How to Create Exploding Food Infographic Videos with Veo 3 and Nano Banana?

Step-by-step guide to making those satisfying ingredient breakdown animations

You’ve probably seen these videos before:

These are often called exploded-view food videos, ingredient breakdown videos, or food infographic animations.

They’re perfect for:

• Restaurants & menus

• TikTok & Reels

• YouTube Shorts

• Ads

• Educational food content

In this tutorial, I’ll show you how to create these videos using Veo 3 and mitte.ai, step by step.

We’ll build this exact type of video:
A realistic burger → exploding into its components → labeled → animated smoothly.

Let’s begin.

---

Step 1: Create the Base Image (Your First Frame)

The most important part of any Veo 3 video is the first frame.

If your first frame looks professional, your final video will look professional.

We’ll generate this image inside mitte.ai.

Settings

• Model: Nano Banana Pro

• Aspect Ratio: 2:3 (important—use this for all images)

• Background: Clean and simple

Prompt

Make an image of a realistic burger that looks like it came from a high-end restaurant. 
Use a plain white background. 
Soft studio lighting. 
Sharp focus. 
High detail. 
Professional food photography style.

This image will become the starting point of your animation.

---

Step 2 (Optional): Clean the Scene

If your burger image contains:

• A plate

• Fries

• Sauce splashes

• Unwanted props

You can remove them by editing the image with Nano Banana Pro on mitte.ai:

Prompt:

remove the plate, fries and sauce, center the burger

Why this matters:

Exploded-view videos look best when:

• The background is clean

• The main object is isolated

• There are no distractions

This makes the animation more readable and professional.

---

Step 3: Create the Exploded Ingredients Image

Now we generate the final frame of the video:
The burger separated into layers, floating, with labels.

This is what Veo 3 will animate toward.

Prompt

Make an image of a burger exploded into its individual components. 
Each ingredient should float above the next in correct order. 
Add a text label for each ingredient. 
Match the label color to the ingredient color. 
Clean white background. 
Minimalist infographic style. 
High detail. 
Professional food illustration look.

You should now have:

✔ Image 1: Full burger
✔ Image 2: Exploded ingredient layout with labels

These two images will define your entire video.

---

Step 4: Animate with Veo 3 (Image → Video)

Now the magic happens.

Go to mitte.ai and select:

Model: Veo 3 (Image → Video)

Upload

• First Frame: The full burger image

• Last Frame: The exploded ingredients image

Settings

• Length: 4 seconds

• Aspect Ratio: 9:16 (for TikTok, Shorts, Reels)

• Speed: Fast or Normal

• Style: Clean, smooth

Prompt

Smooth cinematic transition from a complete burger into an exploded ingredient view. 
Each layer gently separates and floats upward. 
Soft, natural motion. 
No shaking. 
No distortion. 
No flickering.

Negative Prompt (Important!)

blurry, shaky, distorted layers, unreadable text, messy motion, bad lighting

Click the blue generate button.

---

Why This Workflow Works

Most people try to describe everything in one text prompt.

That doesn’t work well.

Professionals use structure:

1. Control the first frame

2. Control the final frame

3. Let Veo animate the transformation

This gives you:

• Predictable results

• Cleaner motion

• Professional composition

• Fewer failed generations

This is why mitte.ai is perfect for this workflow—you can generate, edit, and animate everything in one place.

---

Final Result

After following these steps, here’s our final video:

You can see:

• Clean animation

• Smooth separation

• Clear labels

• Professional look

This is exactly the type of content brands, restaurants, and creators love.

---

Pro Tips

Keep it Short

Exploded-view videos work best between 3–6 seconds.

Use White or Neutral Backgrounds

This makes the labels easier to read and the motion clearer.

Use Color-Matched Text

Matching text color to ingredient color makes the video more intuitive.

Always Use Image → Video

Never rely on text-only prompting for these styles.

---

Why I Recommend mitte.ai for This

mitte.ai makes this workflow simple:

✔ Multiple image models
✔ Advanced editor
✔ Clean UI
✔ Precise control
✔ Image → Video pipeline
✔ Professional results

You don’t need to jump between five tools.

Everything happens in one place.

Want More Tutorials Like This?

In the next posts, I’ll show you how to make:

• Exploding drink videos

• Skincare ingredient breakdowns

• Tech product breakdowns

• Assembly-style animations

• Menu animations

If you want those, subscribe and stay tuned.

Now go create something delicious 🍔✨