How to Make Clay Animation with Veo 3 (Step-by-Step Guide)

Have you ever watched a clay animation or stop-motion video and thought, “Wow, that looks amazing, but it must be super complicated to make”? Well, I’ve got some good news for you—it’s actually way easier than you think. Thanks to the power of AI tools like Veo 3, you don’t need to spend hours moving tiny clay figures frame by frame anymore. Instead, you can create fun, quirky, and professional-looking clay animation videos in just a few steps.

What makes this even cooler is that you don’t have to be a professional animator. If you can copy, paste, and follow simple steps, you’re already halfway there. The magic really happens with the prompt, because that’s where you tell the AI exactly what you want your clay stop motion animation to look like. Think of it as giving directions to a super talented clay artist who never gets tired.

In this clay animation tutorial, I’ll walk you through the entire process—from preparing your prompt to generating the image and finally turning it into a short video with Google Veo 3. And trust me, once you try it, you’ll want to keep experimenting with different characters, scenes, and creative ideas. Whether you want a clay cat skateboarding, a penguin cooking noodles, or astronauts planting a flag on the moon, you can make it happen with just a few clicks.

So, grab a cup of coffee, get comfortable, and let’s dive into the world of AI stop motion. By the end of this Mangidik guide, you’ll know exactly how to create your own clay-style animations using ChatGPT prompts, Google Whisk (for images), and Google Gemini with Veo 3.

Step 1: Preparing the Prompt

Whenever we talk about AI, the word prompt always comes up. A prompt is basically the set of instructions you give the AI so it knows what to create. The clearer and more detailed your prompt is, the better the result will be. The good news? You don’t have to build it from scratch. I’ve already prepared a ready-to-use ChatGPT clay animation prompt that’s specifically designed for stop motion videos.

Here’s the exact prompt you’ll need:

I want you to act as a prompt creator for clay animation in two stages:

• Text-to-Image Prompt

Create a prompt to generate a clay animation image (stop-motion style) based on the following input:

• Main character: [fill here]

• Short description of the scene: [fill here]

Describe in detail: character shape, clay/plasticine texture, facial expression, clothing (if any), scene environment, lighting, and atmosphere.

• Image-to-Video Prompt (Veo 3)

Once the text-to-image is complete, create a prompt for Google Veo 3 using the image as a reference.

Add the following details:

• Camera movements (e.g., close-up, dolly, pan, tilt)

• Sound effects (e.g., clay footsteps, water splash, funny squish)

• Simple conversation/dialogue that fits the mood

• Typical clay animation stop-motion transitions

• Lighting and atmosphere (warm, bright, dramatic, etc.)

• 10–15 seconds duration

Output Format:

Always provide the final output in two separate code blocks for easy copying.

It may look long, but it’s super easy to use. You only need to fill in two things:

1. Main character – The star of your clay animation. The more details, the better. For example: a fluffy orange cat wearing sunglasses and a gold chain.
2. Short description of the scene – What you want your character to do. Keep it short and clear, like skateboarding in a park or cooking pancakes in the kitchen.

Once you’ve filled those in:

1. Copy the entire prompt.
2. Open ChatGPT.
3. Paste the prompt and hit Send.
4. ChatGPT will then generate two ready-made prompts: one for text-to-image and another for image-to-video with Veo 3.

This is the foundation of the whole process and a big reason why making AI clay animation is so simple today.

Step 2: Generate the Image

Now that you have your text-to-image prompt, it’s time to bring your clay character to life in picture form. For this, you can use Google Whisk or any other image-generation tool you like.

Here’s how to do it:

1. Open Google Whisk (or your preferred AI image generator).
2. Paste the text-to-image prompt you got from ChatGPT.
3. Hit Send.
4. Wait for the AI to generate several clay-style images.
5. Pick the one that looks best and download it.

This image will act as the base for your video. Think of it as the starting frame of your clay stop motion animation. Only now, instead of sculpting real clay and moving it frame by frame, the AI instantly creates a clay-style character that looks like it came straight out of a handmade animation.

Pro tip: If you don’t like the first result, don’t panic. Just tweak your clay animation prompt or regenerate until you’re happy. That’s the beauty of working with AI—you can experiment endlessly without wasting hours.

Step 3: Generate the Video

This is the part where the magic happens. Now you’ll turn your clay image into a moving animation using Google Gemini and the Veo 3 video generator.

Here’s the process:

1. Open Google Gemini.
2. Select Videos with Veo.
3. Upload the clay image you downloaded earlier.
4. Copy the image-to-video prompt from ChatGPT.
5. Paste it into the chat box and hit Send.
6. Wait a few minutes while Veo 3 stop motion AI brings your clay character to life.
7. Download your finished clay animation video.

The result? A short but super charming AI stop motion clip with smooth camera movements, sound effects, and even dialogue if you requested it. It’s like creating your own mini-movie without touching a single piece of clay.

Video Tutorial

If you prefer watching the process step by step, check out this video guide:

It shows the entire workflow in action—perfect for visual learners who want to follow along while making their own clay stop motion with Veo 3.

Conclusion

Clay animation has always been one of the most creative and fun forms of storytelling. The only problem? Traditional clay stop-motion takes a lot of time, patience, and equipment. But now, with AI animation tools like Veo 3, ChatGPT, and Google Gemini, that barrier is gone.

Here’s the quick recap:

1. Write your clay animation prompt with ChatGPT.
2. Generate your clay-style image with Google Whisk.
3. Animate it into a video with Veo 3 stop motion.

In less than an hour, you can go from idea to finished animation. Whether you want to post on YouTube, share on TikTok, or just have fun experimenting, this workflow makes clay animation for beginners easier than ever.

So, why wait? Open ChatGPT, prepare your prompt, and start creating. Your next clay character might just be the star of a viral video.