Reference image
Quality
Resolution
Duration
Native audio
Description
Animate the attached creator-and-product image into a single photorealistic, natural UGC advertising video. The attached image is the primary visual reference. Preserve everything established in the source image and animate it naturally rather than redesigning or recreating the scene. CORE INSTRUCTION Identify the exact product, creator/model, environment, clothing, composition, and visual context shown in the reference image. The video's actions, dialogue, body language, camera behavior, and overall performance should be contextually appropriate to the specific product, creator/model, environment, and intended advertising scenario shown in the image. Do not assume a specific product category, gender, age, action, voice, or script. The animation should feel like a natural continuation of the original image. CREATOR / MODEL PRESERVATION Preserve the creator/model's exact: Identity Facial features Face shape Skin tone Hairstyle Hair color Body type and physique Age appearance Clothing Accessories Overall appearance Do not change the creator into a different person. Do not alter their facial structure, hairstyle, skin tone, body proportions, clothing, or recognizable characteristics. Maintain strong identity consistency throughout the entire video. PRODUCT PRESERVATION Preserve the exact product shown in the reference image. Maintain its: Shape Size Packaging Label Branding Colors Typography Logos Proportions Materials Physical structure All visible product details The product must remain visually consistent throughout the animation. Do not redesign, morph, distort, replace, duplicate, or unintentionally alter the product. If the creator interacts with the product, maintain realistic physical contact, grip, scale, orientation, and movement. ACTION & PERFORMANCE The creator's actions must naturally match the type of product and advertising scenario shown in the reference image. Do not use a predetermined action. Instead, create a believable sequence in which the creator naturally: Introduces the product Presents or demonstrates it Talks about it Recommends it Uses or interacts with it only when appropriate to the specific product and scene. The action should progress naturally from the creator's starting pose in the reference image. If the product is something that can be consumed, the creator may naturally demonstrate or consume it when appropriate. If it is a beauty or personal-care product, the creator may naturally demonstrate or discuss its use when appropriate. If it is clothing, fashion, technology, food, fitness, lifestyle, or another category, the interaction should adapt accordingly. Do not introduce an action that would be unnatural or physically inappropriate for the product. Keep movements subtle, believable, and physically achievable. TIMELINE & NATURAL PROGRESSION Create a smooth conversational sequence rather than rigidly forcing identical actions at specific timestamps. Beginning: The creator naturally acknowledges the camera and begins communicating with the viewer. Use subtle facial movement, natural blinking, realistic breathing, and an expression appropriate to the product and message. Middle: The creator naturally gestures, interacts with, demonstrates, or presents the product according to the scenario. Their gestures should support what they are saying rather than appearing randomly generated. Allow natural eye movement between the camera, the product, and relevant parts of the environment. Ending: The creator naturally completes their recommendation, demonstration, or product interaction. Finish with a believable expression and body position rather than a frozen commercial pose. The exact actions should be determined by the product and scenario rather than by a fixed sequence. BODY LANGUAGE Use authentic conversational body language: Natural hand gestures Subtle head movement Natural blinking Realistic breathing Small posture adjustments Natural facial expressions Appropriate eye contact Realistic arm and hand movement Subtle shifts in body position Gestures should correspond naturally to the creator's speech and actions. Avoid repetitive, exaggerated, robotic, or overly theatrical movements. VOICE & DIALOGUE Generate a natural voice that is appropriate for the creator/model shown in the reference image. The voice should match the creator's apparent: Gender presentation Age range Personality Energy Overall character Use a natural conversational delivery appropriate for UGC content. The voice should feel: Authentic Warm Clear Confident Relatable Conversational Appropriate to the product Appropriate to the creator Avoid an announcer voice, radio-commercial delivery, exaggerated enthusiasm, or overly polished advertising narration. VOICEOVER / SCRIPT Create a short, natural spoken script that is specifically relevant to the exact product shown in the image. The dialogue should sound like something the creator would genuinely say in a casual product recommendation or demonstration. The script should: Naturally introduce or reference the product Communicate a believable product-related benefit, experience, feature, or reason for recommending it Match the creator's personality and apparent audience Match the environment and scenario Sound conversational rather than scripted Fit naturally within the video's duration Do not invent highly specific product claims that cannot reasonably be inferred from the visible product or provided context. Do not mention a different product, brand, or category. The spoken dialogue must be fully synchronized with the creator's mouth movements. FACIAL PERFORMANCE Facial expressions should naturally correspond to the meaning of the dialogue. For example: Curiosity or concern when introducing a problem Interest when discussing the product Confidence when explaining a benefit Genuine enthusiasm when recommending it Satisfaction when appropriate to the product interaction Avoid exaggerated reactions. Expressions should remain subtle, believable, and consistent with the creator's established appearance. CAMERA Use a realistic smartphone-style UGC camera. The camera should feel as though the creator is being casually recorded for social media rather than filmed for a traditional television commercial. Use: Subtle handheld movement Very mild natural camera motion Realistic smartphone perspective Natural framing Appropriate medium or medium-close-up composition Realistic autofocus behavior Subtle focus adjustments when appropriate Natural depth of field The camera may make very subtle movements or framing adjustments to follow the creator or product, but it must never become distracting. Preserve the composition and perspective established in the reference image unless a small camera movement is necessary to naturally support the action. LIGHTING Preserve the lighting style and overall visual atmosphere established in the reference image. Lighting should remain: Natural Physically consistent Realistic Appropriate to the environment Consistent across the entire shot Allow subtle natural changes caused by movement, but do not introduce dramatic lighting changes. Do not add artificial beauty lighting or cinematic effects that were not present in the original scene. Maintain realistic skin highlights, shadows, reflections, and exposure. ENVIRONMENT Preserve the original environment shown in the reference image. Background elements should remain stable and consistent. Allow only subtle, physically believable environmental movement when appropriate. Do not introduce unnecessary objects, people, decorations, text, or environmental changes. The environment should remain secondary to the creator and product. REALISM & PHYSICAL CONSISTENCY Maintain realistic: Anatomy Hands Fingers Facial movement Eye movement Hair movement Clothing movement Product physics Object interaction Shadows Reflections Depth Perspective Hands must remain anatomically correct throughout the animation. The creator's body proportions must remain stable. The product must maintain consistent size, shape, branding, and orientation. No object should unexpectedly appear, disappear, duplicate, or transform. LIP SYNC Lip movements must naturally synchronize with every spoken word. Mouth shapes should correspond realistically to the generated dialogue. Facial expressions, eye movements, gestures, and head movements should all support the meaning and timing of the spoken words. Avoid unnatural mouth movement, delayed lip sync, frozen expressions, or excessive facial animation. UGC STYLE The final result should look like an authentic creator-generated social media advertisement. It should feel: Real → Natural → Personal → Relatable → Product-focused rather than: Overproduced → Cinematic → Artificial → Corporate → AI-generated Maintain subtle imperfections associated with real smartphone UGC while keeping the final result commercially usable. EDIBLE PRODUCT INTERACTION — IMPORTANT If the product shown in the reference image is edible or consumable, including beverages, food, snacks, supplements, confectionery, or any other product intended to be consumed, the creator must follow natural human eating and drinking behavior. The creator must NOT speak while the product is inside their mouth or while they are actively chewing, swallowing, or drinking. When consuming the product: The creator naturally brings the product to their mouth. They consume the product realistically. Their mouth remains naturally occupied while consuming it. No spoken dialogue occurs during the actual consumption. After the product has been removed from their mouth and they have naturally finished chewing, swallowing, or drinking, allow a brief natural pause. Before beginning to speak again, the creator should produce a subtle, natural human satisfaction sound or expressive reaction appropriate to the product. The satisfaction reaction should communicate the natural sensory response appropriate to what was consumed. For example: A refreshing drink may produce a subtle "ahh", satisfied exhale, or refreshed breath. A delicious food or snack may produce a subtle satisfied hum, appreciative exhale, or quiet "mmm". A pleasant-tasting product may produce a small natural expression of enjoyment. A refreshing or energizing product may produce a subtle satisfied breath or appreciative reaction. The sound must feel spontaneous and human, not exaggerated, theatrical, cartoonish, or artificially inserted. The creator's facial expression should also naturally reinforce the reaction — for example, a small smile, satisfied look, subtle nod, refreshed expression, or moment of genuine enjoyment. Only after the consumption has completely finished and the satisfaction reaction has naturally occurred should the creator resume speaking. The transition from consuming → satisfaction reaction → speaking should feel seamless and physically believable. Do not make the creator immediately start speaking with food or liquid still in their mouth. Do not make the creator chew while talking. Do not make the creator speak while swallowing. Do not create unnatural or exaggerated eating/drinking sounds. Do not overemphasize chewing, swallowing, lip smacking, or mouth sounds. Keep all consumption sounds subtle, realistic, and appropriate for a natural UGC advertisement. For non-edible products, this rule does not apply; the creator's interaction and dialogue should instead adapt naturally to the specific product and scenario. IMPORTANT RESTRICTIONS Do not redesign the product. Do not change the creator/model's identity. Do not change the creator's appearance. Do not change the product's branding or packaging. Do not introduce unrelated actions. Do not introduce unrelated objects. Do not use a generic script. Do not use a generic voice that conflicts with the creator. Do not force an action that does not make sense for the product. Do not add unsupported product claims. Do not add subtitles. Do not add captions. Do not add watermarks. Do not add additional logos. Do not use beauty filters. Do not use exaggerated cinematic effects. Do not make the animation look obviously AI-generated. FINAL OBJECTIVE Create a believable continuation of the attached image in which the exact creator naturally communicates about, recommends, demonstrates, or interacts with the exact product shown in the reference image. Every aspect of the video — action, dialogue, voice, gestures, facial expressions, camera movement, lighting, and pacing — should automatically adapt to the specific creator, product, environment, and advertising scenario visible in the reference image. The final result should look like a real person naturally creating a high-quality UGC product advertisement for social media.
