How to Create a 10-Second AI Video of Talking Vegetables in a Colorful Market
Artificial Intelligence is changing the way creators make entertaining videos. With the right image-to-video prompt, a single picture can be transformed into a short animated story where characters move, talk, smile, laugh, and interact with each other.
In this tutorial, we will show you how to create a 10-second AI video using an image of three funny animated characters in a colorful vegetable market. The image contains a potato character, an eggplant character, and a beautiful female character walking through the market.
The goal is to make all three characters talk happily in English, interact with one another, smile, laugh, and wave at the camera.
This type of AI video can be useful for TikTok, YouTube Shorts, Facebook Reels, Instagram Reels, Blogger content, and other social media platforms.
What Is Image-to-Video AI?
Image-to-video AI is a technology that takes a still image and turns it into a moving video based on a text prompt.
Instead of creating every frame manually, you upload an image and describe the movement you want. The AI then attempts to animate the characters and environment.
For example, if your image contains three characters sitting in a market, you can tell the AI that one character should speak, another should laugh, and another should walk toward them.
Runway's official image-to-video guidance recommends focusing the text prompt mainly on motion, because the uploaded image already provides important information about the composition, subjects, lighting, and visual style. �
Runway +1
You can learn more from the official Runway Image-to-Video Prompting Guide�.
The AI Video Idea
The idea for this video is simple but entertaining.
The scene takes place in a colorful vegetable market. Two funny vegetable characters are sitting together on a wooden bench. One is a potato and the other is an eggplant.
A beautiful female character is walking through the market carrying a shopping bag.
During the 10-second video, the characters become excited and begin talking happily. They look at each other, smile, laugh, and interact with the woman.
At the end, all three characters look toward the camera and wave happily.
The goal is to create a short video that feels like a small animated movie.
Complete 10-Second AI Video Prompt
You can copy the prompt below and use it with an image-to-video AI generator:
Create a joyful 10-second animated video using the uploaded image as the exact visual reference. Keep the three characters, their faces, clothing, body shapes, the colorful Indian vegetable market, shops, vegetables, and background people consistent throughout the video.
The potato character and eggplant character sitting on the wooden bench suddenly become very happy. They look at the beautiful woman walking toward them, smile, laugh, and wave excitedly. The woman smiles back, walks closer, and happily joins their conversation.
All three characters speak in cheerful English with natural facial expressions and accurate lip-sync.
The potato says: “Wow! What a beautiful day at the market!”
The eggplant laughs and says: “Yes! Let’s have some fun together!”
The woman smiles and replies: “Absolutely! This market is amazing!”
They all laugh happily and wave toward the camera at the end. Add subtle natural movement in the market, people walking in the background, gentle movement of clothes and vegetables, warm sunlight, cinematic 3D animation, expressive faces, smooth character motion, natural lip-sync, cheerful atmosphere, high quality, vertical 9:16 format, continuous seamless shot.
How the Prompt Works
The prompt is designed to give the AI a clear sequence of events.
First, it tells the AI to use the uploaded image as the visual reference. This is important because you want the characters and environment to remain recognizable.
Next, it explains what the characters should do. The potato and eggplant become happy, while the woman approaches them.
The prompt then adds dialogue so the characters can appear to speak English.
Finally, it describes the ending: everyone laughs and waves toward the camera.
For image-to-video generation, clear physical actions are generally more useful than vague instructions. Runway recommends describing subject action, environmental motion, camera motion, timing, direction, and speed where necessary. �
Runway
10-Second Timeline
Because the video is only 10 seconds long, it is important not to include too many complicated actions.
Seconds 0–2
The video begins with the potato and eggplant sitting on the wooden bench.
They notice the woman walking through the market.
The potato looks excited and starts smiling.
Seconds 2–4
The potato speaks:
“Wow! What a beautiful day at the market!”
The character should move its mouth naturally while speaking.
The eggplant looks at the potato and reacts with excitement.
Seconds 4–6
The eggplant laughs and says:
“Yes! Let’s have some fun together!”
The woman continues walking closer.
The background market remains active with subtle movement from people and vegetables.
Seconds 6–8
The woman smiles and replies:
“Absolutely! This market is amazing!”
She can make a small hand gesture while talking.
Seconds 8–10
All three characters laugh happily.
They turn toward the camera, smile, and wave.
The video ends with a cheerful atmosphere.
Using a sequence like this can help an AI video model understand the order of events. Runway also describes sequential prompting as a useful technique for controlling the progression of actions. �
Runway
Why Character Consistency Is Important
One of the biggest challenges in AI animation is keeping characters consistent.
When you upload the image, the AI already has information about the characters' appearance. Therefore, the prompt should avoid unnecessarily changing their appearance.
For example, the potato should remain a potato character, the eggplant should remain an eggplant character, and the woman should keep her original clothing and appearance.
This is why the prompt says:
“Keep the three characters, their faces, clothing, body shapes... consistent throughout the video.”
The purpose is to encourage the video generator to preserve the original visual identity.
A high-quality input image is also important. Runway notes that visual artifacts in the starting image can become more noticeable after animation. �
Runway
Making the Characters Talk
Talking characters can make short AI videos much more entertaining.
For this example, each character has a short English sentence.
The dialogue is intentionally short because a 10-second video does not provide enough time for long conversations.
The three lines are:
Potato:
“Wow! What a beautiful day at the market!”
Eggplant:
“Yes! Let’s have some fun together!”
Woman:
“Absolutely! This market is amazing!”
Short dialogue can make it easier to fit the conversation into the available video duration.
If the AI video generator you use does not create accurate spoken audio or lip-sync, you can generate the animation first and add voice-over using a separate video or audio editing application.
Adding Natural Movement
A good AI video should not make every object move excessively.
The characters should make small natural movements such as:
Moving their heads
Blinking
Smiling
Moving their hands
Turning toward each other
Waving
Slightly moving their bodies while speaking
The background can also have subtle movement.
For example, people can walk naturally, clothing can move slightly, and the market can have gentle environmental activity.
The purpose is to make the scene feel alive without making it chaotic.
Camera Movement
For this particular video, a gentle camera movement is better than a very fast camera movement.
A slow camera push-in can make the characters more interesting while keeping them visible.
You can also use a subtle handheld cinematic movement.
Avoid complicated camera movements when the main goal is dialogue because the characters need to remain clearly visible.
Runway's prompting documentation recommends describing camera movement clearly when camera motion is important to the desired result. �
Runway
Choosing the 9:16 Format
For TikTok, YouTube Shorts, Facebook Reels, and Instagram Reels, a vertical format is usually a practical choice.
The prompt therefore includes:
“vertical 9:16 format.”
A 9:16 video fills the screen on most modern smartphones and is suitable for short-form social media content.
Runway's current Gen-4.5 documentation lists 9:16 as a supported image-to-video aspect ratio, along with other formats such as 16:9, 1:1, and 4:3. �
Runway
How to Create the Video
The basic process is simple.
Step 1: Prepare Your Image
Start with the image of the three characters in the vegetable market.
Use the highest-quality version available.
Step 2: Open an AI Video Generator
Upload your image to an image-to-video AI tool.
For example, Runway supports image-to-video generation, where the uploaded image acts as the starting visual frame. �
Runway
Step 3: Add the Prompt
Copy the complete prompt from this article and paste it into the prompt field.
Step 4: Select 10 Seconds
Choose a 10-second duration if the platform provides that option.
Runway's Gen-4 supports 5- and 10-second generations, while its newer Gen-4.5 supports durations from 2 to 10 seconds. �
Runway +1
Step 5: Select 9:16
Choose the vertical 9:16 aspect ratio if your goal is TikTok, Shorts, or Reels.
Step 6: Generate
Start the generation process and wait for the AI to create the video.
Step 7: Review the Result
Watch the entire 10-second video.
Check whether:
The characters remain consistent.
The characters move naturally.
The dialogue is understandable.
The lip-sync looks reasonable.
The woman interacts with the other characters.
The ending shows all three characters happily waving.
If something is wrong, change only the part of the prompt that needs improvement.
Runway recommends an iterative approach: start with the important motion and then add or adjust details as needed. �
Runway +1
Tips for Better Results
Here are some useful tips when creating similar AI videos.
Use a clear image: A sharp image usually gives the AI better visual information.
Keep dialogue short: Long dialogue can be difficult to fit into a 10-second video.
Describe physical actions: Instead of saying “make them exciting,” describe actions such as smiling, waving, laughing, walking, or turning.
Use simple camera movements: A gentle camera push or slow tracking shot can work well.
Keep the characters consistent: Avoid requesting major changes to their clothing or appearance.
Generate multiple versions: AI video generation can produce different results from the same prompt. Try several versions and choose the best one.
Turn One Idea Into a Video Series
You can also use the same characters for a series of short videos.
For example:
Episode 1: The characters meet at the vegetable market.
Episode 2: The potato and eggplant go shopping.
Episode 3: They start a funny vegetable business.
Episode 4: The characters visit a restaurant.
Episode 5: They have a funny conversation with another vegetable character.
Creating a series can help you build recognizable characters and give viewers a reason to return for another video.
Adding the Video to Blogger
After creating your AI video, you can write a Blogger article explaining the prompt and the creation process.
Blogger supports adding both images and videos to blog posts. You can upload an image directly through the Blogger editor, and videos can be uploaded or selected from YouTube. �
Google Help
You can publish the tutorial together with:
The original image
The complete AI prompt
The generated video
Instructions
Tips for other creators
Your website link
You can also add a thumbnail image to make the article more attractive.
Discover More AI Prompts
If you enjoy creating AI characters, talking objects, animated food, funny vegetables, and short cinematic videos, you can find more tutorials and creative ideas on:
Aashado Online – AI Prompts & Tutorials�
The website can be used as a place to share more AI video prompts, tutorials, technology information, and creative content.
Conclusion
Creating a 10-second AI video from a single image can be a fun and powerful way to produce short-form content.
In this example, we transformed a colorful vegetable-market image into an animated story featuring a potato, an eggplant, and a woman. The characters smile, interact, speak English, laugh, and wave toward the camera.
The most important part is writing a clear prompt that explains the desired movement and sequence. For image-to-video generation, the uploaded image already provides much of the visual information, so the text prompt should concentrate on what the characters and camera should do. �
Runway
With practice, you can create many different stories using the same technique. Try different characters, locations, conversations, emotions, and camera movements.
For more AI video prompts, tutorials, and creative ideas, visit www.aashadoonline.com�.
0 Comments