AI Product Photo Generator

GLOBAL LOCK: 
The video features two distinct subjects. Subject 1 is a Caucasian female in her mid-30s with long, straight light-brown hair, wearing a black sleeveless turtleneck top, sitting at a light wood table in a minimalist room with abstract art. Subject 2 is a Black male model in his mid-20s with short, neat braids, an athletic build, wearing a structured brown zip-up jacket and amber-tinted sunglasses with "MEC" branding on the temples. The environment shifts between a minimalist home office and a high-end, sun-drenched luxury studio/penthouse. The lighting is consistently warm, cinematic, and editorial, with soft-focus backgrounds. The color grade is a warm, high-contrast filmic look with rich browns and creams. The camera language uses a mix of static medium shots and dynamic, handheld-style close-ups with shallow depth of field. Speech is a warm, professional female voice with clear articulation.

[00:00–00:04]
Subject 1 (female creator) is centered in a medium shot, speaking directly to the camera with expressive hand gestures. She is in a bright, minimalist room. The lighting is soft natural light from the side. Her expression is welcoming and authoritative.
Speech: "What if I told you that you could turn a simple image of your product..."
Lip-sync: High strictness.

[00:04–00:07]
A fast-paced 4-grid montage. Top-left: Subject 2 (male model) sitting on a tan leather sofa. Top-right: Close-up of the amber sunglasses. Bottom-left: Subject 2 standing in a low-angle shot. Bottom-right: Close-up of Subject 2's face. The lighting is high-end editorial with strong highlights.
Speech: "...into a full set of campaign images, into studio shots..."

[00:07–00:09]
Subject 2 is in a medium close-up, reaching both hands towards the camera lens, creating a sense of depth. The background is a clean, off-white studio wall. He wears the brown jacket and sunglasses.
Speech: "...and even ads with AI?"

[00:09–00:10]
A sharp close-up of Subject 2's face, looking slightly off-camera. The focus is on the sunglasses. The lighting is dramatic, coming from a window.
Speech: "Now let's say you want to..."

[00:10–00:11]
A match-cut transition to a different model: a Caucasian male with wavy blonde hair, wearing the same sunglasses and brown jacket. Same framing and lighting as the previous shot.
Speech: "...change the model, do it."

[00:11–00:12]
Subject 2 is shown in a full-body low-angle shot, wearing the brown jacket and matching trousers, standing against a bright white background.
Speech: "You don't like the clothes..."

[00:12–00:13]
A quick cut where Subject 2's outfit swaps from the brown jacket to a clean white oversized t-shirt. The pose and background remain identical.
Speech: "...swap them."

[00:13–00:14]
Subject 2 is sitting on a tan leather sofa in a medium shot, looking directly at the camera with a neutral, cool expression.
Speech: "You need one more angle..."

[00:14–00:15]
An extreme close-up of Subject 2's hand adjusting the sunglasses on his face. The "MEC" logo on the temple is clearly visible.
Speech: "...easy."

[00:15–00:18]
Close-up of Subject 2 speaking. His lips move in perfect sync with the voiceover. He looks confident.
Speech: "You want to change the voice? Change it."
Lip-sync: High strictness.

[00:18–00:20]
Subject 2 is sitting in a leather armchair next to a large floor-to-ceiling window overlooking a park. The lighting is golden hour, creating long shadows.
Speech: "Creating content for your brand..."

[00:20–00:23]
Final close-up of Subject 2 looking into the camera. A white button with the text "AI" and a cursor clicking it appears over his chest.
Speech: "...has never been easier. Comment AI to learn how."

NEGATIVE PROMPT: 
Visual: blurry faces, inconsistent sunglasses shape, flickering lighting, distorted hands or fingers, floating objects, low resolution, grainy texture, unnatural skin smoothing, robotic movement, text artifacts on clothing.
Speech: robotic monotone, mismatched lip-sync, background noise, muffled audio, unnatural pauses, harsh 's' sounds, clipping audio, inconsistent volume.

SPEECH PACK:
[00:00-00:08]
Transcript: "What if I told you that you could turn a simple image of your product into a full set of campaign images, into studio shots, and even ads with AI?"
TAKE_A: (Curious, rising intonation on "What if I told you", energetic pace)
TAKE_B: (Professional, steady cadence, emphasis on "simple image" and "full set")
TAKE_C: (Slow, dramatic, pausing after "ads" for impact)

[00:08-00:18]
Transcript: "Now let's say you want to change the model, do it. You don't like the clothes, swap them. You need one more angle, easy. You want to change the voice? Change it."
TAKE_A: (Punchy, fast-paced, authoritative "do it" and "swap them")
TAKE_B: (Conversational, light-hearted, shrug-like cadence on "easy")
TAKE_C: (Instructional, clear pauses between each command)

[00:18-00:23]
Transcript: "Creating content for your brand has never been easier. Comment AI to learn how."
TAKE_A: (Warm, smiling tone, direct and clear CTA)
TAKE_B: (Confident, slightly slower pace on "never been easier")
TAKE_C: (Encouraging, upbeat, emphasis on "Comment AI")

A) MISE EN PLACE
2) Segment the video into scenes/shots:
- [00:00-00:03] Shot 1: ECU face, talking.
- [00:03-00:05] Shot 2: CU face, holding product.
- [00:06-00:09] Shot 3: MS, head turn, dramatic shadow.
- [00:10-00:12] Shot 4: CU, applying product.
- [00:13-00:15] Shot 5: WS, sitting on floor.
- [00:16-00:18] Shot 6: CU, touching neck.
- [00:19-00:21] Shot 7: MS, sitting on stool, talking.
- [00:22-00:24] Shot 8: MS, holding hair up.
- [00:25-00:27] Shot 9: CU, wind in hair.

3) Extract visual evidence:
- Keyframes: 00:01 (talking face), 00:04 (holding product), 00:07 (shadow face), 00:11 (applying product), 00:14 (full body), 00:17 (touching neck), 00:20 (sitting talking), 00:23 (holding hair), 00:26 (wind in hair).

4) Extract speech evidence:
- Speaker: 1 female voice (Speaker A).
- Transcript:
  [00:00-00:03] "What if I told you I'm not even real."
  [00:03-00:05] "But the product I'm holding is Hailey Bieber's Rhode lip balm."
  [00:06-00:09] "Everything you're seeing was created with AI, no camera, no studio."
  [00:10-00:12] "Just one image and a few prompts."
  [00:13-00:15] "Every reflection, every highlight, every detail was generated in seconds."
  [00:16-00:18] "Real product, unreal possibilities."
  [00:19-00:21] "You don't need a full setup anymore."
  [00:22-00:24] "Just imagination."
  [00:25-00:27] "Comment guide to learn how."
- Lip visibility: Full visibility in shots 1 and 7. Partial/implied in others.
- Sync strictness: High for shots 1 and 7.

5) Invariants list (LOCK THESE):
- Visuals: Asian woman, mid-20s, flawless glowing skin, dark brown hair, fitted white ribbed sleeveless turtleneck tank top, small silver hoop earrings. Cinematic studio lighting, 85mm lens feel, photorealistic texture.
- Speech: Female voice, warm, confident, commercial beauty tone, close-mic studio sound, dry room.

6) Variables list (TWEAK THESE):
- Visuals: Lighting direction (soft beauty vs. hard directional), hair state (tied back vs. loose), background color (black, grey, white), pose, camera framing (ECU to WS).
- Speech: Pacing, emphasis on key words ("real", "AI", "seconds").

B) SHOTLIST
[00:00-00:03]
- framing: ECU, eye level.
- lens: 85mm, shallow DoF.
- camera movement: Static.
- subject: Looking directly at lens, speaking.
- environment: Dark studio background.
- lighting: Soft beauty lighting, high contrast.
- speech: Speaker A, on-camera. "What if I told you I'm not even real." High lip-sync strictness.

[00:03-00:05]
- framing: CU, eye level.
- lens: 85mm, shallow DoF.
- camera movement: Slight drift.
- subject: Holding a pink lip balm tube near her cheek, looking at camera.
- environment: Neutral studio background.
- lighting: Soft diffused lighting.
- speech: Speaker A, VO. "But the product I'm holding is Hailey Bieber's Rhode lip balm."

[00:06-00:09]
- framing: MS, eye level.
- lens: 50mm.
- camera movement: Slow pan following head turn.
- subject: Turns head from profile to face camera.
- environment: Dark studio background.
- lighting: Dramatic hard directional light, sharp diagonal shadow across face.
- speech: Speaker A, VO. "Everything you're seeing was created with AI, no camera, no studio."

[00:10-00:12]
- framing: CU, tight on mouth.
- lens: 100mm macro feel.
- camera movement: Static.
- subject: Applying pink lip balm to lips, eyes looking slightly down.
- environment: Neutral background.
- lighting: Bright, even beauty lighting.
- speech: Speaker A, VO. "Just one image and a few prompts."

[00:13-00:15]
- framing: WS, full body.
- lens: 35mm.
- camera movement: Static.
- subject: Sitting on floor, one leg bent, wearing black trousers with the white tank top.
- environment: Grey studio floor and wall.
- lighting: Soft overhead lighting.
- speech: Speaker A, VO. "Every reflection, every highlight, every detail was generated in seconds."

[00:16-00:18]
- framing: CU.
- lens: 85mm.
- camera movement: Slight push-in.
- subject: Touching neck and jawline with both hands.
- environment: Dark background.
- lighting: Warm rim light, deep shadows.
- speech: Speaker A, VO. "Real product, unreal possibilities."

[00:19-00:21]
- framing: MS.
- lens: 50mm.
- camera movement: Static.
- subject: Sitting on a metal stool, leaning forward, speaking to camera.
- environment: Neutral studio background.
- lighting: Neutral studio lighting, slight vignette.
- speech: Speaker A, on-camera. "You don't need a full setup anymore." High lip-sync strictness.

[00:22-00:24]
- framing: MS, slight low angle.
- lens: 50mm.
- camera movement: Static.
- subject: Arms raised, holding hair up in a high ponytail.
- environment: White studio background.
- lighting: Bright, high-key lighting.
- speech: Speaker A, VO. "Just imagination."

[00:25-00:27]
- framing: CU.
- lens: 85mm.
- camera movement: Static.
- subject: Looking intensely at camera, hair blowing.
- environment: Dark background.
- lighting: Soft dramatic lighting.
- motion cues: Wind blowing hair.
- speech: Speaker A, VO. "Comment guide to learn how."

C) STYLE BIBLE
- visual_style: Photorealistic cinematic commercial beauty portrait.
- camera_signature: 85mm portrait lens dominance, shallow depth of field, mostly static or slow, deliberate movements.
- lighting_signature: Highly variable but always professional studio quality, ranging from soft high-key beauty to dramatic low-key hard shadows.
- grade_signature: High contrast, natural skin tones, deep blacks, clean whites.
- texture_signature: Flawless skin detail, sharp focus on eyes and product.
- pacing_signature: Fast-paced cuts every 2-3 seconds.
- speech_style: Commercial beauty VO, confident, direct-to-camera hybrid.
- speaker_profile: Female, warm, articulate, modern vocal fry.
- mic_mix_profile: Close-mic, dry studio, high clarity, compressed for social media.

D) PROMPT SYNTHESIS

1. MASTER PROMPT
GLOBAL LOCK: Photorealistic cinematic commercial style. Subject: Asian woman, mid-20s, flawless glowing skin, dark brown hair, wearing a fitted white ribbed sleeveless turtleneck tank top, small silver hoop earrings. Environment: Minimalist studio setting with solid neutral backgrounds (white/grey/black). Lighting: High-end beauty lighting, varying from soft diffused to dramatic hard shadows. Camera: 85mm lens, shallow depth of field. Speech: Single female speaker, warm commercial tone, close-mic studio sound.

[00:00-00:03] ECU of the woman's face against a dark background. Soft beauty lighting. She is looking directly at the lens, speaking. Lips are moving in sync with speech.
[00:03-00:05] CU. The woman holds a pink lip balm tube next to her cheek. Soft diffused lighting. She looks at the camera. Slight camera drift.
[00:06-00:09] MS. The woman is turned slightly away in profile, then turns her head towards the camera. Dramatic lighting with a harsh diagonal shadow cutting across her face. Slow pan following the head turn.
[00:10-00:12] CU tight on the mouth. The woman is applying the pink lip balm to her lips. Eyes looking slightly down. Bright, even beauty lighting highlighting skin texture.
[00:13-00:15] WS. The woman is sitting on the floor, wearing black trousers with the white tank top. One leg bent. Grey studio background. Soft overhead lighting. Static camera.
[00:16-00:18] CU. The woman touches her neck and jawline with both hands. Warm, glowing rim light, deep shadows on the opposite side. Slight camera push-in.
[00:19-00:21] MS. The woman is sitting on a metal stool, leaning forward slightly, speaking directly to the camera. Lips moving in sync. Neutral studio lighting, slight vignette. Static camera.
[00:22-00:24] MS, slight low angle. The woman has her arms raised, holding her hair up in a high ponytail. Bright, high-key lighting, white background. Static camera.
[00:25-00:27] CU. The woman's hair is blowing in the wind. She looks intensely at the camera. Soft dramatic lighting, dark background. Static camera.

2. NEGATIVE PROMPT
Visuals: cartoon, illustration, anime, 3d render, deformed anatomy, extra fingers, mutated hands, unnatural skin texture, plastic skin, temporal jitter, flickering lighting, morphing objects, text, watermarks, logos, low resolution, blurry, out of focus.
Audio: robotic voice, unnatural cadence, harsh sibilance, plosives, clipping, background noise, room echo, lip-sync mismatch, slurred words.

4. SPEECH PACK
Speaker: Female, 20s, warm, confident, commercial beauty tone.
[00:00-00:03] "What if I told you... I'm not even real." (Pause for dramatic effect, direct eye contact).
[00:03-00:05] "But the product I'm holding... is Hailey Bieber's Rhode lip balm." (Slight emphasis on 'Rhode').
[00:06-00:09] "Everything you're seeing was created with AI... no camera... no studio." (Paced, emphasizing the negatives).
[00:10-00:12] "Just one image... and a few prompts." (Smooth, instructional tone).
[00:13-00:15] "Every reflection... every highlight... every detail... was generated in seconds." (Staccato emphasis on 'every').
[00:16-00:18] "Real product... unreal possibilities." (Contrast emphasis).
[00:19-00:21] "You don't need a full setup anymore." (Direct, conversational).
[00:22-00:24] "Just imagination." (Soft, aspirational).
[00:25-00:27] "Comment guide... to learn how." (Clear CTA, energetic).

GLOBAL LOCK:
Subject: A female host, mid-20s, South Asian ethnicity, warm skin tone, long wavy brown hair, wearing a cozy lavender/purple knit sweater. She sits in a home office with a professional black condenser microphone on a boom arm. Background features a dark wooden bookshelf filled with books and small plants, softly blurred.
AI Subject Consistency: A high-fashion female model, European features, sharp jawline, sleek dark hair, wearing a white luxury power suit.
Environment: High-end studio settings for AI ads; warm home office for host.
Lighting: Soft, three-point lighting for the host; dramatic, high-contrast, cinematic lighting for AI outputs.
Color Grade: Warm, saturated tones for the host; cool blues and deep blacks for the "Dior-style" AI ads.
Speech: Clear, energetic female voice, professional cadence, direct-to-camera address.

[00:00–00:05]
Visual: Rapid montage of luxury brand ads. A model with green eyes holds a perfume bottle; a red "HERA" perfume ad; a man wearing a Calvin Klein watch; a woman with flowers on her face holding perfume.
Camera: Extreme close-ups and medium shots, static with slight internal motion.
Lighting: High-fashion studio lighting, dramatic shadows.
Speech: "You don't need to hire models or designers to create brand ads anymore." (Fast-paced, hook delivery).

[00:05–00:12]
Visual: Cut to host in her office. She gestures towards the camera. A screen overlay shows the URL "lovart.ai/home".
Camera: Medium shot, static.
Lighting: Warm, soft key light from the side.
Speech: "AI can do the full photoshoot and video for you. Just go to lovart.ai and start a new project."

[00:12–00:20]
Visual: Screen recording of the Lovart.ai interface. A cursor clicks "Upload Image," then selects "Nano Banana Pro" from a dropdown menu. A prompt is typed: "Luxury studio photoshoot of a model holding my product, cinematic lighting, premium brand look."
Camera: Screen capture, focused on the UI elements.
Speech: "Upload your product image, choose Nano Banana Pro, and describe the ad you want."

[00:20–00:26]
Visual: The AI generates a photo of a model in a white suit holding a Dior bag. The host is shown in a small window, reacting. The screen shows "Edit Text" and "Model Pose" options.
Camera: Split screen: UI on top, Host on bottom.
Speech: "Lovart's design agent will generate a professional ad visual in seconds. You can adjust anything: text, background, model pose, lighting."

[00:26–00:35]
Visual: A "Before" and "After" comparison. The "Before" is warm-toned; the "After" is cool blue with dramatic shadows. The cursor then selects "Kling 3.0" for video generation.
Camera: Side-by-side comparison, then UI focus.
Speech: "And the best part? These edits don't damage or overwrite your original base image. Once your poster looks perfect, you can turn it into a cinematic video using Kling 3.0 inside Lovart."

[00:35–00:40]
Visual: The final video output shows the model in the white suit subtly moving, adjusting her hand on the bag. The host returns to full screen with a "Comment ART" graphic overlay.
Camera: Full-screen AI video, then Medium Shot of host.
Speech: "Just add a motion prompt, generate, and your animated brand ad is ready. Comment ART and I'll send you the tool link."

NEGATIVE PROMPT:
Visual: Blurry faces, extra fingers, distorted product logos, flickering lights in video, unnatural skin texture, messy background in host segments, low resolution, watermarks on AI outputs.
Speech: Robotic tone, background noise, muffled audio, lip-sync mismatch, long pauses between sentences, harsh "S" sounds.

SPEECH PACK:
[00:00-00:05]
Transcript: "You don't need to hire models or designers to create brand ads anymore."
TAKE_A: (Energetic, fast) "You don't need to hire models or designers to create brand ads anymore!"
TAKE_B: (Authoritative, measured) "You don't need to hire models... or designers... to create brand ads anymore."

[00:05-00:12]
Transcript: "AI can do the full photoshoot and video for you. Just go to lovart.ai and start a new project."
TAKE_A: (Helpful, inviting) "AI can do the full photoshoot and video for you. Just go to lovart dot a-i and start a new project."

[00:35-00:40]
Transcript: "Comment ART and I'll send you the tool link."
TAKE_A: (Direct, friendly) "Comment ART and I'll send you the tool link!"
TAKE_B: (Whispered/Secretive) "Comment ART... and I'll send you the tool link."

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.

MASTER PROMPT
GLOBAL LOCK: Vertical 9:16 creator workflow reel showing how a low-quality phone product photo becomes a premium editorial brand campaign. The piece combines direct-to-camera creator explanation, smartphone screen inserts, dark AI prompt interfaces, polished fragrance and beauty packshots, high-fashion poster layouts, icy blue lighting setups, red background title cards, and glossy close-up beauty shots. Maintain a commercial luxury aesthetic with clean graphic design, sharp product isolation, premium reflections, and fast but readable tutorial pacing. One male creator speaks with confident agency-style cadence, close mic, dry audio, and repeated CTA emphasis on the keyword SNAP.

[00:00-00:05] Open on the creator holding up a poor-quality phone photo of a product while bold on-screen text frames the client problem. Quickly cut to the original image on a smartphone screen and the raw product reference. The creator states the hook: turning one bad iPhone product shot into a full brand campaign.

[00:05-00:10] Show the source product clearly, including dark fragrance bottle imagery and rough input materials. Keep the pace quick and problem-solution oriented. The host explains that the workflow starts with product extraction and building a 2x2 reference grid.

[00:10-00:17] Move into dark AI workflow screens with prompt boxes, image tiles, and reference inputs. The product appears in multiple isolated views while the creator describes feeding references into an LLM to generate several custom prompts. Keep interfaces crisp, black or charcoal, with white type and subtle UI highlights.

[00:17-00:25] Transition into generated campaign outputs. Show premium editorial product renders: dramatic blue-light bottle shots, luxury tabletop scenes, stylized poster frames, and fashion-adjacent compositions. The visual language should alternate between clean packshot precision and moody brand storytelling.

[00:25-00:32] Display a grid or carousel of multiple campaign variants, including print-poster style layouts, branded title cards, and comparative presentation boards. The creator frames this as a scalable shoot process that can create multiple deliverables from one starting photo.

[00:32-00:37] Show high-end beauty close-ups with glossy lips and refined skin detail, suggesting companion campaign imagery beyond the product packshot itself. The grade stays polished, magazine-like, and editorial.

[00:37-00:41] End on a clean CTA beat with a minimal branded frame or title card. The creator closes by telling viewers to comment SNAP to get the full creative shoot process.

NEGATIVE PROMPT
Avoid cheap e-commerce lighting, flat product cutouts, muddy reflections, fake luxury materials, unreadable prompt UI, weak poster typography, inconsistent bottle shape, warped labels, plastic skin on beauty close-ups, noisy shadows, and robotic narration. Keep every asset premium and campaign-ready.

SPEECH PACK
[00:00-00:05]
Closest audible: Comment SNAP to get the full creative shoot process.
Safe paraphrase: Open with a keyword CTA tied to the full workflow.

[00:05-00:17]
Closest audible: Your client sends a trash iPhone photo and expects a full brand campaign, and here is the workflow.
Safe paraphrase: He frames the challenge and explains the early extraction and prompt-building steps.

[00:17-00:32]
Closest audible: Product extraction, 2x2 grid, LLM prompts, then Nano Banana or Flux, then upscale and Lightroom finish.
Safe paraphrase: He walks through the generation and finishing stack that turns one input image into multiple outputs.

[00:32-00:41]
Closest audible: Table top, on figure, lifestyle, print poster, one photo, one workflow; comment SNAP.
Safe paraphrase: Close by emphasizing output variety and repeating the CTA.

GLOBAL LOCK:
Subject: A consistent East Asian female model, mid-20s, athletic/slender build, sleek black hair tied in a long ponytail.
Wardrobe: White ribbed cotton tank top, black high-waisted trousers, black pointed-toe heels.
Environment: Minimalist professional photography studio, neutral grey/white background, clean floor with subtle reflections.
Lighting: High-contrast chiaroscuro lighting, sharp motivated light source creating deep shadows across the face and body, editorial fashion mood.
Color Grade: Neutral palette, high contrast, warm skin tones, sharp details, 8k resolution, cinematic film grain.
Camera: 35mm and 50mm prime lenses, shallow depth of field, professional stabilization.
Speech: Female voice, calm, sophisticated, medium pace, crisp articulation, studio-dry microphone signature.

[00:00–00:02]
Subject: MCU, over-the-shoulder view. The model turns her head slowly to look directly into the camera lens.
Action: Subtle, neutral expression, slight parting of lips.
Camera: Static MCU, 50mm lens.
Lighting: Rim light on the ponytail, shadow covering the front of the shoulder.
Speech: "I told you..." (Off-camera feel, transitioning to on-camera).

[00:02–00:05]
Subject: ECU of the model's face. She is holding a pink "rhode" lip balm tube horizontally just below her nose.
Action: She speaks directly to the camera. High skin detail, visible pores, and realistic lip texture.
Camera: ECU, macro feel.
Lighting: A sharp shadow bisects her face vertically, leaving one eye in darkness.
Speech: "...not even real. What I'm holding is..." (Strict lip-sync required).

[00:05–00:08]
Subject: CU of the model holding the pink "rhode" tube.
Action: She brings the tube to her lips. The tube has clear "rhode" branding.
Camera: CU, slight handheld shake for realism.
Lighting: Glossy highlights on the product packaging and her lips.
Speech: "...Hailey Bieber's Rhode lip balm."

[00:08–00:11]
Subject: MCU of the model's profile.
Action: She applies the lip balm to her bottom lip. Her eyes are closed slightly in a posing manner.
Camera: Profile MCU.
Lighting: High-key lighting on the face, dark background.
Speech: "Everything you're seeing... AI."

[00:11–00:15]
Subject: WS of the model sitting on the studio floor.
Action: She is posed with one leg bent, arm resting on her knee, looking at the camera.
Camera: WS, low angle.
Lighting: Hard shadow cast on the floor to the right.
Speech: "No camera, no... just one image and a few..."

[00:15–00:18]
Subject: MCU of the model sitting on a chrome and black leather studio stool.
Action: She rests her chin on her hand, then moves her hands to her neck.
Camera: MCU, 35mm lens.
Lighting: Soft fill light from the front, deep shadows in the background.
Speech: "...every reflection, every highlight, every detail was..."

[00:18–00:22]
Subject: MS of the model sitting on the stool, leaning forward.
Action: She speaks with expressive hand gestures, looking confident.
Camera: MS, eye-level.
Lighting: Dramatic side lighting.
Speech: "...generated in seconds. Real product, unreal possibilities."

[00:22–00:27]
Subject: MCU of the model.
Action: She reaches up with one hand to grab her ponytail and pulls it upward, letting the hair fan out. Wind blows through the loose strands of hair.
Camera: MCU, slight zoom in.
Lighting: Dynamic lighting shifting as she moves.
Speech: "You don't need... anymore. Just imagination. Learn how." (Cut lands on "Learn how").

NEGATIVE PROMPT:
Visual: Cartoonish features, distorted fingers, melting textures, flickering clothes, floating hair, blurry product labels, double limbs, unnatural eye movement, low resolution, watermark, text artifacts.
Speech: Robotic tone, monotone delivery, muffled audio, background hiss, lip-sync mismatch, popping 'p' sounds, unnatural pauses, synthesized artifacts.

SPEECH PACK:
[00:00–00:05] "I told you... not even real. What I'm holding is..."
TAKE_A: (Whispered, mysterious)
TAKE_B: (Confident, direct)
TAKE_C: (Casual, conversational)

[00:05–00:15] "Hailey Bieber's Rhode lip balm. Everything you're seeing... AI. No camera, no..."
TAKE_A: (Emphasis on "AI" and "Rhode")
TAKE_B: (Fast-paced, energetic)

[00:15–00:27] "...every reflection, every highlight, every detail was generated in seconds. Real product, unreal possibilities. You don't need... anymore. Just imagination. Learn how."
TAKE_A: (Inspiring, visionary tone)
TAKE_B: (Professional, matter-of-fact)
TAKE_C: (Slow, emphasizing "unreal possibilities")

GLOBAL LOCK: vertical 9:16 paid-social style SaaS promo video for an AI image and video generation platform aimed at marketers and brand teams. The visual structure alternates between a dark premium product UI and a talking-head founder/creator picture-in-picture window. The presenter is a young adult man with medium-length dark hair, short beard, baseball cap, dark jacket with contrast stitching, and a black microphone visible in front of him. He speaks directly to camera from a home-office setup while the main screen above and behind him demonstrates the product. The interface should feel modern, black-background, neon-accent, high-contrast, and polished, with glowing borders around product cards, upload panels, and preview windows. Branding should prominently feature the name “VERV.”

The product story is: marketers can generate ad-ready images and videos from product references. Show a sequence of examples: selecting a product, generating polished model photography, lifestyle placements, beverage shots, packaging concepts, candy/snack ads, and then turning an image into a short video through a guided interface. The emotional tone is practical, high-conviction, performance-marketing oriented, and aspirational. This is not a generic explainer deck. It should feel like a creator selling a real tool with fast visual proof.

[00:00-00:05] Open on a dark app interface with a glowing product-selection panel. A talking-head box with rounded corners sits near the lower portion of frame showing the presenter speaking and gesturing naturally. The UI highlights a simple white 3D mannequin or product placeholder inside a card labeled “Product.” Cursor movement or selection states should suggest the user is choosing a base object to build content from.

[00:05-00:10] Transition to generated campaign imagery. Show fashion-model style results and clean lifestyle scenes built around the product: a white mannequin in a bright editorial room, then a woman standing at a doorway with the same mannequin or product-themed concept. The presenter remains in the lower picture-in-picture, continuing to explain the platform's use for marketing creatives.

[00:10-00:16] Cut to another example set: a colorful lifestyle frame with a subject near a washing machine or rooftop setup, followed by product packaging or bottle mockups. The interface intermittently returns to “Product” cards and clean selection screens so the audience understands this is driven by software, not just a montage of random ads.

[00:16-00:24] Show beauty and beverage examples. A glamorous female model holds a sleek metallic bottle in a polished campaign shot. Another scene shows a bottle alone in an atmospheric setting. Keep these examples bright, premium, and commercially usable. The presenter window continues reacting and talking while the main visual area displays case-study style outputs.

[00:24-00:32] Shift into food and snack ad territory. Show a woman eating or posing with a chocolate or candy bar in bold studio colors. Return briefly to the platform UI where a product image card is highlighted and the software appears to generate matching branded creative variations. Keep the cuts fast and made for ad-world attention spans.

[00:32-00:40] Emphasize the software workflow. A large VERV screen shows a multi-panel dashboard and then a specific feature titled “Turn image into video.” The interface includes an original image preview and a prompt box with descriptive text, for example a person holding a bottle at an athletics track. The presenter remains visible below, explaining the workflow like a founder demoing a new release.

[00:40-00:45] End on branded product UI and a strong software payoff: VERV logo over a gradient or dark dashboard background, plus screens showing generated outputs and controls for creative generation. The feeling should be that this tool bridges AI image generation, ad creative production, and image-to-video in one polished marketing stack.

VISUAL DNA:
- Dark premium SaaS interface with black panels, glowing neon edges, gradient accents, and rounded cards.
- Persistent creator/founder talking-head picture-in-picture near the bottom of frame.
- Product cards labeled “Product,” upload areas, prompts, dashboards, and output galleries.
- Generated ad creative spanning fashion, beauty, beverage, lifestyle, and snack categories.
- Strong “VERV” branding integrated into multiple scenes.

CAMERA AND EDITING LOCK:
- Fast social-ad pacing with clear section changes every few seconds.
- Mix of screen-recording style UI shots and static talking-head reactions.
- No cinematic handheld realism; this is polished app-demo editing.
- Keep the presenter's face small enough to support the product visuals, not dominate them.

NEGATIVE PROMPT: generic corporate slideshow, boring webinar screen share, plain white software UI, no presenter, no branding, random stock footage with no app context, chaotic meme editing, gaming UI, crypto dashboard, coding IDE, horror tone, political content, travel vlog, subtitles burned in, low-quality screen capture, messy desktop clutter, unrelated ecommerce website.

SHOT PROMPTS:
SHOT 1: dark VERV interface with glowing product card and founder talking-head inset.
SHOT 2: generated fashion and lifestyle ad visuals switching above the presenter's commentary window.
SHOT 3: premium bottle and beauty campaign images created from product references.
SHOT 4: snack and consumer-goods creative examples with quick app returns.
SHOT 5: “Turn image into video” workflow screen with prompt field and original image preview.
SHOT 6: final VERV-branded dashboard and outputs montage.

SPEECH PACK:
[00:00-00:45] Conversational founder-style ad read, confident and concise, explaining that VERV helps marketers generate high-quality AI images and videos for brand content, product ads, and creative testing. Natural spoken delivery, no robotic narration.

GLOBAL LOCK: A consistent young Black female model with short buzz-cut hair, natural skin texture with visible freckles, and a slender build. She wears a beige distressed baseball cap with "ROSE" embroidered in large 3D letters on the front. The environment is a minimalist professional photo studio with a seamless light grey paper backdrop. Lighting is soft-box studio lighting with a subtle rim light to separate the subject from the background. The color grade is clean, neutral, and editorial with high contrast and sharp details.

[00:00–00:03]
A dark mode software UI on a vertical screen. A small 3D icon of a burger is centered, then quickly replaced by a leopard print belt. Text "This AI" and "Creating something beautiful... (63%)" appears. The UI is sleek with various model icons on the left sidebar.

[00:04–00:07]
A handheld POV shot of a beige "ROSE" baseball cap lying on a white tiled floor. A smartphone enters the frame, showing the camera app interface as it takes a photo of the hat. Text "reshoot" and "five" appears on screen.

[00:08–00:12]
The smartphone screen shows the "Artlist Toolkit" UI. A prompt box at the bottom contains detailed text about recreating the hat photo. The UI shows the hat being processed. Text "Now I take one" and "my workflow through" overlays the screen.

[00:13–00:16]
A grid view of various AI models like "Nano Banana 2," "Seedream 5.0," and "Kling 3.0" with their respective credit costs. The mouse cursor navigates the dark-themed workspace. Text "All the leading AI models," and "one workspace," appears.

[00:17–00:24]
A rapid montage of the Black female model wearing the beige "ROSE" hat in different outfits: a grey ribbed sweater, a white tank top, and a green knit sweater. Extreme close-up shots of the green knit fabric showing intricate weave patterns and a white "ohneis" care label. Text "Complex garments," "weird shapes," "quality materials."

[00:25–00:31]
The UI shows a video generation prompt: "slow dolly in, she moves her hand away from the hat." A progress bar moves. Text "You can generate images and videos from the same session."

[00:32–00:35]
A cinematic profile shot of the model wearing the beige hat and a dark grey knit sweater. She has a neutral, confident expression. The camera is static. Lighting highlights her facial structure and the texture of the hat. Text "If you're building a brand or creating for clients,".

[00:36–00:39]
A frontal MCU of a different blonde female model wearing oversized black heart-shaped sunglasses, followed by a shot of her in a black and grey striped "London UK" sports jersey. Final screen is black with white text: "Comment 'Artlist' and I'll send you the full workflow."

NEGATIVE PROMPT: blurry textures, inconsistent hat logo, distorted facial features, shaky camera, low resolution, unnatural skin smoothing, flickering lighting, messy background, floating objects, mismatched clothing physics, robotic speech cadence, lip-sync lag.

SPEECH PACK:
[00:00-00:03] "This AI trick legit makes your product photos look studio level."
TAKE_A: (Energetic, fast-paced) "This AI trick... legit makes your product photos... look studio level!"
TAKE_B: (Confident, smooth) "This AI trick legit makes your product photos look studio level."

[00:04-00:08] "I used to reshoot the same product five times and it still looked off. So I stopped."
TAKE_A: (Frustrated tone on 'five times') "I used to reshoot the same product FIVE times... and it still looked off. (Pause) So I stopped."

[00:09-00:16] "Now I take one flat lay on my phone and run my workflow through the Artlist Toolkit. All the leading AI models, one workspace, no switching tabs."
TAKE_A: (Informative, rhythmic) "Now I take one flat lay on my phone... and run my workflow through the Artlist Toolkit. All the leading AI models... one workspace... no switching tabs."

[00:17-00:24] "A few prompts later, it looks like a full blown studio shoot. Complex garments, weird shapes, quality materials. Still works every time."
TAKE_A: (Impressed, emphasizing 'quality') "A few prompts later... it looks like a full blown studio shoot. Complex garments... weird shapes... quality materials. Still works every time."

[00:25-00:31] "And the best part? You can generate images and videos from the same session. No photographer, no studio, no reshoots."
TAKE_A: (Punchy delivery) "And the best part? You can generate images AND videos from the same session. No photographer... no studio... no reshoots."

[00:32-00:39] "If you're building a brand or creating for clients, this will save you hours. Comment 'Artlist' and I'll send you the full workflow."
TAKE_A: (Direct, CTA focus) "If you're building a brand or creating for clients... this will save you hours. Comment 'Artlist'... and I'll send you the full workflow."

GLOBAL LOCK: 
Subject: East Asian female model, mid-20s, natural skin with prominent freckles on cheeks and nose, neutral editorial expression. 
Wardrobe: High-end minimalist cream-colored oversized wool scarf and matching off-white coat/trousers. 
Environment: Arid desert landscape, dry cracked earth, distant low hills, clear deep blue sky. 
Lighting: Harsh, direct overhead sunlight (golden hour), creating deep shadows and high contrast. 
Color Grade: Warm, desaturated earth tones, high-end fashion magazine aesthetic. 
Camera: 35mm lens feel, slight film grain, cinematic movement. 
Audio/Speech: No speech, rhythmic deep bass beat; cuts must happen exactly on the beat.

[00:00–00:01]
Extreme close-up of the model's face. She holds her hand up to shade her eyes from the sun, casting a sharp horizontal shadow across her eyes. Her freckles are highly detailed. Static camera. Harsh sunlight.

[00:01–00:02]
Hard cut to a product shot: A dark brown, minimalist leather tote bag centered on a seamless white studio background. Flat, even lighting. No movement.

[00:02–00:04]
Hard cut to a full shot of the model walking through the desert. She is carrying the brown leather bag at her side. The camera tracks her movement from a low angle. The wind gently ruffles her cream scarf.

[00:04–00:05]
Close-up of the model's hand gripping the dark brown leather strap of the bag. The texture of the leather is visible under the bright sun. Slight handheld camera shake.

[00:05–00:07]
Medium shot of the model standing still, looking directly into the lens with a neutral, confident expression. The desert background is slightly blurred (shallow depth of field).

[00:07–00:10]
A rapid-fire montage of shots: 
1. Model walking away from the camera into the vast desert.
2. Low angle shot of the model looking down at the camera.
3. Wide shot of the model as a small figure against the massive blue sky and desert floor.
Each cut is perfectly synced to the aggressive beat of the music.

NEGATIVE PROMPT: blurry, low resolution, distorted facial features, inconsistent freckles, plastic skin, cartoonish, neon colors, busy background, extra limbs, flickering shadows, shaky camera, text overlays, logos.

SPEECH PACK:
(No speech present in the original video. Pacing is entirely driven by the BGM.)
TAKE_A: Rhythmic cuts every 0.5 seconds during the final montage.
TAKE_B: Rhythmic cuts every 1.0 seconds for a slower, more dramatic feel.
TAKE_C: Variable speed ramps (fast-slow-fast) between the walking shots.

GLOBAL LOCK:
Subject is a Caucasian male, late 20s, light brown hair, short beard, wearing a beige crewneck sweatshirt and a silver chain. Product is a luxury red geometric perfume bottle with a silver crocodile-shaped cap. Environment alternates between a high-end cinematic red studio, a neutral UGC indoor setting, and a software UI. Color grade is dominated by saturated "Louboutin Red" and deep blacks. Lighting is hard, directional, and dramatic for product shots; soft and natural for UGC shots. Speech is direct-to-camera, energetic, and professional.

[00:00–00:03]
Extreme close-up of the red perfume bottle. A hand with long, pointed red acrylic nails holds the bottle. Background is glossy red latex with vertical folds. Lighting is sharp, creating bright specular highlights on the silver crocodile cap. Text overlay: "every product SKU". Motion: Subtle camera drift towards the bottle.

[00:03–00:05]
Medium shot of a glamorous woman in a sharp red blazer and a man in a black tuxedo standing behind her. The woman holds the red perfume bottle. Background is a dark, moody gala setting with red curtains. Lighting is cinematic rim lighting. Text overlay: "but traditional shots are slow expensive and hard to scale".

[00:05–00:06]
Cut to the creator (Caucasian male, beige sweatshirt) in a brightly lit room with a green wall. He is speaking directly to the camera. Natural window lighting from the side.

[00:06–00:11]
Screen recording of the "Invideo" web interface. The cursor navigates to "Advertising Studio". A single product photo of the red bottle is uploaded. The UI shows various "Thematic Photography" presets like "Cartier" and "Amazon A+ Content". Text overlay: "this is advertising studio inside invideo".

[00:11–00:15]
The screen transitions to show a grid of generated assets: a primary Amazon white-background image, followed by a collage of "secondary listing visuals" and "lifestyle catalogue shots" featuring the red bottle in various Parisian and luxury settings.

[00:16–00:18]
A vertical three-panel split screen. Top panel: A black high-heeled boot on a white background. Middle panel: The red perfume bottle. Bottom panel: Black patent leather dress shoes. All three panels show the products rotating or being showcased cleanly. Text overlay: "if you manage products at scale this changes the entire workflow".

[00:19–00:21]
Return to the cinematic shot of the woman in the red suit and the man in the tuxedo. The woman holds the bottle towards the camera. Large bold text overlay: "comment 'STUDIO'". The lighting is warm and dramatic.

[00:22–00:24]
Black screen with a white animated logo (a stylized "i" or blob) followed by the "invideo" brand name and the tagline "Your Power to Play".

NEGATIVE PROMPT:
Visual: blurry textures, inconsistent bottle shape, distorted crocodile cap, flickering red lights, messy background, low resolution, watermark, distorted hands, extra fingers.
Speech: robotic tone, background noise, muffled audio, lip-sync delay, stuttering, flat delivery.

SPEECH PACK:
[00:00–00:05] "Every product SKU needs around 7 to 10 images to sell online, but traditional shots are slow, expensive, and hard to scale."
TAKE_A: Fast-paced, emphasizing "7 to 10" and "hard to scale."
TAKE_B: Concerned tone, slowing down on "slow, expensive."
TAKE_C: Professional narrator style, crisp enunciation.

[00:05–00:11] "This is Advertising Studio inside Invideo. Upload a single product photo, choose a preset..."
TAKE_A: Excited, "Aha!" moment delivery.
TAKE_B: Instructional, steady pace.
TAKE_C: Casual, like sharing a secret.

[00:11–00:21] "...and generate a complete asset set. If you manage products at scale, this changes the entire workflow. Comment 'STUDIO'."
TAKE_A: Authoritative, strong emphasis on "entire workflow."
TAKE_B: Direct and punchy, fast CTA.
TAKE_C: Smooth transition from explanation to the final command.

Vertical AI fashion-tech tutorial showing how to generate virtual try-on and outfit variations from a single street-style image. The video opens with a woman standing in a sunlit city street lined with yellow taxis and brick buildings, framed like a fashion campaign shot. Her original look is then transformed into multiple outfit variations, including a structured pale blue blazer dress, a dramatic deep-blue gown, a dark tailored look, and a short blue dress with bright shoes. The visual contrast between these versions immediately establishes the core promise: one subject, many AI-generated fashion outcomes.

The middle of the video moves into a software walkthrough. We see desktop interface screens with product selection, camera angle choices, photography style references, model or garment grids, and form fields for configuration. The creator clicks through options like selecting products, choosing visual style, adjusting photo settings, and generating new outfit versions. The tutorial keeps alternating between the interface and the finished fashion outputs, making it easy to connect each UI step to the visual change in the model image.

Later sections show the generated results in a side-by-side or sequential way, emphasizing how the same woman can be restyled into multiple commercial-ready looks. The workflow expands into broader catalog-style selection views and a final “Create Your Video” screen, suggesting this tool can turn fashion product choices into dynamic visual content. Overall, the clip should feel like a clean AI styling and virtual fashion try-on tutorial, blending product UI, model transformations, street-style fashion imagery, and creator-driven instructional pacing.

GLOBAL LOCK: 
Subject is a Caucasian male in his mid-30s with a well-groomed brown beard and medium-length wavy brown hair. He consistently wears a white and olive-green "VANS" trucker hat and a plain, high-quality white crew-neck t-shirt. The environment for the creator's shots is a warm, indoor setting with soft ambient lighting and a neutral, slightly out-of-focus background. The AI-generated content features a cinematic, high-contrast aesthetic with vibrant colors (primarily deep reds and blacks). The speech is energetic, clear, and direct-to-camera, delivered with a "tech-enthusiast" persona.

[00:00–00:05]
Visual: A cinematic, deep red Porsche 911 is shown from multiple angles: top-down, rear view, and 3/4 side profile. The car has a metallic finish and is set against a dark, moody red background with dramatic studio lighting. Text overlay reads "Multiview Perspective Change."
Subject: The creator appears in a small, rounded-square overlay at the bottom center, pointing upwards with both index fingers.
Camera: Smooth transitions between static product shots.
Speech: "This genuinely feels like a cheat code to create high-quality AI visuals for your brand or business."
Sync: Cut to the next shot on the word "business."

[00:05–00:19]
Visual: A rapid-fire montage of the creator's face swapped into various AI-generated scenes: 
1. A close-up of the VANS hat.
2. A model holding a smartphone.
3. A bold fisheye portrait wearing colorful puffer jackets and sunglasses.
4. An "Indie Garden Polaroid" shot with sunflowers and a guitar.
5. A "Halloween Party" shot of the creator in a yellow duck costume holding a red cup.
6. An "Urban Glare Portrait" in a city street.
Subject: Creator remains in the bottom overlay, gesturing with his hands as if explaining the variety.
Motion: Fast cuts (approx. 1-2 seconds each) with slight zoom-ins.
Speech: "This is called Blueprints, and it allows you to create multiple angled shots of any scene. You can upload product reference images and you can even replicate certain styles of images with a simple VFX template they've created for you."

[00:20–00:35]
Visual: Screen recording of the Leonardo.ai interface. The cursor moves to the left sidebar, hovering over and clicking the "Blueprints (Beta)" button highlighted with a red box. It then scrolls through a gallery of templates, selecting "Product Studio Photoshoot."
Subject: Creator in the overlay, looking slightly off-camera as if watching the screen, pointing to the UI elements.
Speech: "All you have to do is upload an image of yourself, and here's how to do it. To get started on Leonardo, you can go to the Blueprints section, and they have all of these different templates."

[00:36–00:45]
Visual: The UI shows the "Upload Person Photo" step. A photo of the creator in his white t-shirt and VANS hat is uploaded. Then, a "Product Photo" of a black smartphone is uploaded. The "Generate" button is clicked. The result shows the creator holding the phone in a professional studio setting.
Subject: Creator in the overlay, nodding and smiling as the result is revealed.
Speech: "You can then select one you want and upload a reference image of your face, for example, and then hit next. Now you can upload a reference image of a product, and then boom! You can actually create images of you holding the product in that environment."

[00:46–00:51]
Visual: The UI shows a "Multiview Perspective Change" generation of the creator sitting on a park bench from different angles (back view, side view, top-down). The video ends with the creator full-screen (or large overlay) against a dark background with the text "TYPE AI COMMENTS."
Subject: The creator winks at the camera and points forward.
Speech: "But it gets crazier because you can use different templates like multiview perspective... if you want to try it out for yourself, type AI in the comments and I'll send you the link."
Sync: Final wink lands exactly on the last word.

NEGATIVE PROMPT:
Visual: blurry face, inconsistent beard length, distorted VANS logo, extra fingers, flickering background, low-resolution UI, robotic body movements, unnatural skin texture, messy hair transitions.
Speech: monotone delivery, background noise, muffled audio, robotic cadence, misaligned lip-sync, harsh "S" sounds, long pauses between sentences.

SPEECH PACK:
[00:00-00:05]
Transcript: "This genuinely feels like a cheat code to create high-quality AI visuals for your brand or business."
TAKE_A: (Energetic, emphasizing "cheat code" and "business")
TAKE_B: (Fast-paced, breathless excitement)
TAKE_C: (Confident, authoritative tone)

[00:46-00:51]
Transcript: "If you want to try it out for yourself, type AI in the comments and I'll send you the link."
TAKE_A: (Friendly, inviting, with a wink at the end)
TAKE_B: (Direct, urgent, pointing at the camera)
TAKE_C: (Casual, "by the way" style delivery)

GLOBAL LOCK:
Subject is a fit Caucasian woman in her mid-20s, blonde hair tied in a high sleek ponytail, wearing a white zip-up athletic jacket. Skin tone is fair with warm undertones. Environment is a bright, high-key fitness studio with visible softbox lights and industrial windows. Lighting is soft, professional studio lighting. Color grade is clean, bright, high-contrast with vibrant whites. Speech is energetic, direct-to-camera UGC style. Mic signature is clean, close-proximity studio sound.

[00:00–00:04]
The subject is in a medium close-up, facing the camera. She holds a silver "GoodDay" sports drink can in her right hand at chest level. She is speaking directly to the camera with an energetic and friendly expression. Her head tilts slightly as she talks. Background shows a blurred studio setting with soft lighting.
Speech: "After training this hard, I need to recharge."
Lip-sync: High strictness required.

[00:04–00:06]
The subject continues speaking, gesturing slightly with her left hand while holding the can steady. She maintains a bright smile and high energy. The camera remains static in a medium close-up.
Speech: "That's why I grab my sports drink. What about you?"
Lip-sync: High strictness required.

[00:06–00:08]
The subject asks the final question and then pushes the silver can directly toward the camera lens, transitioning from a medium close-up to a close-up of the product. The motion is smooth and deliberate. The video ends with the can dominating the frame.
Speech: "Ready to feel unstoppable?"
Action: Forward push of the can toward the lens.
Lip-sync: High strictness on the final words.

NEGATIVE PROMPT:
Visual: blurry textures, distorted fingers, flickering background, inconsistent hair strands, unnatural eye movement, product label warping, low resolution, muddy colors, robotic limb movement.
Speech: robotic monotone, muffled audio, background hiss, lip-sync delay, unnatural pauses, slurred consonants, clipping audio.

SPEECH PACK:
Transcript:
00:00-00:02: "After training this hard,"
00:02-00:04: "I need to recharge."
00:04-00:06: "That's why I grab my sports drink. What about you?"
00:06-00:08: "Ready to feel unstoppable?"

Delivery Takes:
TAKE_A (Energetic): High pitch, fast pace, emphasis on "hard" and "unstoppable."
TAKE_B (Relatable): Medium pace, warm tone, slight breathiness after "hard."
TAKE_C (Authoritative): Crisp enunciation, steady pace, punchy delivery on "recharge."

Prosody Markup:
"After training THIS hard [pause], I need to RECHARGE. [pause] That's why I grab MY sports drink. What about YOU? [pause] Ready to feel UNSTOPPABLE?"

GLOBAL LOCK: Two primary female subjects. Subject A: Black woman, mid-20s, voluminous natural curly hair, warm skin tone, wearing a beige/cream oversized blazer and matching trousers. Subject B: Caucasian woman with red curly hair and prominent freckles, mid-20s, wearing a dark chocolate brown blazer and trousers. Environment: Minimalist studio with solid color backgrounds (beige, soft pink). Lighting: High-end cinematic editorial lighting, soft-box style, gentle shadows, vibrant color palette (orange, red, pink). Camera: Professional 35mm lens feel, shallow depth of field, dynamic movement. Speech: Energetic female voiceover, crisp studio recording, high lip-sync strictness for on-camera moments.

[00:00–00:02]
Subject A is in a medium close-up, leaning her arms over the curved edge of a large orange slide. She is looking directly at the camera, speaking with an engaging expression. Background is a clean, solid beige. Lighting is bright and even.
Speech: "So I heard you want to generate"
Lip-sync: High.

[00:02–00:04]
Wide shot, high angle. A long, orange spiral slide winds down against a beige wall. A model in a beige suit slides down the curves. The camera pans slightly to follow the movement.
Speech: "campaigns for your brand that are creative and fast"

[00:04–00:06]
Subject A is sitting on a bright red seesaw, medium shot. She is holding the handles and laughing. Background is a soft pastel pink. 
Speech: "that allow you to"

[00:06–00:07]
Hard cut to the exact same framing and seesaw, but Subject A is replaced by Subject B (redhead). She is in the same pose, laughing. This is a seamless "model swap."
Speech: "change the colors, swap models"

[00:07–00:09]
Subject B is standing in a full shot against the pink background. She holds a red bowl of dog food. A long-haired brown dachshund stands at her feet, looking up. She bends down slightly.
Speech: "and even make them hold or wear"

[00:09–00:10]
Close-up of the dachshund eating from the red bowl on the floor. The dog's fur texture is detailed.
Speech: "your products"

[00:10–00:13]
A dynamic grid animation showing multiple rectangular frames of both models in various poses and outfits (beige and brown suits). The frames tilt and move slightly.
Speech: "for your socials, your ads, and even your website"

[00:13–00:15]
Subject A is sliding down a red slide, medium shot, smiling. The camera tracks her movement. Beige background.
Speech: "Sounds fun, right?"

[00:15–00:16]
Subject B is walking across a red and white striped crosswalk painted on the floor. Side profile, medium shot. Pink background.
Speech: "The thing is"

[00:16–00:18]
Wide shot of Subject A sliding down the red slide, arms out, laughing.
Speech: "smart brands build campaigns"

[00:18–00:19]
Subject B is crouching on the red and white crosswalk, looking at the camera and laughing.
Speech: "that are worth remembering"

[00:19–00:21]
Extreme close-up profile of Subject B smiling and looking off-camera. Focus on her freckles and red hair texture.
Speech: "And thanks to AI, that's now easier than ever"

[00:21–00:25]
Subject B is in a direct-to-camera close-up, speaking directly to the viewer with a friendly, professional expression. Dark brown blazer visible.
Speech: "Comment AI and we'll send you the link to learn how"
Lip-sync: High.

NEGATIVE PROMPT: Uncanny valley, distorted facial features, inconsistent hair texture between shots, blurry skin, robotic body movement, flickering lighting, text artifacts, messy background, low resolution, mismatched lip-sync, harsh sibilance in audio, background noise.

SPEECH PACK:
[00:00-00:02] "So I heard you want to generate"
TAKE_A: (Curious, upbeat) So... I heard you want to generate...
TAKE_B: (Direct, professional) So I heard you want to generate...
TAKE_C: (Friendly, conspiratorial) So, I heard *you* want to generate...

[00:21-00:25] "Comment AI and we'll send you the link to learn how"
TAKE_A: (Action-oriented) Comment AI, and we'll send you the link to learn how!
TAKE_B: (Helpful) Just comment AI, and we'll send over the link.
TAKE_C: (Energetic) Comment AI now, and we'll send you the link to learn how!

A polished vertical fashion commercial featuring the same fair-skinned red-haired woman in two coordinated visual setups. The video opens in a bright white living room with natural daylight, a pale sofa, and tall green plants behind her, where she wears an oversized light pink shirt and speaks casually to camera like a lifestyle recommendation or personal confession. Minimal wardrobe graphic overlays appear briefly above or beside her, suggesting clothing choices or a styling comparison. Midway through the clip, the tone pivots sharply into a clean white seamless studio, where the woman now wears a deep burgundy long-sleeve turtleneck knit dress or coordinated fitted fashion set. She poses in a high-end editorial manner with angular arm lines, seated and crouched poses, and direct beauty-camera eye contact. White text reads “Never mind.” The overall look is elegant, minimal, luxury fashion advertising with clean color control, soft skin detail, premium styling, and a dramatic contrast between casual lifestyle setup and editorial studio reveal.

GLOBAL LOCK: 
Subject: A gourmet double-cheeseburger and a stack of berry pancakes. 
Identity: Photorealistic, high-end commercial product photography. 
Lighting: Studio-quality key lighting, soft shadows, high-contrast highlights on textures (sesame seeds, melting cheese, glistening syrup). 
Color Grade: Warm and saturated for the burger (red/orange/brown); bright, airy, and pastel for the pancakes (soft blue background, vibrant red berries). 
Camera: Macro lenses, shallow depth of field (bokeh), smooth slow-motion movement. 
Speech: Male creator, mid-30s, energetic and instructional tone, clear articulation, close-mic podcast quality.

[00:00–00:05]
Visual: A gourmet burger centered on a dark red gradient background. The burger "explodes" vertically, with the top bun, lettuce, tomato slices, cheese, and patty floating upwards in slow motion. Floating text labels "Cheese $0.50", "Tomato $1.50", "Lettuce $1.00" appear next to the layers.
Motion: Smooth vertical expansion, slight rotation of the burger.
Speech: "Here's how you can create this epic transition using AI to showcase all the ingredients in any product."
Lip-sync: High (creator visible in bottom split-screen).

[00:05–00:10]
Visual: Screen recording of LTX Studio interface. A storyboard view shows "Shot 1" (exploded burger) and "Shot 2" (whole burger). The cursor moves between shots.
Motion: UI navigation, scrolling through a timeline.
Speech: "And you can even add all of these shots into a perfect timeline to help you with this sequence."

[00:10–00:14]
Visual: A top-down iPhone photo of a pancake stack on a pink plate, sitting on a wooden table. Hands are visible briefly at the edges.
Motion: Static photo, slight handheld camera shake.
Speech: "To get started, you want to take a picture of the product that you want to showcase."

[00:14–00:23]
Visual: UI of LTX Studio. A cursor drags the pancake photo into an "Image" slot. The user types "fix the light and make it look like an e-commerce photo" into a prompt bar.
Motion: Drag-and-drop action, real-time text typing.
Speech: "Then you can go to LTX Studio where you can drag and drop in this photo. In the prompt bar now you can write in a basic prompt..."

[00:24–00:27]
Visual: A 2x2 grid of four AI-generated pancake images. Each shows the stack from a slightly different angle with a clean light blue background. One is selected.
Motion: Selection highlight, "Before" and "After" comparison wipe.
Speech: "Then you can select Nano Banana for your image model and you can pick the image you like the most. Here's the before and after."

[00:28–00:32]
Visual: The AI-generated pancake stack. The layers separate vertically. A silver spoon appears at the top, pouring thick white cream/syrup onto the stack.
Motion: Slow-motion liquid simulation, vertical layer separation.
Speech: "Now you can use that image and prompt different camera angles of this shot."

[00:33–00:40]
Visual: Final montage of pancake shots: top-down view, side view with falling fruit (blueberries, raspberries, mango). Text overlay: "type 'AI' in the comments".
Motion: Dynamic falling objects, smooth camera pans.
Speech: "Then you can take these images and turn them into fully crafted videos all inside of LTX Studio. If you want to try it out, type AI in the comments and I'll send you the links."

NEGATIVE PROMPT: 
Visual: Blurry textures, distorted food shapes, flickering lighting, inconsistent berry placement, messy syrup flow, robotic hand movements, low-resolution UI, text artifacts in the background.
Speech: Robotic monotone, background hiss, muffled audio, lip-sync delay, unnatural pauses, harsh "S" sounds.

SPEECH PACK:
[00:00-00:05]
TAKE_A: "Here's how you can create this epic transition using AI to showcase all the ingredients in any product." (Fast, high energy)
TAKE_B: "Check out this smooth AI transition that breaks down every ingredient in your product commercial." (Professional, rhythmic)
TAKE_C: "Want to make your products pop? Here is the AI secret for exploding transitions." (Hook-focused, punchy)

[00:36-00:40]
TAKE_A: "If you want to try it out, type AI in the comments and I'll send you the links." (Direct, friendly)
TAKE_B: "Comment the word AI below and I'll DM you the link to get started." (Instructional)
TAKE_C: "Ready to build this? Just type AI below and check your DMs." (Short, urgent)