Explore. Create. Go viral.

GLOBAL LOCK: 9:16 vertical tutorial Reel, same young adult white male presenter with short brown hair explains an image-to-video toolkit workflow from a dark home-studio setup with a front microphone and warm practical lighting. The visual examples alternate between original talking-head footage, backyard phone clips, and transformed AI outputs: molten fire-skinned humanoid, metallic mask or robot-faced desert character, tuxedo pianist in a library, Joker-style clown portrait with flames, cowboy gunfighter in a dry field, and disaster-scene full-body walk. Keep a strong before-and-after structure with original footage clearly contrasted against stylized generated results, while the presenter remains the instructional anchor.

00:00-00:06
Open with stacked original-versus-AI comparisons of the presenter in a studio, where the top frame shows the original gray-sweater talking head and the bottom frame shows radical AI reinterpretations: a molten lava humanoid glowing orange, a metallic or armored face under desert light, and other cinematic variants, labels clearly distinguish ORIGINAL from AI, pacing is immediate and conversion-focused.

00:06-00:12
Continue with more direct-to-camera transformations, then briefly introduce another talking-head speaker clip and cut to backyard phone footage of a young man seated at an outdoor table, showing that the workflow is not limited to studio recordings, but can start from casual everyday source material.

00:12-00:18
Show the backyard footage evolve into a tuxedo pianist in a warm library or salon setting, the same seated body posture transformed into a cinematic piano performance, then return to the presenter who explains the completion of the first workflow segment, preserving a sharp contrast between raw source and stylized output.

00:18-00:24
Introduce a second character transformation set: the presenter in a dark shirt becomes a Joker-inspired clown with white face paint and red smile, flames burning behind him, the video cycles through labels such as character, movement, emotion, and lighting, framing the process as controllable image-to-video direction rather than random style filters.

00:24-00:30
Display title cards announcing how to get started, then move into the actual toolkit screens: image-to-video menus, generation options, upload slots, and model selections, the presenter points upward and counts steps, keeping a fast but teachable rhythm.

00:30-00:36
Show specific tool states and model cards using the same backyard subject, now transformed into a cowboy with a revolver in a dry outdoor landscape, the interface indicates different model variants and generation paths, highlighting how the toolkit turns still or simple footage into genre scenes.

00:36-00:39
Finish with a final before-and-after comparison of a man walking in a smoky disaster zone above and the ordinary backyard source below, on-screen text asks viewers to comment “AI,” ending the reel as a clear tutorial funnel for the toolkit.

NEGATIVE PROMPT: weak before-after distinction, face drift between original and transformed variants, broken lava texture, warped metallic helmet, unnatural clown makeup, bad piano hand anatomy, inconsistent tuxedo, broken revolver, blurry UI cards, unreadable model names, bad backyard geometry, fake smoke, wrong body proportions, duplicate people, poor lip-sync on presenter, overexposed highlights, muddy flames, random style mixing.

SHOT PROMPTS:
1. Original vs AI stacked comparison for talking-head transformation.
2. Molten lava humanoid close-up built from same presenter framing.
3. Metallic desert-face reinterpretation with glowing reflections.
4. Backyard source clip at outdoor table.
5. Tuxedo pianist transformation in warm library setting.
6. Joker-style portrait with flames and expressive clown makeup.
7. Image-to-video toolkit interface with model selection.
8. Cowboy gunfighter transformation from backyard subject.
9. Final disaster-zone before-and-after with comment-AI CTA.

SPEECH PACK:
Single male presenter voice, fast tutorial cadence, close-mic studio sound, energetic but clear. Core meaning across the reel: here is original footage, here is what AI can turn it into, here is another example from casual backyard source material, here are controllable parameters like character, movement, emotion, and lighting, here is the image-to-video toolkit, here are model choices, and comment AI if you want the workflow. Lips are visible and should sync tightly to emphasized instructional beats and CTA moments.