AI Book Cover Generator for Self-Published & KDP Authors

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 blonde female creator in a vertical talking-head tutorial explains why Midjourney still stands out compared with every other image generator she has tested. She appears in a clean indoor creator setup with a clip-on lav mic, speaking directly to camera. The edit repeatedly cuts to example images demonstrating many different creative categories: editorial portraits, lifestyle photography, cinematic fantasy creatures, poster design, product shots, business scenes, thumbnails, nail beauty macro, illustrated covers, and branded commercial visuals. Bright yellow all-caps caption fragments appear over the presenter to emphasize key claims. The tone is opinionated, fast, educational, and highly creator-oriented.

[00:00-00:06]
Open with the presenter stating that she has tested every major image generator. Intercut quick example visuals: polished editorial portraits, high-style fashion or business shots, and surreal fantasy imagery. The hook establishes a comparison-based tutorial.

[00:06-00:12]
The presenter continues in direct-to-camera mode while examples flash on screen showing poster-style graphics, clean product imagery, lifestyle travel scenes, and stylized character art. The message is that no other tool matches Midjourney’s breadth and quality.

[00:12-00:18]
Cut through more categories: beauty close-ups, cinematic environments, realistic portraits, thumbnails, branded compositions, and bold poster designs. The creator points out use cases like thumbnails, products, and business visuals.

[00:18-00:24]
The tutorial emphasizes practical strengths: consistency, versatility, and premium-looking results. More examples appear, including animals, commercial-style food or product shots, and polished people imagery. The pacing remains sharp and category-driven.

[00:24-00:27]
End with the presenter delivering a summary and call-to-action style close, while the final frames reinforce the Midjourney comparison point and encourage saving or following for more creator-tool advice.

NEGATIVE PROMPT:
male presenter, no example images, no yellow caption phrases, blurry screenshots, no variety of styles, no portrait examples, no poster or product visuals, flat stock imagery, watermark, text glitches

SPEECH PACK:
One female English-speaking creator voice.
TRANSCRIPT INTENT: Explain that after testing many image generators, Midjourney still outperforms others across multiple visual categories such as portraits, products, thumbnails, posters, and stylized scenes.
DELIVERY: Fast, assertive, expert-review cadence with short emphasized claims and creator-focused framing.
SYNC: Talking-head segments require tight lip-sync; image example sections can run under voiceover and caption emphasis.

Create a vertical 9:16 minimal premium design-poster visual for an AI creative workflow, featuring a bright yellow tennis ball floating just above an outstretched human hand against a clean blue sky. The hand should rise from the lower portion of the frame wearing a white wristband, with the ball suspended in crisp sunlight so it feels like a polished 3D object hovering in space. Bold yellow Lovart text repeats in the upper left, while repeated Design text appears in the lower right like confident editorial poster typography. The overall result should feel like a high-end animated 3D poster concept for designers: simple, modern, vector-friendly, and easy to manipulate as a motion design asset. No clutter, no subtitles, no extra objects, no cartoon style.

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!"

GLOBAL LOCK: A young South Asian woman with long, straight dark hair and a friendly, articulate expression. She wears a light pink/beige long-sleeved ribbed top. The setting is a bright, modern indoor room with a neutral off-white wall. In the background, a minimalist black abstract sculpture sits on a wooden desk. Lighting is soft, even, and frontal, creating a clean UGC aesthetic. Audio is crisp with a close-mic signature, as she holds a small black wireless lavalier microphone.

[00:00–00:02]
Subject: Medium shot of the woman holding the microphone near her mouth.
Action: She speaks directly to the camera with an enthusiastic expression.
Text Overlay: Large, stylized pink and white text reads "SIDE HUSTLE you NEVER thought of".
Camera: Static MS, eye-level.
Lighting: Soft indoor lighting.

[00:02–00:04]
Environment: Screen recording of a Google search page.
Action: A cursor moves and clicks on a search result for "Gemini Storybook — for the story".
Text Overlay: Green text "Go to this" appears at the top.
Camera: Direct screen capture.

[00:04–00:06]
Environment: Digital interface showing a 10-panel storyboard titled "THE LIBRARY OF WHISPERS".
Action: The screen scrolls slightly to show the different panels (P1 to P10) featuring indie-style illustrations of a girl in a library.
Text Overlay: Green text "Plan an entire storyboard".
Camera: Direct screen capture.

[00:06–00:09]
Environment: AI tool interface showing an upload area.
Action: A cursor drags a white square icon into an upload box. Then, a character sheet titled "OUTFIT DETAILS" is shown, featuring a girl in a green cardigan and brown corduroy pants.
Text Overlay: Green text "your inputs like images characters or sketches".
Camera: Direct screen capture.

[00:10–00:12]
Environment: Text prompt box in an AI interface.
Action: The text "Create a 10-page comic titled The Library of Whispers..." is visible. The cursor clicks a "Send/Generate" arrow icon.
Text Overlay: Green text "an entire storyline Hit generate".
Camera: Direct screen capture.

[00:13–00:16]
Subject: Medium shot of the woman holding a smartphone vertically.
Action: The phone screen displays a digital comic book cover. She uses her thumb to "flip" a digital page, revealing a beautifully illustrated page with text.
Text Overlay: Green text "and boom! a comic book without any".
Camera: Static MS, focusing on the phone in her hand.

[00:17–00:19]
Subject: Medium shot of the woman speaking to the camera.
Action: She gestures with her hands while explaining the customization options.
Text Overlay: Green text "involved customize for any".
Camera: Static MS.

[00:20–00:25]
Environment: Close-up of a digital comic book page.
Action: The page features a yellow background with two characters (a girl with dark hair and a boy with white hair). The text on the page discusses "identifying feelings and thoughts."
Text Overlay: Green text "educational I made one for EQ which will identify between and thoughts".
Camera: Direct screen capture/Close-up of the art.

[00:26–00:28]
Environment: Amazon Kindle Direct Publishing (KDP) dashboard.
Action: The screen shows the "Manage. Publish." section with buttons for "Kindle eBook" and "Series page".
Text Overlay: Green text "After this you can sell them as ebooks".
Camera: Direct screen capture, dark mode UI.

[00:29–00:32]
Subject: Medium shot of the woman speaking her final call to action.
Action: She smiles and gestures towards the screen.
Text Overlay: Green text "And for cool as such" followed by a stylized logo "the CYBORG girl" in pink.
Camera: Static MS.
Speech: "And for cool AI hacks as such, follow the Cyborg Girl for more."

NEGATIVE PROMPT: blurry, low resolution, inconsistent facial features, flickering lighting, robotic movements, distorted text in overlays, messy background, poor lip-sync, harsh shadows, over-saturated colors, watermark, low-quality audio, background noise.

SPEECH PACK:
[00:00-00:02] "Here's a side hustle you never thought of."
TAKE_A: (Energetic, fast-paced) "Here's a side hustle you NEVER thought of!"
TAKE_B: (Intriguing, lower pitch) "Check out this side hustle... you probably never thought of."
TAKE_C: (Friendly, casual) "So, here is a side hustle you've never thought of before."

[00:13-00:16] "And boom! You just made a comic book without any manpower involved."
TAKE_A: (Excited, emphasizing 'boom') "And BOOM! You just made a comic book, no manpower needed."
TAKE_B: (Satisfied, calm) "And just like that, you've got a comic book without any manual work."
TAKE_C: (Punchy) "Boom! A full comic book, zero manpower involved."

[00:29-00:32] "And for cool AI hacks as such, follow the Cyborg Girl for more."
TAKE_A: (Warm, inviting) "For more cool AI hacks like this, follow the Cyborg Girl!"
TAKE_B: (Direct, authoritative) "Follow the Cyborg Girl for more AI hacks just like this one."
TAKE_C: (Smiling, upbeat) "Want more AI hacks? Follow the Cyborg Girl!"

GLOBAL LOCK: A 9:16 vertical social-first AI tutorial video explaining how brands or businesses can create AI videos. Alternate between a male creator speaking directly to camera and polished example visuals or screen-style workflow inserts. The speaker is a white male in his 20s or 30s with medium dark beard, shoulder-length hair, and a light baseball cap, framed chest-up against a neutral indoor background. His delivery is energetic, instructional, and creator-economy fluent. The visual examples should look like premium Midjourney-to-Kling style concept art: dreamy clouds, music-brand inspired posters, cinematic surreal scenes, and polished brand-ready compositions. Keep the edit fast, clear, and educational, with bold on-screen references to steps or examples. No heavy cinematic drama; this should feel like a viral creator tutorial optimized for Instagram. Audio is speech-first, with the speaker driving the narrative and visuals supporting each claim.

[00:00-00:04] Open on a polished AI visual concept frame in a square-ish or embedded example format, such as a dreamy cloud scene with brand-style treatment, immediately establishing the quality level of the output being discussed.

[00:04-00:08] Cut to the male creator speaking directly to camera, chest-up, hands visible making small emphasis gestures, clearly introducing how brands or businesses can create AI videos.

[00:08-00:14] Alternate quickly between more AI-generated example images and the creator talking head, showing branded concepts, surreal poster-like compositions, and elevated campaign-style visuals while the speaker explains the workflow.

[00:14-00:20] Show additional examples such as Nike-style or music-video-inspired visual mockups, then return to the speaker for practical commentary, keeping the rhythm instructional rather than purely aesthetic.

[00:20-00:28] Introduce workflow-style inserts that resemble app or editing interfaces, indicating transformation from image generation to video generation, while the speaker continues the explanation.

[00:28-00:40] Continue the pattern of speaker-to-example, making the process feel accessible: generate the image, upscale or refine it, animate it, and adapt it for brand content.

[00:40-00:52] Close with more high-quality AI visuals and one final talking-head summary, reinforcing that this is a repeatable business or creator workflow rather than a one-off trend.

NEGATIVE PROMPT: static corporate webinar, boring slide deck, low-detail AI art, cartoon mascot, ugly text clutter, broken face, stiff talking head, empty gestures, dark moody studio, podcast mic setup, random unrelated b-roll, unreadable UI, logos that dominate every frame, lip-sync mismatch, robotic speech cadence, badly generated hands, muddy branded visuals, overlong transitions, generic business office stock footage.

SHOT PROMPT DELTAS:
1) Premium AI brand example visual in dreamy commercial style.
2) Direct-to-camera creator explanation with hand gestures.
3) Alternating branded concept art and tutorial talking head.
4) Workflow/UI inserts suggesting image-to-video pipeline.
5) Final summary with more polished example outputs.

SPEECH PACK:
[00:00-00:52] Speech present. One male speaker throughout. Delivery should be confident, quick, and educational, with short punchy sentences explaining how to create AI videos for brands or business use. No lip-sync perfection required if used only as narration over cuts; medium strictness if the mouth is visible.

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

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

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

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

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

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

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

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

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

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

GLOBAL LOCK:
Subject: 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."

GLOBAL LOCK: Subject is Natalia Dyer, an American actress with an oval face, high cheekbones, large expressive brown eyes, and fair skin with natural warmth. Her hair is dark brown, long, and wavy, styled into two thick, loose braids falling over her shoulders. She wears a dark, high-collared cloak/coat. Her expression is neutral, serene, and slightly melancholic, looking directly at the camera. The camera is a static Medium Close-Up (MCU) with a cinematic 35mm lens feel. High-fidelity skin textures and realistic lighting are mandatory.

[00:00–00:01]
Subject is centered in a grand, atmospheric gothic cathedral. Background features intricate stone arches and stained glass windows. Lighting: Misty, volumetric light beams (God rays) filter through the windows, creating a teal and orange contrast. Subject's face is softly lit by the ambient glow. Motion: Subtle dust motes dancing in the light beams.

[00:01–00:02]
Subject is centered in a vast golden hour meadow. Background features tall, dry grass and a distant horizon under a setting sun. Lighting: Warm, intense amber backlighting creating a soft rim light on her hair and cloak. A subtle lens flare peeks from the corner. Motion: Very slight swaying of the grass in the background.

[00:02–00:03]
Subject is centered in a dense autumn forest. Background is filled with vibrant orange and red maple leaves. Lighting: Dappled sunlight filtering through the canopy, creating soft patches of light on her face. Shallow depth of field with a creamy bokeh effect on the leaves. Motion: A few leaves slowly falling in the background.

NEGATIVE PROMPT: 
Facial distortion, changing eye color, changing hair style, inconsistent facial features, cartoonish look, plastic skin, extra limbs, blurry face, text, watermark, logo, flickering lighting, sudden jumps in subject position, robotic movement, oversaturated colors, low resolution.

GLOBAL LOCK: A vertical collector-review talking-head video, approximately 1 minute 53 seconds, centered on a male creator enthusiastically discussing a physical book or art publication in a cozy media room. The host is a light-skinned ginger-bearded man wearing glasses, a dark baseball cap, and a graphic tee, speaking directly to camera from a seated desk setup. Behind him are shelves, posters, anime and pop-culture decor, a world map, collectibles, and lit computer equipment, giving the room a casual nerd-culture creator vibe. He uses animated hand gestures, points toward the camera, and repeatedly holds up the book and interior pages as visual proof while talking.

The featured item is a printed publication with a bold teal or green cover and franchise-style branding, shown both closed and open. The host flips through pages, highlights “starter” materials, and calls attention to interior photos or artwork. The edit occasionally cuts away from the host to close-up shots of the book itself, including black-and-white illustration pages with fantasy-creature or goblin-like line art, allowing viewers to inspect the visual content directly. White subtitle text appears across many shots, emphasizing key spoken points and giving the video a clipped, creator-review rhythm.

The overall tone is enthusiastic, collector-friendly, and explanatory. This is not a cinematic ad and not a generic vlog; it is a fandom/collector breakdown where the value lies in seeing a real person present and react to a physical piece of media. Visual priorities: direct-to-camera creator presence, cozy decorated room, clear visibility of the book cover and interior spreads, subtitle emphasis on key phrases, hand-held page flips, and a sense of personal recommendation or show-and-tell. Avoid over-stylized editing. The charm comes from authenticity, physical object handling, and the host’s excited commentary.

GLOBAL LOCK: A fast-paced vertical 9:16 creator-tool Reel, approximately 39 seconds, built from alternating talking-head footage and bright white SaaS interface screens. Keep the host consistent across the whole timeline: white male in his late 20s to early 30s, slim build, side-parted brown hair, clean-shaven, wearing a dark charcoal or black crew-neck top, speaking into a large black front-address microphone, framed in a rounded-corner lower panel with warm amber-brown studio background and soft flattering key light. The second visual world is a clean Lovart interface shown mostly on white backgrounds with black text, light-gray cards, and thumbnail canvases. The third visual world is a set of YouTube-style thumbnails focused on male self-improvement / money / outreach / rules content, often with bold yellow or blue text, a male presenter portrait on the right, chart graphics, arrows, and high-contrast click-oriented design. Maintain aggressive jump-cut pacing every 1 to 2 seconds, crisp UI readability, no clutter outside the interface elements, and one energetic male speaker throughout with close-mic dry audio, clear English cadence, excited but practical tone, lips visible during host shots.

[00:00-00:03] Open on a white Lovart-branded background showing three example thumbnails in a row: a bold yellow money thumbnail, a red-and-white net worth thumbnail, and a numbered bottle-style comparison graphic. The host appears in a rounded talking-head box below, raising one finger as he starts the hook. Audio: single male host announces that this is a better or easier way to create thumbnails, or that the tool changes how thumbnail ideation works.

[00:03-00:07] Cut between the host and more sample thumbnails, including a finance/investing guide style card with a male face, dollar annotations, and editing instructions, then an outreach chart thumbnail labeled 4 TYPES OF OUTREACH. The host keeps pointing upward, matching the beat of each new thumbnail. Lighting on host stays warm; thumbnails stay bright, white-dominant, and highly legible.

[00:07-00:11] Move into the Lovart file/document view on a dark gray workspace with multiple imported thumbnail references arranged in a grid. Show the host below continuing to talk while the interface demonstrates that several inspiration images can be loaded at once. Audio: same speaker explains that you can upload inspiration thumbnails and work from them directly.

[00:11-00:16] Transition to the white Lovart prompt workspace labeled Design is easier with Lovart. Show a large prompt field and a card-based layout where attached references appear on the right or top. Cursor focus should imply a natural-language command is being entered. Audio: host explains that you simply tell the system in plain English how to transform or take inspiration from the reference thumbnail.

[00:16-00:22] Show a sequence of prompt cards with explicit edit instructions, such as recreating the second attached thumbnail, placing the host face from the first image, or keeping the main text while changing the face. The host continues in the lower frame, gesturing rhythmically. The interface should feel beginner-friendly and not overly technical. Audio: one speaker emphasizes simplicity and speed, with phrases about using plain English and uploading inspiration thumbnails.

[00:22-00:27] Reveal a zoomed view of the edited prompt result and the generated thumbnail outputs. Use variants around a self-improvement thumbnail reading 5 Rules 1. No phone after 10pm, including slight typography or layout changes across versions. Show how the face, title placement, and color block stay recognizable while the design gets remixed. Audio: host underscores that the tool can iterate thumbnail ideas faster than building each one manually.

[00:27-00:33] Expand the result set into multiple derivative thumbnails, such as 7 Mantras 1. No food after 10pm or revised 5 Rules variants, then display UI controls that suggest choosing among versions or continuing to refine. Keep the white interface clean and uncluttered, with the host below maintaining eye contact. Audio: host frames the value in terms of scaling from one idea to multiple ideas and faster testing.

[00:33-00:36] Show the final polished YouTube-style thumbnail on a dark background with a clear title treatment, then cut to a comparison-style CTA row at the bottom featuring labels such as 3x faster, 10x faster, STOP, Manual, and AI. The host intensifies his delivery to set up the conversion. Audio: same speaker makes the benefit explicit: more thumbnail ideas in less time.

[00:36-00:39] End on a bold CTA screen reading COMMENT "AI" while the host remains in the lower panel finishing his line. Use strong white text with yellow AI accent on a dark card, and retain the polished thumbnail examples nearby so the CTA remains tied to the promised outcome. Audio: punchy final ask to comment AI for the link, no fade.

NEGATIVE PROMPT: avoid unreadable thumbnail text, avoid distorted charts or arrows, avoid broken facial features on sample thumbnail portraits, avoid muddy interface screenshots, avoid random extra UI panels, avoid low-resolution white backgrounds, avoid incorrect Lovart branding, avoid host identity drift, microphone deformation, warped hands during finger-pointing, robotic speech, lip-sync mismatch, harsh compression, clipping, or CTA text other than COMMENT "AI".

GLOBAL LOCK: The video is a high-quality screen recording of a desktop browser. The interface is ChatGPT in "Dark Mode" (dark charcoal background, light gray text). The font is the standard ChatGPT sans-serif. The cursor is a standard white pointer. All text overlays are in a bold, white, all-caps sans-serif font, positioned in black "letterbox" bars at the top and bottom of the frame. The overall vibe is clean, instructional, and tech-focused.

[00:00–00:03]
Visual: A static screen recording of the ChatGPT interface. A large text overlay at the top reads "STEP 1: CREATE YOUR CHARACTER PROMPT USING CHATGPT". The GPT name "Midjourney V7 - Photorealistic Image Prompts" is visible at the top of the chat.
Action: The screen is still, establishing the scene.
Audio: Low-fi tech beat starts, steady and rhythmic.

[00:03–00:07]
Visual: The cursor clicks into the "Ask anything" input box at the bottom. The text "give me a front view shot of portrait shot of woman in her 20s, model, with crazy facial features and should look very unique and easily recognizable, front view shot, looking into the camera, flat studio lighting" is typed out rapidly.
Action: Rapid typing animation.
Audio: Subtle keyboard clicking sounds synced to the typing.

[00:07–00:11]
Visual: The AI begins to respond. The text "Here's your photorealistic Midjourney prompt based on your description: Prompt: A front view portrait shot of a woman in her 20s, fashion model, with highly unique and exaggerated facial features..." streams onto the screen.
Action: Text "streaming" effect where words appear one by one from left to right.
Audio: The music continues; the typing sounds stop as the AI generates.

[00:11–00:14]
Visual: The cursor moves up and highlights the generated prompt text in a light blue selection box. A bottom text overlay appears: "Head to ChatGPT and search for GPTs to find 'Midjourney V7...'. Describe your character, and the GPT will generate the perfect prompt for you to copy." A small white hand icon with a clicking animation appears in the bottom right corner.
Action: Smooth cursor movement and text selection.
Audio: Music swells slightly for the conclusion.

NEGATIVE PROMPT: Handheld camera shake, blurry screen, light mode UI, messy desktop icons, low resolution, watermark, robotic voiceover, stuttering text generation, inconsistent font styles, bright colors, distracting background elements.

SPEECH PACK:
(Note: This video has no spoken dialogue, only text-to-be-read. The "Speech" here refers to the rhythmic delivery of the text overlays.)

Segment 1 [00:00-00:03]: "STEP 1: CREATE YOUR CHARACTER PROMPT USING CHATGPT"
TAKE_A: Bold, authoritative, slow pacing.
TAKE_B: Fast, energetic, "hack" style.
TAKE_C: Neutral, instructional.

Segment 2 [00:11-00:14]: "Head to ChatGPT and search for GPTs to find 'Midjourney V7...'"
TAKE_A: Informative, helpful tone.
TAKE_B: Urgent, "do this now" tone.
TAKE_C: Calm, step-by-step guidance.

GLOBAL LOCK: vertical 9:16 creator-tutorial video about making animated 3D poster designs with AI inside Lovart. The format combines a creator talking-head inset with a large design-canvas interface showing poster layouts, object compositions, typography placement, and brand-style concept iterations. The presenter is a young man in a blue baseball cap with yellow detail, neutral-colored t-shirt, and studio lighting, speaking directly to camera from a creator setup. His inset remains near the lower part of the frame while the main screen above demonstrates the design process.

The content should show multiple high-impact poster examples on a clean white design workspace: a sporty Wilson tennis poster with a player and oversized racket, a luxury-style watch poster inspired by Rolex, tech-product hand-and-watch layouts inspired by Apple and Casio, skate-fashion and shoe posters inspired by Vans “Off The Wall,” and bold graphic poster compositions with brand-like typography, textured backgrounds, and floating 3D product placements. The interface should feel like a modern AI design tool with draggable elements, scaling handles, layer boxes, and editable text areas. The emotional tone is practical, design-forward, visually trendy, and aimed at creators, brands, and marketers who want poster-level visuals without complex 3D software.

[00:00-00:07] Open on a clean white design canvas showing a bold AI-generated poster mockup. Examples include a yellow/blue sports-fashion poster and a Wilson-themed tennis composition with oversized typography and a player holding a racket. The creator appears in a small lower inset explaining that Lovart can be used to create animated 3D posters without traditional complex 3D workflows.

[00:07-00:15] Move through several poster variations on the canvas. Show a seated figure in a fashion-style poster, a tennis player composition with giant racket framing, and editable layout elements with bounding boxes or control handles around the artwork. The interface should make it obvious that these are being designed inside one platform rather than assembled manually across multiple apps.

[00:15-00:24] Shift to luxury and product-poster examples. Show close-up hand shots wearing watches against bold green, red, and beige background blocks, evoking Rolex, Apple, and Casio-inspired poster layouts. The creator continues talking while the main design workspace cycles through these premium, brand-like concepts.

[00:24-00:34] Transition into sneaker and skate posters. Feature a black sneaker in dynamic perspective over checkerboard or gradient backgrounds, large “Off The Wall” / Vans-like typography, and poster-style compositions that feel slightly three-dimensional or layered. Include multiple variations to emphasize iteration and creative control.

[00:34-00:45] End on the strongest Lovart workflow payoff: several poster versions shown in sequence with editable text fields, layer guides, and template-style composition zones. The message should be clear that AI can accelerate poster ideation, visual styling, and animated design output for brands and creators, all within a single polished design environment.

VISUAL DNA:
- Clean white or light design-canvas UI with editable poster boards.
- Creator talking-head inset at the bottom.
- Brand-inspired poster concepts across sports, watches, tech, and skate culture.
- Bold typography, oversized product framing, layered image cutouts, and 3D-ish design depth.
- Lovart branding and AI design-tool positioning.

STYLE LOCK:
- Creator tutorial and software demo, not generic inspiration slideshow.
- Graphic-design-first visuals with polished poster aesthetics.
- Multiple case-study style poster examples to prove breadth.
- Modern social design energy with premium art-direction sensibility.

NEGATIVE PROMPT: dark coding dashboard, plain webinar slideshow, no creator inset, generic stock ad montage, no editable canvas, no poster composition tools, boring corporate presentation, random unrelated brand assets, political content, horror visuals, sports broadcast footage, no typography, low-quality Canva template feel, subtitles burned in, fully finished commercial with no design-process context.

SHOT PROMPTS:
SHOT 1: Lovart design canvas with sports-fashion and Wilson-style poster examples plus creator inset.
SHOT 2: editable layout handles around poster boards on a clean white workspace.
SHOT 3: luxury watch posters with hand close-ups and bold background color fields.
SHOT 4: Vans-style skate sneaker posters with “Off The Wall” graphic composition energy.
SHOT 5: final multi-poster workflow view showing text edits and AI design control.

SPEECH PACK:
[00:00-00:45] Natural creator tutorial commentary explaining how to use Lovart's AI-powered design tools to create animated 3D posters quickly for brands, designers, and content creators.

GLOBAL LOCK: A vertical cinematic-teaching reel, approximately 47 seconds, designed as a visually rich prompt-and-framing tutorial for better AI-generated film stills. The video alternates between sample portrait or scene imagery and bold centered on-screen text that critiques low-quality AI aesthetics and then replaces them with concrete visual principles. The piece opens with a polished but generic blonde beauty portrait on a black background labeled as “low quality AI,” then pivots into stronger cinematic examples: moody urban night scenes under arches, distant silhouettes in fog, soft practical lighting, handheld-style portraits, and warm sunset close-ups of a short-haired woman. The overall color world leans teal-green shadows, warm amber highlights, subtle grain, and low-key cinematic contrast.

The structure is educational, not narrative. Text captions carry the teaching flow: first rejecting weak AI image habits, then introducing simple filmmaking rules such as better frames, one dominant camera perspective, warm sunset key light from one side, natural texture, contrast, and the idea that the work should visually prove itself. The imagery should feel like proof-of-concept boards or moving mood references rather than continuous story scenes. Most shots are carefully composed single moments: a woman framed in shallow light, two people under an urban arch, a hand-held close-up with soft night lighting, and other filmic fragments that demonstrate intentional cinematography.

The tone should feel confident, minimalist, and opinionated, like a creator explaining how to stop making generic AI portraits and start making cinematic images with stronger visual grammar. Visual priorities: centered all-caps instructional text, black separators or negative space, elegant comparison between generic beauty render and moodier cinematic frames, teal-and-amber grading, shallow depth of field, strong directional light, tasteful grain, and compact tutorial pacing. Avoid busy graphics, loud meme styling, or heavy voice-dependent explanation. The point is that the lesson is readable through image-plus-caption alone.

GLOBAL LOCK: A vertical 9:16 split-screen social proof video featuring the same white European-looking man in his late 20s to early 30s with fair neutral skin, brown side-swept hair, athletic build, clean-shaven face, fitted dark t-shirt, thin silver necklace, and dark smartwatch, seated at a round table using a space gray laptop. Keep his identity, face shape, hair, posture, laptop position, hand placement, watch, necklace, and down-looking focused expression consistent across the full sequence. The lower half of the frame is always the original source clip: a clean but ordinary bright apartment interior with white walls, hallway opening, wall-mounted TV on the left, soft daylight, and neutral consumer-camera realism. The upper half is always the AI-transformed version of the same moment, preserving pose and laptop interaction while swapping only wardrobe details slightly and dramatically changing the environment. Camera remains static, eye-level to slightly high, medium shot, portrait framing. Motion is minimal and realistic: typing, brief thinking gesture to chin, subtle head angle changes. Text overlays read “AI:” at top left, “Original:” above the lower section, and “Comment ‘AI’ for the prompts” centered between the halves. Style is crisp creator-demo proof, optimized for instant comparison and save/share behavior.

[00:00-00:01] Show the first split-screen comparison. In the upper half, place the creator in a warm wooden cabin interior with large windows, mountain view, practical lamp glow, and cozy brown timber walls while he types on the laptop. In the lower half, show the original bright apartment scene with the same seated pose and laptop placement. Keep the comparison clean and immediately readable.

[00:01-00:02] Swap only the upper half environment to a Santorini-style terrace at golden hour with blue railing, sea cliffs, and warm sunset light. The creator remains seated with matching body angle and laptop orientation. Lower half stays unchanged as the original apartment plate.

[00:02-00:03] Change the AI upper half to a Mediterranean villa interior with arched windows, cream stucco walls, sunlit floor, and olive trees visible outside. The creator briefly raises a hand toward his face in a thinking pose; mirror that motion in the original bottom half.

[00:03-00:04] Move the upper half into a high-rise luxury apartment with floor-to-ceiling windows and orange city sunset. Keep the creator’s pose, laptop, and chin-touch gesture aligned to the original. Preserve the centered comparison layout and CTA text.

[00:04-00:05] Transform the upper half into a dark wood library office with desk lamp, warm pools of light, bookshelves, and a more formal mood. The creator’s hands return to the keyboard. The original lower clip remains a plain daylight apartment with no background change.

[00:05-00:06] Hold on the same library-office transformation for an extra beat to let the comparison land. Maintain fixed camera, no zoom, and the same overlay text.

[00:06-00:07] Replace the upper half with a moody rainy-window lounge scene in teal and amber tones, soft reflections on glass, and a dim modern sofa in the back. The creator continues typing with serious concentration. Bottom half remains the bright apartment.

[00:07-00:08] Switch the upper half to a tropical outdoor workspace with wood structure, large tropical leaves, bright sun patches, and warm travel-lifestyle energy. The creator stays locked in the same seated laptop pose.

[00:08-00:09] Change the upper half to a glass house surrounded by green forest, soft daylight filtered through large panes, and minimalist modern architecture. Preserve the same shirt silhouette, watch, necklace, laptop size, and head tilt.

[00:09-00:10] Move the upper half to a luxury hotel suite at night with warm lamps, city lights outside, beige furnishings, and premium travel ambience. Keep the original lower half unchanged and clearly labeled.

[00:10-00:11] End on the final split-screen comparison with the same city-hotel AI background held long enough for viewers to read the CTA: Comment “AI” for the prompts. No extra camera motion, just a clean proof-driven finish.

NEGATIVE PROMPT: do not alter identity, face proportions, hairstyle, skin tone, build, laptop scale, or seated posture between scenes; avoid warped hands on keyboard, broken wrists, floating elbows, inconsistent necklace, or missing watch; avoid morphing furniture, flicker, unstable split line, typography corruption, or mismatched perspective between AI and original; do not change the lower original frame at all except natural motion from the source clip; no surreal lighting, extra people, extra laptops, bent table edges, or melting architecture; avoid jittery transitions, logo clutter, artifacting, blurred facial features, or unnatural eye direction.