On short-form video platforms like TikTok, food and beverage ads that rely on pushy sales pitches and oversaturated, overly polished filters are often swiped away instantly. This ad by traditional Spanish food brand TORTAS DE ACEITE INÉS ROSALES takes the opposite approach. Instead of listing product features, it builds a high-quality, slow-living atmosphere for its new product, "Mary Trini Select Leaves" (puff pastry), using a cozy afternoon tea scene and first-person point-of-view (POV) camera work.

In this case study, we will break down the creative logic behind this trending TikTok ad, provide steps to replicate it using AI video generators, and show you how to write precise prompts to recreate this warm, organic aesthetic.

1. Case Overview & Visual Style
2. Why This Ad Works on TikTok
3. Video Script Structure & Emotional Curve
4. Deep Dive into AI Video Prompts
5. How to Replicate & Extend This Concept
6. FAQ: Generating Food Ads with AI

Case Overview & Visual Style

Rather than focusing on static packaging, this ad showcases a "relaxing afternoon ritual." The visuals feature soft, natural sunlight and warm tones. The setting is a cozy dining table draped in a cream-white cotton linen tablecloth, decorated with a few scattered nuts and utensils to give it a natural, lived-in feel.

https://github.com/user-attachments/assets/066d9237-7fcf-49b8-b80c-cf1c834ee868

The video has no text overlays or watermarks. Instead, it guides the viewer's attention solely through upbeat xylophone and percussion music mixed with the satisfying ambient sound (ASMR) of coffee being poured.

• Advertiser: TORTAS DE ACEITE INÉS ROSALES
• Product: Hojitas selectas Mary Trini (puff pastries)
• Key Setting: Minimalist, cozy home afternoon tea
• Video Style: UGC style, low commercial feel, first-person perspective (POV)

Why This Ad Works on TikTok

For brands in the food and beverage industry, this ad works because it aligns perfectly with how users consume content on social media:

1. Soft Selling: By using a first-person perspective, the video feels less like an ad and more like a creator sharing their afternoon routine. The white-and-gold product packaging stacked in the background blends naturally into the scene, providing brand exposure without triggering ad fatigue.
2. ASMR to Trigger Appetite: Instead of using voiceover narration, the ad amplifies the sound of hot black coffee being poured from an octagonal Moka pot into a ceramic cup. This sound design (ASMR) stimulates the senses, helping viewers associate the visuals with the aroma of coffee and the crisp texture of the pastries.
3. Aesthetics & Emotional Value: The cream tablecloth, warm wood tones, and soft angled sunlight create a comforting atmosphere. This "wabi-sabi" style appeals to younger consumers who value wellness and aesthetics, offering them a moment of relaxation.

Video Script Structure & Emotional Curve

Though only a few seconds long, the video has a tight pace and a clear narrative progression:

Deep Dive into AI Video Prompts

To recreate this realistic, organic style using AI video generators (such as Sora, Kling, or Luma), you need to describe perspectives, materials, lighting, and camera movement in detail.

Here is a prompt template based on this case study:

AI Prompt Template (Copy & Customize)

Prompt Description: A mobile phone POV, first-person perspective video of a cozy afternoon tea time. Natural warm sunlight streaming in from the side, casting soft shadows. The setting is a cozy wooden dining table covered with a cream-white cotton linen tablecloth.

Shot 1: A close-up shot of a hand gently placing a vintage glass plate filled with chocolate and cream-filled puff pastries onto the center of the table. In the background, three minimalist white-and-gold snack bags are neatly stacked out of focus.

Shot 2: Smooth camera glide pushing in to focus on the product packages, elegant retro cursive logo on the packaging. The puff pastries in the foreground glass plate are captured in sharp detail with a shallow depth of field.

Shot 3: A close-up shot panning slightly to the right, showing a silver metal octagonal Moka pot slowly pouring hot black coffee into a clean white ceramic cup. Steam gently rising from the coffee, warm and inviting atmosphere.

Shot 4: A slow crane shot, rising up to a top-down flat lay view, showing the entire warm table setting with the coffee cup, the plate of pastries, scattered almonds, and the package bags. Seamless transition, hyper-realistic, 4k resolution, organic feel, no AI-generated artifacts.

Key Prompt Elements to Note:

• Camera Movement: Using terms like POV (first-person perspective), Smooth camera glide, and Slow crane shot helps the AI generate movements that look like they were filmed by a human rather than a robotic camera.
• Lighting & Color: Prompts like Natural warm sunlight and soft shadows prevent the harsh, artificial look of studio lighting, making the scene feel more authentic.
• Materials & Textures: Specifying details like cotton linen tablecloth, vintage glass plate, and silver metal octagonal Moka pot helps the AI render realistic surfaces and reduces typical AI artifacts.

How to Replicate & Extend This Concept

You can easily adapt this format for other food, tea, or bakery products by following these steps:

1. Swap the Core Product (Keep the Formula)

• Formula: [Cozy/Aesthetic Setting] + [POV Action (Pouring/Cutting)] + [Detailed Product Close-up] = High-Converting Food Content
• Example (Tea Brand):
  • Replace the Moka pot and coffee with: "A transparent glass teapot pouring golden herbal tea into a cup, with the tea bag tag hanging over the rim."
  • Replace the pastries with: "A matcha cake slice on a wooden plate."

2. Enhance the ASMR Sound Design

Sound is critical for engagement in this style of video. Add these sound effects during editing:

• The rustle of opening a paper snack bag.
• The crisp crunch of taking a bite (for cookies or chips).
• The bubbling or pouring sound of water, tea, or coffee.

3. Write Platform-Friendly Copy

Because the video focuses on the mood, the caption should focus on building connection and directing viewers where to buy.

• Original Spanish Caption: "Cada año vuelven... El placer de lo auténtico." (Every year they return... The pleasure of the authentic.)
• English Option: "POV: The sweet afternoon escape you deserve. ☕✨ Found my new favorite pairing."