.74 seconds.
- Presenter lock:
  - Young adult white male creator with medium-length dark hair, short beard, wearing a black baseball cap and dark navy or black sweatshirt.
  - He speaks directly to camera from a minimal creator setup with a large black desk microphone visible at lower right or center foreground.
- Interface / demo lock:
  - Upper portion shows a mostly white design workspace with a left vertical toolbar, floating canvas area, and a right-side prompt/chat panel.
  - Early examples focus on high-contrast black-and-white floral poster design with large typography such as “DESIGN” and “AI.”
  - Later examples show prompt text, generated poster refinements, and animated or product-style compositions such as orange headphones or a phone emerging from clouds.
  - Closing CTA visually includes “Comment ‘AI’”.
- Scene segmentation:
  - Shot 1: 00:00-00:07.00, hook with monochrome floral poster visuals and the host introducing animated imagery with AI design agents.
  - Shot 2: 00:07.00-00:15.00, clearer UI walkthrough showing prompt panel and generated flower poster iterations.
  - Shot 3: 00:15.00-00:23.00, expanded design workflow with poster composition and product-mockup examples.
  - Shot 4: 00:23.00-00:29.74, wrap-up and CTA with final animated visual and “Comment ‘AI’” prompt.
- Key visual evidence:
  - Bold black typography on white poster layouts.
  - Metallic or reflective flower forms and grayscale floral framing.
  - Right-side text prompt area with generated-result thumbnails.
  - Left-side vertical UI icons suggesting a design canvas workflow.
  - Orange product visuals later in the clip, especially headphones floating in clouds and phone imagery.
- Speech evidence inferred from caption and visuals:
  - Main topic: how to create animated imagery with AI design agents.
  - Delivery: instructional, fast, creator-friendly, focused on practical workflow.
- LOCK THESE invariants:
  - host-on-bottom + UI-on-top format, floral poster tutorial, white interface, black cap and dark sweatshirt host, microphone visible, CTA comment mechanic.
- Variables that may drift slightly:
  - exact host gestures, exact arrangement of the generated poster variations, specific cursor or panel microstates.

SHOTLIST
Shot 1
- shot_id: 1
- timecode_start: 00:00.00
- timecode_end: 00:07.00
- duration: 7.0s
- framing: split-screen with host medium close at bottom and large poster examples above.
- lens: 50mm equivalent creator lens on host.
- camera movement: host static, upper visuals cut or animate through poster variants.
- subject: host points upward while black-and-white floral poster layouts with “DESIGN” and “AI” cycle above him.
- environment: minimal creator room or neutral background, microphone in foreground.
- lighting: soft frontal key on host, bright flat white UI background above.
- speech/audio: direct instructional hook about using AI design agents.
- must match: editorial black-and-white flower aesthetic.

Shot 2
- shot_id: 2
- timecode_start: 00:07.00
- timecode_end: 00:15.00
- duration: 8.0s
- framing: same split layout, more interface-visible.
- lens: same host framing.
- subject: upper panel shows a prompt/chat panel and canvas with glowing flower or poster iterations while the host explains the workflow steps.
- environment: white workspace with left toolbar icons and right-side conversation panel.
- lighting: consistent soft host light, bright UI above.
- motion cues: UI transitions, generated image swaps, subtle host hand motions.
- speech/audio: concise explanation of generating and iterating poster concepts.
- must match: actual design-agent workflow feel, not just static images.

Shot 3
- shot_id: 3
- timecode_start: 00:15.00
- timecode_end: 00:23.00
- duration: 8.0s
- framing: upper panel rotates into more applied examples.
- lens: same host lens.
- subject: product-style poster compositions appear, including orange headphones and a smartphone-like device in cloud-themed layouts, while the host explains expanding the same workflow into animated imagery or campaign-ready assets.
- environment: same interface structure persists with generated thumbnails and poster artboards.
- lighting: bright clean digital design surface above, natural creator lighting below.
- speech/audio: host discusses moving from static visuals into more polished animated outputs.
- must match: product-marketing style examples and clean white workspace.

Shot 4
- shot_id: 4
- timecode_start: 00:23.00
- timecode_end: 00:29.74
- duration: 6.74s
- framing: final split-screen CTA.
- lens: same host framing.
- subject: upper panel lands on an orange headphone-in-cloud visual with text prompt “Comment ‘AI’” while the host closes with a direct call to action.
- environment: same clean white interface or finished hero visual.
- lighting: consistent, simple, social-native.
- speech/audio: closing CTA and final takeaway.
- must match: comment-driven CTA ending.

STYLE BIBLE
- visual_style: creator workflow tutorial, clean design-tech explainer, editorial AI poster demo.
- camera_signature: mostly static host frame with UI-driven motion above.
- lighting_signature: soft creator key light below, bright white interface above.
- grade_signature: minimal white-gray-black palette early, then selective warm orange product accents later.
- texture_signature: crisp UI, sharp typography, reflective grayscale flowers, polished mockup visuals.
- pacing_signature: hook with pretty output, reveal the workflow, broaden use cases, close with CTA.
- speech_style: practical, creator-to-creator teaching tone.
- mic_mix_profile: clean close-mic voice, low ambient room noise, light tutorial pacing.

MASTER PROMPT
GLOBAL LOCK: Keep a vertical split-screen tutorial video. The host stays visible in the lower section for most of the runtime, wearing a black cap and dark sweatshirt, speaking directly to camera with a large black microphone visible beside him. The upper section shows a bright white AI design-agent interface and generated poster outputs. The overall feel should be modern creative-software education for social media, with sharp typography, polished poster visuals, and a practical workflow tone. No subtitles are necessary in the prompt body, but the showcased design outputs may contain text that is visibly part of the examples.

[00:00-00:07.00] Start with large monochrome poster examples in the upper section: grayscale flowers, floral wreaths, metallic petals, and bold text like “DESIGN” and “AI.” Below, the host points and explains that he is about to show how to create animated imagery with AI design agents. Keep his expression engaged and instructive.

[00:07.00-00:15.00] Make the upper section show more of the interface itself: a left toolbar, a canvas with poster artwork, and a right-side prompt or chat panel generating and refining flower-based poster designs. The host below explains the workflow, likely how he prompts and iterates the output.

[00:15.00-00:23.00] Expand the example set in the upper section from floral editorial posters into product-style designs, including orange headphones and a phone-like object emerging from clouds. The host explains how the same design-agent workflow can be used to make more applied animated imagery and campaign-ready assets.

[00:23.00-00:29.74] Finish with a polished hero-style visual in the upper section, such as orange headphones floating in soft white clouds, plus a clear CTA reading “Comment ‘AI’.” The host below closes with a direct final recommendation and invitation to engage.

NEGATIVE PROMPT
Avoid dark moody coding interfaces, messy cluttered rooms, enterprise webinar style, shaky handheld footage, neon gamer lighting, generic stock AI art unrelated to the workflow, overcomplicated UI clutter, overly corporate voice, or cinematic narrative scenes that break the tutorial format.

SHOT PROMPT DELTAS
- Shot 1 delta: emphasize bold monochrome floral poster designs with big typography.
- Shot 2 delta: emphasize the actual design-agent UI with prompt panel and iteration flow.
- Shot 3 delta: emphasize product-style outputs such as orange headphones and phone/cloud visuals.
- Shot 4 delta: emphasize the “Comment ‘AI’” CTA and clean final hero image.

SPEECH PACK
- Timecoded speech intent:
  - [00:00-00:07.00] introduce the goal of making animated imagery with AI design agents.
  - [00:07.00-00:15.00] explain the core workflow and prompt-based iteration.
  - [00:15.00-00:23.00] explain how to turn the workflow into more commercial product-style outputs.
  - [00:23.00-00:29.74] deliver the CTA and recap.
- Delivery direction: energetic but instructional, medium-fast pace, clear creator language, lightly persuasive close.

GLOBAL LOCK:
- Subject: Caucasian woman, early 30s, blonde hair (tied in a ponytail in outdoor/hammock scenes, loose in studio).
- Wardrobe: Tan quilted puffer jacket (outdoor), black blazer over a white t-shirt (studio), light blue button-down shirt (hammock).
- Environment: Modern urban waterfront (outdoor), professional studio with bookshelves and warm/blue lighting (studio), tropical beach with palm trees (hammock).
- Camera: High-quality mobile cinematography, 4K, 60fps feel, mix of handheld and static tripod shots.
- Speech: Enthusiastic, clear, professional female voice. Mic-to-mouth distance is close in studio.

[00:00–00:04]
Subject: Blonde woman in tan puffer jacket, ponytail.
Environment: Outdoor waterfront with modern glass buildings.
Action: Looking down at her phone, then looks up at the camera smiling.
Camera: Handheld MCU, slight natural shake.
Lighting: Bright natural daylight.
Speech: "Hey what you doing?" (Off-camera) / "I'm making an app." (On-camera, smiling).

[00:05–00:08]
Subject: Same woman, hair loose, black blazer, white tee.
Environment: Studio, bookshelves behind, warm orange practical lights and blue rim light.
Action: Holding a professional black microphone, gesturing with the other hand.
Camera: Static MCU, centered.
Lighting: Cinematic 3-point lighting.
Speech: "Replit lets you build entire apps even if you don't know how to code."

[00:09–00:13]
Subject: Split screen. Top half: Phone UI showing Replit AI prompt "Create an app to track my daily pushups". Bottom half: Subject in studio talking.
Action: Subject gestures while the UI shows text being typed into a prompt box.
Camera: Static MCU (bottom), Screen recording (top).
Speech: "I just made an app that sends me the top three AI news every morning..."

[00:14–00:16]
Subject: Split screen. Top half: Phone UI showing an email inbox with "Today's AI Stories". Bottom half: Subject in studio.
Action: Subject points upwards toward the UI.
Speech: "...with ready to film scripts just by describing what I wanted in a few sentences."

[00:17–00:19]
Subject: Subject in studio, hair loose.
Action: Expressive hand gestures, talking directly to camera.
Camera: MCU, slightly wider than before.
Speech: "So now I know exactly what to say in my next video."

[00:20–00:22]
Subject: Quick cut to a male developer in a dark studio with multiple monitors (B-roll), then back to female subject in studio.
Action: Developer is typing; subject is talking and pointing.
Camera: MS (B-roll), MCU (Subject).
Speech: "Replit writes the full code for you and if there are any bugs..."

[00:23–00:24]
Subject: Split screen. Top half: UI showing a chat interface "I'll help you create a time-based automation". Bottom half: Subject in studio.
Action: Subject shrugs and smiles.
Speech: "...it literally fixes its own code."

[00:25–00:29]
Subject: Subject in light blue shirt, ponytail.
Environment: Tropical setting, sitting in a white rope hammock between palm trees.
Action: Holding up her phone showing the Replit logo, smiling at the camera.
Camera: Medium Wide Shot, static.
Lighting: Bright tropical sun, saturated greens and blues.
Speech: "Use the Replit mobile app and show me where you're creating from."

NEGATIVE PROMPT:
Visual: Robotic movements, blurry face, inconsistent hair color, flickering lights, distorted phone screen, extra fingers, messy background, low resolution, watermark.
Speech: Robotic voice, monotone, background noise, muffled audio, lip-sync mismatch, stuttering, unnatural pauses.

SPEECH PACK:
[00:00-00:04]
TAKE_A: "I'm making an app." (Playful, casual)
TAKE_B: "Just building an app right here." (Confident)
TAKE_C: "Oh, I'm just making an app on my phone." (Surprised/Happy)

[00:05-00:08]
TAKE_A: "Replit lets you build entire apps even if you don't know how to code." (Authoritative)
TAKE_B: "With Replit, you can build full apps without knowing a single line of code." (Educational)

[00:25-00:29]
TAKE_A: "Use the Replit mobile app and show me where you're creating from." (Inviting, CTA)
TAKE_B: "Download the Replit app and show me your workspace!" (Energetic)