Tutorial Β· how to make a Sheru AI video

How to Make a Sheru Bhai AI Video Sheru Bhai AI video kaise banaye

The same steps the Sheru tutorials on YouTube use, with every Sheru Bhai video prompt ready to copy: write a Hinglish script, make one Sheru character image, animate each scene in Google Flow, keep him consistent, add Hindi dialogue, join the clips and post.

Phone or laptop Β· free Google Flow credits Β· about an hour for a 32-second Short

Skip the typing

The free Sheru Bhai prompt generator writes steps 1–3 for any play and rival.

Open the prompt generator

Before you start

Requirements

  • A Google account (Google Flow; available in India for users 18 and over).[1]
  • ChatGPT or any chatbot for the script (free tier is fine).
  • An image tool for the character: the Gemini app (Nano Banana), Flow's image tool or similar.
  • A video editor: CapCut, InShot, VN or KineMaster (free versions work).
  • About an hour and Google Flow's free daily credits (50 a day, checked 12 Nov 2026; Google may change this).[2]

Step 1

Write the Hinglish script

Paste this into ChatGPT (or any chatbot). Change the story idea in the brackets. You get four scenes, each with a first-frame image prompt, an 8-second video prompt and Hinglish dialogue.

ChatGPT story prompt

You write viral Hindi AI shorts. Write a 4-scene Sheru Bhai story for a 32-second vertical YouTube Short (9:16).

Characters:
SHERU: a tall anthropomorphic white lion man, photoreal 3D fur, thick snow-white mane swept back, pale gold eyes, broad shoulders, human body proportions, wearing a tailored white three-piece suit (white jacket, white waistcoat, crisp white shirt, no tie, gold pocket square), a heavy gold Cuban-link chain on his chest, a large gold wristwatch, a gold ring on the right hand, slim black aviator sunglasses on his eyes
KALA DON: a tall anthropomorphic black panther man, photoreal 3D, sleek jet-black fur, glowing green eyes, wearing a black three-piece suit with a black shirt, a thick silver chain and a silver skull ring, his long black tail curling out behind him

Story idea: [Kala Don bids one arab for a gold supercar at an auction, and Sheru outbids him]

For every scene give me:
1. FIRST FRAME: an English image prompt for the opening picture of the scene, with the full character descriptions.
2. VIDEO: an English prompt for one 8-second clip that only describes movement: one big action, plus at least three other things moving (hands, head, gold chain, camera, crowd). Never tell a character to stand in place or wait.
3. DIALOGUE: at most two short lines in Hinglish (Hindi in Latin letters) in quotes, written as: Sheru says in Hindi: "...".

End the last scene on Sheru's line "Tadpan tadpan... arban kharban gazillion dollar!"
No guns, no blood, no real brands or logos, no children in danger.

Step 2

Make the Sheru character image

Make one picture of Sheru first and reuse it in every scene; that is what keeps the same lion, suit and chain from clip to clip. Use the Gemini app, Flow's image tool or any image generator, in 9:16. Make the rival the same way.

AI-generated image of Sheru Bhai: an anthropomorphic white lion in a white three-piece suit, gold chain, gold watch and black aviator sunglasses, in a marble palace hall
Sheru Bhai Β· the white lion Don

Sheru character image

SHERU: a tall anthropomorphic white lion man, photoreal 3D fur, thick snow-white mane swept back, pale gold eyes, broad shoulders, human body proportions, wearing a tailored white three-piece suit (white jacket, white waistcoat, crisp white shirt, no tie, gold pocket square), a heavy gold Cuban-link chain on his chest, a large gold wristwatch, a gold ring on the right hand, slim black aviator sunglasses on his eyes. Waist-up portrait, facing the camera, confident half-smile, standing in a marble palace hall with crystal chandeliers. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

Kala Don character image

KALA DON: a tall anthropomorphic black panther man, photoreal 3D, sleek jet-black fur, glowing green eyes, wearing a black three-piece suit with a black shirt, a thick silver chain and a silver skull ring, his long black tail curling out behind him. Waist-up portrait, facing the camera, scowling, standing in a dark warehouse lit by red neon. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

Step 3

Generate the clips in Google Flow / Veo

Google Flow is Google's AI filmmaking tool built around its Veo video models.[3] Start a project and, for each scene, use Frames to Video (upload the scene's first frame) or Ingredients to Video (add your Sheru image as a reference), paste the video prompt and generate. From Google's Flow Help Center, last checked 12 Nov 2026 β€” check the official page, Google changes these often:[4]

  • Veo 3.1 Lite makes clips of 4, 6 or 8 seconds; pick 8. Omni Flash 1.2 makes 3–10 seconds (up to 15 with a Google AI plan).[4]
  • Everyone gets 50 free Flow credits a day; Google AI Plus, Pro and Ultra add monthly credits.[2]
  • Extend (continuing a clip) needs a paid Google AI plan; Google retired the old Veo Extend on 5 Nov 2026. On the free tier, make each scene as its own 8-second clip and join them later. Scenebuilder lets you order and trim clips inside Flow.[5]

Here are the four auction-boli scenes, ready to paste:

Auction boli Β· scene 1 of 4 Β· 8 seconds

FIRST FRAME (image, 9:16, use the character image as reference):
A luxurious auction hall with red velvet seats and a gold supercar on a turntable stage; a giant LED bid board shows only rows of glowing gold zeros. KALA DON (a tall anthropomorphic black panther man, photoreal 3D, sleek jet-black fur, glowing green eyes, wearing a black three-piece suit with a black shirt, a thick silver chain and a silver skull ring, his long black tail curling out behind him) sits in the front row with a bidding paddle in his lap; FOX AUCTIONEER (an anthropomorphic red fox man, round gold spectacles, a burgundy tuxedo with a gold bow tie, a wooden gavel) at a podium behind him. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

VIDEO (8 seconds, one continuous take):
Cast: KALA DON (the black panther in the black suit and silver chain); the FOX AUCTIONEER (the red fox in the burgundy tuxedo). One continuous 8-second take with no cuts, medium-full shot at chest height on KALA DON, slow push-in that tilts up as he rises; the main character fills about three quarters of the frame height, faces clearly visible. Light: warm 3200K spotlights from upper left, soft fill on the faces. Pace: the clip opens mid-action and something on screen visibly changes every second, with a new action at least every half second; the longest moment without movement is under half a second. Base motion for all 8 seconds: KALA DON's shoulders bounce, his head bobs to the beat and his free hand slaps his thigh every half second; the panther's long black tail lashes; the crowd behind him sways in their seats. 0–1s: KALA DON springs up from his seat, puffing his chest out. 1–2s: KALA DON swings the paddle high with his right arm, head tipping back. 2–3s: KALA DON rolls his head toward the crowd, smirking, chin up. 3–4s: KALA DON pumps the paddle twice, shoulders bouncing. 4–5s: KALA DON jabs a finger at the bid board, leaning forward. 5–6s: KALA DON throws his shoulders back and shouts his bid, mouth wide. 6–7s: the FOX AUCTIONEER points the gavel at him and leans over the podium, ears up. 7–8s: KALA DON spreads both arms wide and grins, chin up. The clip ends mid-motion. The LED board shows only rows of glowing gold zeros and gold sparks, no letters, no other numbers. At 4–8s Kala Don says in Hindi: "Meri boli... ek arab dollar!" Voices: Kala Don: low, gravelly, sneering male voice. Every line ends before the 8-second mark. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

Auction boli Β· scene 2 of 4 Β· 8 seconds

FIRST FRAME (image, 9:16, use the character image as reference):
The tall gold doors of the auction hall swinging open; SHERU (a tall anthropomorphic white lion man, photoreal 3D fur, thick snow-white mane swept back, pale gold eyes, broad shoulders, human body proportions, wearing a tailored white three-piece suit (white jacket, white waistcoat, crisp white shirt, no tie, gold pocket square), a heavy gold Cuban-link chain on his chest, a large gold wristwatch, a gold ring on the right hand, slim black aviator sunglasses on his eyes) in the doorway with two anthropomorphic tiger bodyguards in black suits; the red-velvet audience turned toward him. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

VIDEO (8 seconds, one continuous take):
Cast: SHERU (the white lion in the white three-piece suit, heavy gold chain and black aviators from the first frame); the TIGER BODYGUARDS (two tigers in black suits). One continuous 8-second take with no cuts, full shot at hip height, the camera tracking backward ahead of Sheru; the main character fills about three quarters of the frame height, faces clearly visible. Light: warm 3200K key light from the open doors at his side, soft fill from the front so his face is lit. Pace: the clip opens mid-action and something on screen visibly changes every second, with a new action at least every half second; the longest moment without movement is under half a second. Base motion for all 8 seconds: SHERU strides every half second, his shoulders roll and his arms swing; his gold chain swings; the TIGER BODYGUARDS march in step beside him. 0–1s: SHERU strides through the doors, arms swinging. 1–2s: SHERU rolls his shoulders on the next step, chin up, sunglasses glinting. 2–3s: SHERU tugs his jacket cuffs with both hands without breaking stride. 3–4s: SHERU rolls his head left, then right, chin up, mid-stride. 4–5s: Every head in the crowd whips around; a peacock lady in a silk sari fans herself with her feathers. 5–6s: SHERU lifts his chin and smirks, shoulders rolling as he walks. 6–7s: SHERU brushes the outer edge of his lapel near the shoulder with two fingers mid-stride, head nodding. 7–8s: SHERU points at the stage with his ringed hand, stepping forward. The clip ends mid-motion. Nobody speaks. Audio: heavy bass hits on each step, crowd gasping, no music. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

Auction boli Β· scene 3 of 4 Β· 8 seconds

FIRST FRAME (image, 9:16, use the character image as reference):
SHERU (a tall anthropomorphic white lion man, photoreal 3D fur, thick snow-white mane swept back, pale gold eyes, broad shoulders, human body proportions, wearing a tailored white three-piece suit (white jacket, white waistcoat, crisp white shirt, no tie, gold pocket square), a heavy gold Cuban-link chain on his chest, a large gold wristwatch, a gold ring on the right hand, slim black aviator sunglasses on his eyes) in the aisle raising one ringed hand toward the stage, the giant LED bid board of gold zeros behind the stage; KALA DON (a tall anthropomorphic black panther man, photoreal 3D, sleek jet-black fur, glowing green eyes, wearing a black three-piece suit with a black shirt, a thick silver chain and a silver skull ring, his long black tail curling out behind him) standing in the front row, turned around toward Sheru, glaring. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

VIDEO (8 seconds, one continuous take):
Cast: SHERU (the white lion in the white three-piece suit, heavy gold chain and black aviators from the first frame); KALA DON (the black panther in the black suit and silver chain). One continuous 8-second take with no cuts, medium shot at chest height on Sheru, quick push-in; the main character fills about three quarters of the frame height, faces clearly visible. Light: warm 3200K spotlight from upper right, soft fill from the front. Pace: the clip opens mid-action and something on screen visibly changes every second, with a new action at least every half second; the longest moment without movement is under half a second. Base motion for all 8 seconds: SHERU's head nods every half second, his shoulders bounce and he rocks his weight from one foot to the other; his gold chain swings; the crowd leans forward row by row. 0–1s: SHERU raises his ringed hand high, eyebrows jumping. 1–2s: SHERU counts on his fingers one after another, head nodding on each count. 2–3s: SHERU wags one finger side to side, shoulders bouncing. 3–4s: SHERU slices the air with his free hand on each word, leaning in. 4–5s: SHERU flicks his raised fingers at the giant LED board like a magician, wrist snapping; the board flares bright gold and bursts into a shower of gold sparks. 5–6s: KALA DON drops his jaw and flattens his ears, the panther's tail lashing. 6–7s: SHERU spreads both arms wide, grinning. 7–8s: SHERU leans back, puffing his chest out, head tipping back in a laugh. The clip ends mid-motion. The LED board shows only rows of glowing gold zeros and gold sparks, no letters, no other numbers. At 2–6s Sheru says in Hindi: "Tadpan tadpan, tadap tadap ke... arban kharban gazillion dollar!" Voices: Sheru: deep, raspy male baritone with Mumbai-style Hindi swagger. Every line ends before the 8-second mark. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

Auction boli Β· scene 4 of 4 Β· 8 seconds

FIRST FRAME (image, 9:16, use the character image as reference):
FOX AUCTIONEER (an anthropomorphic red fox man, round gold spectacles, a burgundy tuxedo with a gold bow tie, a wooden gavel) at the podium with the gavel raised high; KALA DON (a tall anthropomorphic black panther man, photoreal 3D, sleek jet-black fur, glowing green eyes, wearing a black three-piece suit with a black shirt, a thick silver chain and a silver skull ring, his long black tail curling out behind him) sinking low in a red velvet seat; SHERU (a tall anthropomorphic white lion man, photoreal 3D fur, thick snow-white mane swept back, pale gold eyes, broad shoulders, human body proportions, wearing a tailored white three-piece suit (white jacket, white waistcoat, crisp white shirt, no tie, gold pocket square), a heavy gold Cuban-link chain on his chest, a large gold wristwatch, a gold ring on the right hand, slim black aviator sunglasses on his eyes) in the aisle in the foreground spinning a plain gold car key with no emblem on one finger. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

VIDEO (8 seconds, one continuous take):
Cast: SHERU (the white lion in the white three-piece suit, heavy gold chain and black aviators from the first frame); KALA DON (the black panther in the black suit and silver chain); the FOX AUCTIONEER (the red fox in the burgundy tuxedo). One continuous 8-second take with no cuts, medium-full shot at chest height, slow push-in toward Sheru; the main character fills about three quarters of the frame height, faces clearly visible. Light: warm 3200K stage light, gold confetti catching the light. Pace: the clip opens mid-action and something on screen visibly changes every second, with a new action at least every half second; the longest moment without movement is under half a second. Base motion for all 8 seconds: SHERU twirls the plain gold car key with no emblem on one finger, his head bobs and his shoulders roll; gold confetti swirls through the air; the crowd claps. 0–1s: the FOX AUCTIONEER swings the gavel up with his whole arm, ears up. 1–2s: the FOX AUCTIONEER slams the gavel down and shouts, leaning over the podium. 2–3s: Gold confetti blasts from the ceiling; heads tip up in the crowd. 3–4s: The crowd jumps up clapping, arms in the air. 4–5s: KALA DON shakes his head in disbelief, shoulders slumping. 5–6s: KALA DON flattens his ears, the panther's tail lashing. 6–7s: SHERU tosses the key high with a flick of the wrist, head tilting up. 7–8s: SHERU catches it and turns toward the camera, shoulders rolling, grinning wide. The clip ends mid-motion. The LED board shows only rows of glowing gold zeros and gold sparks, no letters, no other numbers. At 0–4s the fox auctioneer says in Hindi: "Bik gaya! Sheru Bhai ko!" Voices: the fox auctioneer: loud, excited auctioneer voice. Every line ends before the 8-second mark. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, Indian luxury setting, no readable text, no logos, no subtitles, no watermark.

Step 4

Keep Sheru consistent

Start every scene from the same character image, paste the same short tag ("SHERU, the white lion in the white three-piece suit, heavy gold chain and black aviators"), and keep the setting words the same across scenes. Describe what moves in every second, not a pose to stop in: models that are given a pose tend to stand in it. Do not give a last frame unless the clip really has to end on that picture; a last frame makes the model spend the final second sliding into it.

AI-generated image: Sheru walks his cub Beta through palace-style school gates, bear bodyguards in black suits on both sides
Buys the school
AI-generated image: Sheru spreads his arms on a mall balcony, animal shoppers in suits on the floors below
Buys the mall

Step 5

Hindi dialogue and dubbing

Write each line in Hinglish inside quotes, say "says in Hindi", keep it to about 2–2.5 words per second of the clip, and give each character a fixed voice description (our prompts do this). Veo in Flow can generate speech and may move the lips to it, but results vary; when the lip-sync or the Hindi is off, turn on silent output ("Return silent videos" in Flow) and record or generate the line yourself, then lay it over the clip in CapCut.[4]

Step 6

Edit in CapCut or InShot

Download the clips and put them in order on a 9:16 canvas in CapCut, InShot, VN or KineMaster. Trim black frames at the joins. Add a top caption ("Sheru Bhai 😎"), Hinglish subtitles for viewers on mute, a one-second end card ("Aura +999999 πŸ—Ώ") and background music low under the dialogue (the tutorials use about 35%).

Step 7

Export and publish

Export 1080Γ—1920 (or the clips' own 720Γ—1280), 30 fps. Title it like the format ("Sheru Bhai ki boli! Kala Don hil gaya 😱"), hashtag #sherubhai #sheruai #aivideo, and turn on the AI or synthetic content label.[6] End with "Part 2 chahiye? Comment SHERU" and make part 2 from the same character image.

Real run

Complete Example

One real run made for this page on 12 Nov 2026: the character prompt, the first-frame prompt with the character image as reference, then the 8-second video prompt (Veo 3.1 Lite, image-to-video, no sound). Prompts and outputs are shown exactly as used.

AI-generated full-length image of Sheru: an anthropomorphic white lion in a white three-piece suit, gold chain, gold watch and black aviators in a marble palace hall
1 Β· Character prompt β†’ character image
AI-generated 8-second clip: a white lion in a white suit kneels in a palace garden, laughs with a small cartoon lion cub in a red shirt, lifts him onto his hip and sets him down
2 Β· First-frame prompt β†’ first frame
3 Β· Video prompt β†’ 8-second clip

1 Β· Character prompt β†’ character image

Character reference sheet image of SHERU BHAI: a tall anthropomorphic white lion man, photoreal 3D fur, thick snow-white mane swept back, pale gold eyes, broad shoulders, human body proportions, wearing a tailored white three-piece suit (white jacket, white waistcoat, crisp white shirt, no tie, gold pocket square), a heavy gold Cuban-link chain on his chest, a large gold wristwatch on the left wrist, a gold ring on the right hand, slim black aviator sunglasses on his eyes. Full-length portrait from head to white shoes, standing tall and facing the camera, confident half-smile, one hand in his trouser pocket, in a white marble palace hall with crystal chandeliers and gold trim. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, no on-screen text, no subtitles, no watermark, no logo.

2 Β· First-frame prompt β†’ first frame

Use the reference image for SHERU: keep his face, white mane, white three-piece suit, gold chain, gold watch and black aviator sunglasses exactly the same. A sunny palace garden with fountains and gold railings. SHERU kneels on one knee on the lawn next to BETA, his son: a small, chubby, Pixar-style anthropomorphic white lion cub with big round gold eyes and a fluffy short white mane, wearing a red short-sleeve shirt, blue shorts and a tiny gold chain. Sheru has one hand on the cub's shoulder; both grin at the camera; the cub gives a thumbs-up. Wholesome, family-friendly. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, no on-screen text, no subtitles, no watermark, no logo.

3 Β· Video prompt β†’ 8-second clip

Cast: SHERU (the white lion in the white three-piece suit, heavy gold chain and black aviators from the first frame); BETA (the small Pixar-style white lion cub in the red shirt, Sheru's son). One continuous 8-second take with no cuts, full shot at chest height on both, slow push-in to a medium shot that tilts up as Sheru rises; the main character fills about three quarters of the frame height, faces clearly visible. Light: warm golden-hour sun behind them from the upper left as a rim light, soft fill on both faces from the front. Pace: the clip opens mid-action and something on screen visibly changes every second, with a new action at least every half second; the longest moment without movement is under half a second; no music. Base motion for all 8 seconds: SHERU nods along every half second, his shoulders bounce and his free hand pats the cub's back between moves; BETA wiggles and bounces, both arms pumping, feet bouncing; palace fountains splash behind them. 0–1s: SHERU ruffles BETA's mane with one hand, head tipping back in a laugh. 1–2s: BETA pumps his thumbs-up twice, giggling, ears wiggling. 2–3s: SHERU scoops BETA up into the crook of one arm, leaning in, shoulders rolling. 3–4s: SHERU pushes up from his knee with the cub on his arm, his free hand on his thigh, shoulders rising. 4–5s: BETA throws both arms wide, snug in the crook of Sheru's arm, kicking his feet, head thrown back laughing. 5–6s: SHERU sways side to side on his heels, bouncing the cub on his arm, laughing. 6–7s: SHERU tips his sunglasses down his nose with one finger of his free hand, the glasses staying on his face, brows rising. 7–8s: SHERU winks at the camera over the glasses while BETA claps his paws above his head, both grinning. The clip ends mid-motion. Nobody speaks. Audio: birdsong, fountains splashing, laughter, no music. Photoreal 3D CGI, cinematic lighting, warm gold highlights, shallow depth of field, vertical 9:16, luxury setting matching the first frame, no readable text, no logos, no subtitles, no watermark.

Fixes

Common Problems and Fixes

ProblemFix
Sheru looks different in every clipStart every scene from the same character image; paste the same tag; never re-describe the suit differently.
The clip stands still for a second, then movesSay what moves in every second and open mid-action; remove words like "hold", "freeze", "pause" or "still".
Garbled letters on boards, cheques or phonesAdd "no readable text, no logos"; describe screens as glowing or sparkling, not as showing numbers or words.
The Hindi line is cut off or out of syncShorten it to about 2 words per second of its window; or switch to silent output and dub it in CapCut.
"Content policy" refusalRemove weapons, blood, children in danger and real brands; a cartoon cub in a happy scene is usually fine. Our own auction clip was refused twice; we show its first frame instead.
Out of free creditsFlow's free credits reset daily; make the character image and first frames first, then the videos.

Prompt

How to write a Sheru Bhai video prompt that moves

  1. Character bible first

    One fixed description of Sheru, pasted word for word into every image prompt: white lion, white three-piece suit, gold pocket square, heavy gold Cuban-link chain, gold watch, gold ring, black aviators. In video prompts, use a short tag and let the first frame carry the look.

  2. Say what moves every second

    Write eight one-second clauses for an 8-second clip, each a different visible action, plus a base layer that never stops (head nods, shoulders roll, chain swings). Open mid-action; end mid-motion.

  3. Camera words

    One camera move per clip: push in, track backward ahead of him, or tilt up from the shoes to the face. Keep Sheru about three quarters of the frame height so his face reads.

  4. No stopping words

    Words like "hold", "freeze", "pause" or "still" make the model stand the characters in place and wait. The aura card comes in the edit.

  5. Dialogue in quotes

    Two lines at most per scene, in Hinglish, in quotes, about 2 words per second: Sheru says in Hindi: "Meri boli... arban kharban!" Veo can voice the line; lip-sync is not guaranteed.

  6. Stay safe

    No guns, no blood, no real brands or logos, no children in danger, and "no readable text, no logos" at the end of every prompt.

Open the prompt generator

Hinglish

Sheru Bhai AI Video Kaise Banaye? (Hindi Guide)

Sabse pehle ChatGPT se 4 scene ki Hinglish story likhwao, ya hamara free generator use karo. Phir Gemini ya Flow mein Sheru ki ek character image banao: safed sher, white three-piece suit, moti gold chain, gold watch, kaala chashma.

Har scene ke liye Google Flow kholo, Frames to Video mein woh image daalo, 8 second ka video prompt paste karo aur generate karo. Dialogue quotes mein likho: Sheru says in Hindi: "Meri boli... arban kharban!" Lip-sync theek na ho to silent video lo aur CapCut mein awaaz daal do.

Aakhir mein CapCut ya InShot mein saare clips jodo, caption aur "Aura +999999" card lagao, aur Shorts ya Reels par daal do. Poora Hindi tutorial: ΰ€Άΰ₯‡ΰ€°ΰ₯‚ ΰ€­ΰ€Ύΰ€ˆ AI ΰ€΅ΰ₯€ΰ€‘ΰ€Ώΰ€―ΰ₯‹ ΰ€•ΰ₯ˆΰ€Έΰ₯‡ ΰ€¬ΰ€¨ΰ€Ύΰ€ΰ€‚.

FAQ

Questions about making Sheru videos

Can I make a Sheru Bhai AI video for free?

Yes. ChatGPT, the Gemini app and Google Flow's free daily credits are enough for a short video, and CapCut and InShot have free versions.[2] Limits change; check Flow before you start.

How many scenes for a 30-second video?

Four 8-second scenes make 32 seconds, which you trim to 30; three scenes make 24 seconds. Most Sheru Shorts are 30–60 seconds, so 4–7 scenes.

Why does Google Flow change Sheru's face?

Each clip is generated on its own, so the model re-imagines him unless you anchor him. Start every scene from the same character image (Frames to Video or Ingredients to Video) and keep the same tag in every prompt.

How do I fix incorrect Hindi lip-sync?

Shorten the line, put it in quotes with "says in Hindi", and give it a time window of at least half a second per word. If it is still off, generate the clip silent and dub the line in CapCut.

How do I join multiple clips?

Download each clip, put them in order on a 9:16 canvas in CapCut or InShot, trim the black frames at the joins and export once. Flow's Scenebuilder can also order and trim clips.[5]

Can I make it without a computer?

Yes. ChatGPT, the Gemini app, Google Flow and CapCut all run on a phone; the tutorials we read are made phone-first.

Can I upload to Shorts and Reels?

Yes. Export vertical 9:16, keep it under 60 seconds for Shorts, and turn on the AI / synthetic content label where the platform asks.[6]