The Motu Patlu AI photo is a still image of you redrawn as a bright 3D cartoon in a colourful small town. You upload one photo, pick one of three scenes and get a vertical 2:3 picture back in about a minute.
People also search it as Motu Patlu AI photo editing, Motu Patlu AI prompt or Motu Patlu ke sath photo. This guide goes deeper than the page FAQ, covering the copyright line, the source photo, the three scenes, failures, posting and what not to make.
Key takeaways
- The result is one silent 2:3 still image made from a single photo of you, not a video.
- videosi does not draw Motu, Patlu or any other show character. Only you appear, as an original 3D cartoon.
- Pick from three scenes: town lane, samosa and chai stall, or village road.
- Use a sharp, evenly lit photo of one adult. Photos of children are not allowed.
- Each image is 1 credit, and packs start at $8.90 for 10 credits.
In this guide
- Where does the Motu Patlu AI photo look come from?
- Why won't the real characters appear in my picture?
- Which of the three scenes should I pick?
- What kind of source photo works best?
- Why does the cartoon not look like me?
- Why are there no shop names or signboards?
- Should I use ChatGPT or Gemini myself, or videosi?
- How do I post it and move it into a reel?
- What does it cost, and what should I not make?
Where does the Motu Patlu AI photo look come from?
The look borrows from Motu Patlu, an Indian animated series about two friends in the fictional town of Furfuri Nagar. According to Wikipedia's Motu Patlu article, the show first aired on Nickelodeon India on 16 October 2012, and the town has a market, a police station and neighbouring cities. That busy, colourful small-town world is what the photo trend imitates.
The AI edit itself is much newer. The earliest dated photo tutorials we found are from 9 June 2026, usually YouTube videos pointing at Instagram reels. A bigger Motu Patlu AI video wave followed on Instagram Reels and YouTube Shorts, and one Hindi video tutorial posted on 9 July 2026 had about 431,000 views when we looked. Our trend radar picked up the photo version as an emerging search on 6 November 2026.
No single original creator is known, and the posts use many different sounds. That matters for you: there is no required track and no official template to follow.
Why won't the real characters appear in my picture?
Motu, Patlu and the other characters belong to the show's owners. Many tutorials ask the AI to put them next to you, as a selfie, an arrest scene or a welcome signboard. That copies the show's artwork, and image models can refuse or block such requests.
The videosi Motu Patlu AI photo takes a different route. It turns only you into an original 3D cartoon and places you in the same kind of small-town world. The setup tells the model not to add any other cartoon character, mascot or lookalike, and to keep the foreground to you alone.
This is a practical choice as well as a legal one. A cartoon of you is far less likely to be flagged, while a copied show character can get a post taken down. If you want the show's look without the risk, the original-character route is the safer one.
Which of the three scenes should I pick?
All three scenes cost the same, so the choice is about mood and about how much of your photo they use.
The cartoon town lane is the classic. You stand full length in a busy lane with pastel two-storey houses, small balconies, striped shop awnings and a parked scooter, waving with a big grin. It suits a cheerful intro post or a profile story.
The samosa and chai stall is the funniest and the most personal. It is a half-length shot of you at a roadside snack stall, holding a plate of golden samosas in one hand and a small glass of chai in the other, laughing. Behind you are a big wok, a steaming kettle and hanging snack packets with no writing. It crops well for food, tea or birthday captions.
The village road is the calmest. You stand with hands on hips on a dusty road between green fields and palm trees, with a blank green road sign and a small bullock cart far behind. It has the most open sky, so it works well as a wide, airy post.
Since credits are per image, a good first session is one photo run through all three scenes. Then post the one that looks most like you.
What kind of source photo works best?
Use a sharp, front-facing photo where your face is clearly visible and the light is even. Daylight or open shade keeps skin tone and features right, and heavy filters get copied into the cartoon.
Match the framing to the scene. The town lane and the village road show your whole body, so a full-length photo works best there. If your photo stops at the chest, the model has to invent your trousers and shoes. The chai stall is a half-length shot, so a head and shoulders photo is fine.
Plain, bright clothes carry over better than small prints or logos. Very dark photos lose skin tone and hair colour once they are cartoonised. Keep one person in the frame, and crop a group picture before you upload it.
Keep any head covering you normally wear. The setup tells the model to keep a hijab or a turban, so you do not need to remove it for the photo.
Why does the cartoon not look like me?
A cartoon changes proportions on purpose. The head gets slightly larger, the eyes get bigger and the skin gets smooth shading. So some difference is the style, not a fault.
A real miss usually has one of two causes. The first is a source photo that is small, dark or filtered, which gives the model too little to read. The second is a tool that never locked your identity. Prompts that only say make me Motu Patlu style often return a generic cartoon face, because nothing says to keep your face shape, hair, glasses and build.
Here your photo is the only source for the face, hair, facial hair, glasses and clothes, and the setup says not to slim, beautify, whiten or age you. Likeness is still never guaranteed. If the first result is off, retake the photo closer and in better light, then generate again. Each run is a fresh draw, and a failed or blocked generation returns its credit automatically.
Why are there no shop names or signboards?
You may have seen tutorial results with a big welcome signboard in Hindi or English. Those are the part that most often goes wrong. Image models tend to turn shop names and signs into garbled letters, and a sign that reads wrong ruins an otherwise good picture.
The three scenes here keep every sign blank. The snack packets have no writing, the road sign is plain green and the shop awnings are just striped. The setup also bans text, logos, watermarks and borders.
If you want words on the picture, add them yourself afterwards in any photo editor or in your reel app. That keeps the spelling right and lets you use your own town or your own name.
Should I use ChatGPT or Gemini myself, or videosi?
Doing it yourself is a fair way to learn the look, and it is how the trend spread. The usual recipe is to upload a selfie to an AI image editor and paste a long prompt. Google's own help page explains how to upload your own images to edit in Gemini.
The trade-off is repeatability. Pasted prompts tend to drift into a generic cartoon face, add the show's characters or draw garbled signs. You also have to find, paste and tweak the prompt each time.
The videosi page runs OpenAI's GPT Image 2.6 with the identity lock, scene, look, original-character rule and safety rules already written. You upload one photo, pick a scene and press Generate, so there is no prompt to paste. The full prompt is not published.
How do I post it and move it into a reel?
The result is a still vertical 2:3 image with no sound. Post it as a photo or a carousel slide, use it as a profile picture, or drop it into a reel as one slide with your own audio. The trend has no confirmed sound, so any track you have the right to use works.
The profile circle will crop a 2:3 image, so check that your face survives the crop before you set it. The chai stall is the easiest to crop to a face, because it is already a half-length shot.
It is not a video, and the page does not turn it into one. The video side of the trend, such as village vlogs and shop promotions, is made with video models. If you want motion, add the image to a slideshow in your reel app.
It is also good manners to say the picture is AI-made. A short caption such as made with AI is enough for readers and protects you if a platform adds its own label.
What does it cost, and what should I not make?
Each image is 1 credit, and packs start at $8.90 for 10 credits, with local prices lower in some countries. Credits never expire, there is no free tier, and a failed or blocked generation returns its credit.
Keep it to yourself and to adults who agreed. The show is a kids' cartoon, but photos of children are not allowed, and the setup tells the model not to generate an image if the photo shows a child. The scenes are built for one adult per image. For a friend or partner, crop the photo and make a second image for each person.
Do not upload someone else's photo without their consent, and do not use the picture to mock or impersonate a real person. A cartoon of a real face is still that person's face.
Ready to try it? Open the Motu Patlu AI photo page, upload one clear photo and pick a scene. Start with all three scenes from the same photo and keep the one that looks most like you.



