Dheepan Ratnam's banner
Dheepan Ratnam's profile picture

Dheepan Ratnam

@Dheepanratnam • 15,953 subscribers

AI storyteller and digital artist | Weaving whimsical tales and vibrant artwork from the wild heart of AI. CPP of @higgsfield | From the island of Sri Lanka🇱🇰

Shorts

15 seconds of pure visual storytelling. 100% AI generated (Seedance 2.0) the camera moves from wet stone, through the fire of a wok, up to the rooftops, and back down. all in one continuous take. prompt below 🏮👇

15 seconds of pure visual storytelling. 100% AI generated (Seedance 2.0) the camera moves from wet stone, through the fire of a wok, up to the rooftops, and back down. all in one continuous take. prompt below 🏮👇

130,427 views

AI is wild Chatgpt 2.0 images + Seedance 2.0 tried to generate a red carpet AI video using this custom Sydney Sweeney character sheet. the result looks exactly like "we have sydney sweeney at home" 😭 A Simple Prompt used to test - Use the provided character reference for the facial features and body structure. create a 15 second red carpet multi shot walk with elegant designer wear

AI is wild Chatgpt 2.0 images + Seedance 2.0 tried to generate a red carpet AI video using this custom Sydney Sweeney character sheet. the result looks exactly like "we have sydney sweeney at home" 😭 A Simple Prompt used to test - Use the provided character reference for the facial features and body structure. create a 15 second red carpet multi shot walk with elegant designer wear

102,315 views

I gave Sora 2, Veo 3.1, and Seedance 2.0 a nearly impossible prompt: extreme weather, complex physics, and a dynamic tracking camera following a golf ball mid-flight. Seedance 2.0 is the only one that survived. Steal the prompt: [Insert full prompt text with paragraph breaks here] Watch the Seedance 2.0 result below. Dropping the Sora, Veo attempts and the prompt in the thread so you can see the difference. 🤯

I gave Sora 2, Veo 3.1, and Seedance 2.0 a nearly impossible prompt: extreme weather, complex physics, and a dynamic tracking camera following a golf ball mid-flight. Seedance 2.0 is the only one that survived. Steal the prompt: [Insert full prompt text with paragraph breaks here] Watch the Seedance 2.0 result below. Dropping the Sora, Veo attempts and the prompt in the thread so you can see the difference. 🤯

128,850 views

OMG guysss Seedance Pro 2.0 creature fight made with it and the SOUND EFFECTS are actually INSANE 😱🔥 This is next level

OMG guysss Seedance Pro 2.0 creature fight made with it and the SOUND EFFECTS are actually INSANE 😱🔥 This is next level

107,340 views

Seedance Pro 2.0 - Fighting a colossal mechanical beast Prompt used 👇 A dense industrial refinery during a thunderstorm, metal catwalks and pipes forming a maze above a sea of fire and steam. The masked ronin, lit by flashing warning lights, confronts a colossal mechanical beast with hydraulic limbs and a furnace burning in its chest. The camera barrels after the ronin as he sprints along swaying catwalks, the structure groaning and buckling under the monster’s weight. Sparks and steam constantly obscure the frame as the beast’s limbs smash through railings and tanks, causing explosions that hurl the camera off-axis. Quick, shaky close-ups capture the ronin sliding under swinging metal arms and using chains and cables to slingshot himself upward. In the final movement, the camera chases him in a dizzying upward spiral as he climbs the creature’s back, then cuts to a wide but still trembling shot as he plunges his sword into the furnace chest, sending a pillar of flame skyward that silhouettes his figure against the stormy sky.

Seedance Pro 2.0 - Fighting a colossal mechanical beast Prompt used 👇 A dense industrial refinery during a thunderstorm, metal catwalks and pipes forming a maze above a sea of fire and steam. The masked ronin, lit by flashing warning lights, confronts a colossal mechanical beast with hydraulic limbs and a furnace burning in its chest. The camera barrels after the ronin as he sprints along swaying catwalks, the structure groaning and buckling under the monster’s weight. Sparks and steam constantly obscure the frame as the beast’s limbs smash through railings and tanks, causing explosions that hurl the camera off-axis. Quick, shaky close-ups capture the ronin sliding under swinging metal arms and using chains and cables to slingshot himself upward. In the final movement, the camera chases him in a dizzying upward spiral as he climbs the creature’s back, then cuts to a wide but still trembling shot as he plunges his sword into the furnace chest, sending a pillar of flame skyward that silhouettes his figure against the stormy sky.

98,969 views

15-second Fresh Pasta Tutorial that looks cool 🔥 Made with ChatGPT 2.0 + Seedance. One reference sheet + one prompt = perfectly consistent video. Watch the chef flow through all 9 steps seamlessly. Full prompts dropping now 👇 Thread 🧵

15-second Fresh Pasta Tutorial that looks cool 🔥 Made with ChatGPT 2.0 + Seedance. One reference sheet + one prompt = perfectly consistent video. Watch the chef flow through all 9 steps seamlessly. Full prompts dropping now 👇 Thread 🧵

68,720 views

Seedance 2.0🤯🤯 what did they even train the model with? everything i test the results make me wonder wtf 🔥 This is just the tip of the 🧊🍨😍

Seedance 2.0🤯🤯 what did they even train the model with? everything i test the results make me wonder wtf 🔥 This is just the tip of the 🧊🍨😍

72,506 views

Seedance 2.0 is now available in Europe in capcut🔥 Animated short with Multi-shot sequence and dialogues Ep 01 15 seconds Text to Video Prompt 👇 A humorous Pixar-style animated short featuring two anthropomorphic toothbrushes debating in a bright modern bathroom: grumpy old manual toothbrush with worn bristles, tiny arms, and expressive face vs. sleek confident electric toothbrush with glowing LED eyes, vibrating body, and influencer attitude. Multi-shot sequence: medium shot of manual toothbrush shaking angrily on the counter, close-up push-in on electric toothbrush proudly vibrating with flashing lights, over-the-shoulder shot during argument, chaotic wide shot as toothpaste flies everywhere, ending in sink with both looking defeated but friendly. Manual toothbrush complains: "Back in my day we scrubbed with elbow grease! You just sit there buzzing like a lazy phone on vibrate!" E lectric replies: "Bro, I clean 40,000 times per minute while you’re doing cardio. I’m basically a gym membership for teeth!" Twist: both get dropped in the sink, manual says "Truce?", electric buzzes weakly "Fine… but I still win on TikTok." Vibrant colors, bouncy physics, exaggerated facial expressions, cartoon sound effects including angry shakes, buzzing vibrations, toothpaste splats, and dramatic whooshes. Dynamic camera: quick cuts, zooms, and playful pans. Soft morning lighting with shiny reflections on tiles. High quality, smooth animation, 15-second duration, funny and relatable tech vs old-school vibe.

Seedance 2.0 is now available in Europe in capcut🔥 Animated short with Multi-shot sequence and dialogues Ep 01 15 seconds Text to Video Prompt 👇 A humorous Pixar-style animated short featuring two anthropomorphic toothbrushes debating in a bright modern bathroom: grumpy old manual toothbrush with worn bristles, tiny arms, and expressive face vs. sleek confident electric toothbrush with glowing LED eyes, vibrating body, and influencer attitude. Multi-shot sequence: medium shot of manual toothbrush shaking angrily on the counter, close-up push-in on electric toothbrush proudly vibrating with flashing lights, over-the-shoulder shot during argument, chaotic wide shot as toothpaste flies everywhere, ending in sink with both looking defeated but friendly. Manual toothbrush complains: "Back in my day we scrubbed with elbow grease! You just sit there buzzing like a lazy phone on vibrate!" E lectric replies: "Bro, I clean 40,000 times per minute while you’re doing cardio. I’m basically a gym membership for teeth!" Twist: both get dropped in the sink, manual says "Truce?", electric buzzes weakly "Fine… but I still win on TikTok." Vibrant colors, bouncy physics, exaggerated facial expressions, cartoon sound effects including angry shakes, buzzing vibrations, toothpaste splats, and dramatic whooshes. Dynamic camera: quick cuts, zooms, and playful pans. Soft morning lighting with shiny reflections on tiles. High quality, smooth animation, 15-second duration, funny and relatable tech vs old-school vibe.

46,015 views

Seedance 2.0 photorealistic macro cinematic Shot Video Prompt used 👇 FORMAT: 15s / 6 SHOTS / single continuous chase energy / no dialogue STYLE: Macro jungle floor, towering grass blades, dew drops, damp earth vs neon pink cyber-implants, photorealistic macro cinematic Shot 01 (0:00-0:02) Dive from the canopy of a giant fern down to a cybernetically enhanced rhinoceros beetle sprinting across a fallen, moss-covered log. Shot 02 (0:02-0:04) Camera tracks parallel to the beetle's mechanical legs, sweeps under its glowing pink thorax, and snaps to the spinning micro-rotors on its back. Shot 03 (0:04-0:07) A heavy rain droplet dislodges a pebble from above; the beetle initiates a thruster-assisted sidestep, scraping its metallic horn against a fungal stalk. Shot 04 (0:07-0:10) The path dives into a dense thicket of thorny briars, spiderwebs, and overlapping leaves; the camera seamlessly navigates the micro-labyrinth. Shot 05 (0:10-0:13) The beetle bursts from the thicket into a clearing, a splash of muddy dew hitting the lens as its optical sensors flash tactical warnings. Shot 06 (0:13-0:15) Camera pulls back exponentially, transitioning from the micro scale to reveal an immense, sprawling bioluminescent greenhouse, the beetle lost in the glowing flora.

Seedance 2.0 photorealistic macro cinematic Shot Video Prompt used 👇 FORMAT: 15s / 6 SHOTS / single continuous chase energy / no dialogue STYLE: Macro jungle floor, towering grass blades, dew drops, damp earth vs neon pink cyber-implants, photorealistic macro cinematic Shot 01 (0:00-0:02) Dive from the canopy of a giant fern down to a cybernetically enhanced rhinoceros beetle sprinting across a fallen, moss-covered log. Shot 02 (0:02-0:04) Camera tracks parallel to the beetle's mechanical legs, sweeps under its glowing pink thorax, and snaps to the spinning micro-rotors on its back. Shot 03 (0:04-0:07) A heavy rain droplet dislodges a pebble from above; the beetle initiates a thruster-assisted sidestep, scraping its metallic horn against a fungal stalk. Shot 04 (0:07-0:10) The path dives into a dense thicket of thorny briars, spiderwebs, and overlapping leaves; the camera seamlessly navigates the micro-labyrinth. Shot 05 (0:10-0:13) The beetle bursts from the thicket into a clearing, a splash of muddy dew hitting the lens as its optical sensors flash tactical warnings. Shot 06 (0:13-0:15) Camera pulls back exponentially, transitioning from the micro scale to reveal an immense, sprawling bioluminescent greenhouse, the beetle lost in the glowing flora.

44,216 views

Made a full Pixar-style animation of The Lion & The Mouse in 15 seconds, 15 shots, 🦁🐭✨ GPT 2 Images for storyboards → Seedance 2.0 for animation This is what AI storytelling looks like in 2026. 🔥 Here's exactly how I made the Pixar-style animated short with AI 👇

Made a full Pixar-style animation of The Lion & The Mouse in 15 seconds, 15 shots, 🦁🐭✨ GPT 2 Images for storyboards → Seedance 2.0 for animation This is what AI storytelling looks like in 2026. 🔥 Here's exactly how I made the Pixar-style animated short with AI 👇

29,890 views

Seedance 2.0 What are they all excited about? Wrong answers only 😃

Seedance 2.0 What are they all excited about? Wrong answers only 😃

43,523 views

Seedance 2.0 / continuous one-take / hyperreal water physics. It takes lot of time to make VFX rendering for a shot like this. Seedance just generated it in minutes First frame image prompt 🔽 A lone emergency technician in an orange survival jacket stands on the shattered roof of a flooded museum in a drowned European capital, storm clouds overhead, broken statues and floating debris below, cold blue-grey palette, cinematic disaster realism, wet surfaces, strong scale, 35mm film look Created with nano banana pro ImagineArt Video Prompt: 👇 "Disaster film realism, one-take. The camera starts high above a drowned capital city in violent storm weather, then dives toward a lone emergency technician standing on the shattered roof of a flooded museum. He sees a rescue flare in the distance and runs. The camera follows tightly behind him as he sprints across collapsing rooftops, leaps over broken skylights, slides down a tilted glass dome, and grabs a dangling cable. Below, dark floodwater surges through streets filled with drifting cars and statues. He lands on a partially submerged tram roof, keeps moving, and reaches a rescue beacon platform just as a giant wave crashes past behind him. Cold grey-blue apocalyptic palette, hyperreal water physics, wind, spray, handheld urgency, one continuous shot, no cuts."

Seedance 2.0 / continuous one-take / hyperreal water physics. It takes lot of time to make VFX rendering for a shot like this. Seedance just generated it in minutes First frame image prompt 🔽 A lone emergency technician in an orange survival jacket stands on the shattered roof of a flooded museum in a drowned European capital, storm clouds overhead, broken statues and floating debris below, cold blue-grey palette, cinematic disaster realism, wet surfaces, strong scale, 35mm film look Created with nano banana pro ImagineArt Video Prompt: 👇 "Disaster film realism, one-take. The camera starts high above a drowned capital city in violent storm weather, then dives toward a lone emergency technician standing on the shattered roof of a flooded museum. He sees a rescue flare in the distance and runs. The camera follows tightly behind him as he sprints across collapsing rooftops, leaps over broken skylights, slides down a tilted glass dome, and grabs a dangling cable. Below, dark floodwater surges through streets filled with drifting cars and statues. He lands on a partially submerged tram roof, keeps moving, and reaches a rescue beacon platform just as a giant wave crashes past behind him. Cold grey-blue apocalyptic palette, hyperreal water physics, wind, spray, handheld urgency, one continuous shot, no cuts."

33,863 views

Seedance 2.0 is a cheat code. This shot would cost a traditional VFX studio $100,000 and 2 weeks of rendering. I just generated it in minutes. The morph from car ➡️ dragon is absolutely seamless.

Seedance 2.0 is a cheat code. This shot would cost a traditional VFX studio $100,000 and 2 weeks of rendering. I just generated it in minutes. The morph from car ➡️ dragon is absolutely seamless.

31,865 views

Seedance 2.0 can do cinema Prompt 👇 战争灾难电影感，一镜到底，清晨灰蓝色天光下，一名年轻传令员冲出被炮火撕开的地下掩体，镜头紧贴其身后高速跟随，穿过泥泞战壕、燃烧的补给车、炸裂的木桥和四散奔逃的人群。远处不断有炮弹落下，泥土、木屑、火焰和烟柱在镜头两侧连续爆开，士兵和担架队从前景横穿而过，极具临场感。主角翻越一段坍塌沙袋墙，滑下满是积水的斜坡，穿过一片布满铁丝网和弹坑的开阔地，爆炸冲击波在身后掀起巨大尘浪。最后他冲上一座半毁钟楼废墟，将一枚发光信号筒插入高处装置，镜头随之迅速拉起，俯瞰整片燃烧战场与远处仍在推进的军阵，电影级写实战争规模感，强节奏，无剪辑。

Seedance 2.0 can do cinema Prompt 👇 战争灾难电影感，一镜到底，清晨灰蓝色天光下，一名年轻传令员冲出被炮火撕开的地下掩体，镜头紧贴其身后高速跟随，穿过泥泞战壕、燃烧的补给车、炸裂的木桥和四散奔逃的人群。远处不断有炮弹落下，泥土、木屑、火焰和烟柱在镜头两侧连续爆开，士兵和担架队从前景横穿而过，极具临场感。主角翻越一段坍塌沙袋墙，滑下满是积水的斜坡，穿过一片布满铁丝网和弹坑的开阔地，爆炸冲击波在身后掀起巨大尘浪。最后他冲上一座半毁钟楼废墟，将一枚发光信号筒插入高处装置，镜头随之迅速拉起，俯瞰整片燃烧战场与远处仍在推进的军阵，电影级写实战争规模感，强节奏，无剪辑。

26,590 views

i am literally creating seedance 2.0 videos for FREE 5 videos a day for free is an infinite glitch 🤯. only text to video & 10 sec available / no reference to image video -Its from doubao

i am literally creating seedance 2.0 videos for FREE 5 videos a day for free is an infinite glitch 🤯. only text to video & 10 sec available / no reference to image video -Its from doubao

28,831 views

I typed a sentence. I got a movie. Seedance 2.0 is absolutely insane. 🤯 The lighting, physics, and consistency in these one-shot generations are next level. Look at these 4 outputs.

I typed a sentence. I got a movie. Seedance 2.0 is absolutely insane. 🤯 The lighting, physics, and consistency in these one-shot generations are next level. Look at these 4 outputs.

27,695 views

From concept to screen in one flow. ChatGPT 2.0 created the full character bible mood, silhouette, gestures, accessories. Seedance 2.0 brought him to life. This is the new standard for villain entrances 🔥 Full character design sheet + video in the post🧵👇

From concept to screen in one flow. ChatGPT 2.0 created the full character bible mood, silhouette, gestures, accessories. Seedance 2.0 brought him to life. This is the new standard for villain entrances 🔥 Full character design sheet + video in the post🧵👇

16,054 views

Jewelry layering, perfected in 12 seconds ✨ Clean, calm, and actually useful. Base → layers → final look in perfect motion. ChatGPT 2.0 + Seedance 2.0 just cooked this. Save for your next outfit Prompts in the Thread 🧵👇

Jewelry layering, perfected in 12 seconds ✨ Clean, calm, and actually useful. Base → layers → final look in perfect motion. ChatGPT 2.0 + Seedance 2.0 just cooked this. Save for your next outfit Prompts in the Thread 🧵👇

15,869 views

War Time shots Episode 1 with Seedance 2.0 First video prompt 15-second impossible siege shot. The camera races toward a massive wooden siege tower as it rolls across the battlefield under flaming impacts. It climbs vertically along the outside as the structure begins to collapse, then slips through a shattered side panel into the tower interior, passing ladders, panicked soldiers, splintering beams, and falling ropes. It bursts out the top platform just as the tower tips over, dives off the collapsing edge, and re-enters the battlefield in a low flying arc over the heads of charging infantry. Continuous camera motion through solid structure and open battle space, impossible rigging, splinters, fire, dust, and giant war scale. All other prompts are in the comments 👇 Created with Dreamina AI #DreaminaCPP

War Time shots Episode 1 with Seedance 2.0 First video prompt 15-second impossible siege shot. The camera races toward a massive wooden siege tower as it rolls across the battlefield under flaming impacts. It climbs vertically along the outside as the structure begins to collapse, then slips through a shattered side panel into the tower interior, passing ladders, panicked soldiers, splintering beams, and falling ropes. It bursts out the top platform just as the tower tips over, dives off the collapsing edge, and re-enters the battlefield in a low flying arc over the heads of charging infantry. Continuous camera motion through solid structure and open battle space, impossible rigging, splinters, fire, dust, and giant war scale. All other prompts are in the comments 👇 Created with Dreamina AI #DreaminaCPP

17,145 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Bollywood isn’t ready for this 🤯💃 30s single-shot music video created with Seedance 2.5. Just 1 reference image + text prompt. Full visual fidelity, zero cutaways. AI cinema is moving way too fast. 🎬✨
0:30
Dheepanratnam's profile picture

Bollywood isn’t ready for this 🤯💃 30s single-shot music video created with Seedance 2.5. Just 1 reference image + text prompt. Full visual fidelity, zero cutaways. AI cinema is moving way too fast. 🎬✨

Dheepan Ratnam

924,005 views • 10 days ago

What happens when Mollywood energy meets Rio Carnival? 💃🦜 AI is coming for Mollywood too 🤯 30-second continuous music video featuring MB using Seedance 2.5. • 1 ref image• and prompt Full Video+ audio & vocal generation from seedance • Sand, forest, and feather wing physics • 0 cutaways AI cinema isn't slowing down. sound on 🔊👇
0:30
Dheepanratnam's profile picture

What happens when Mollywood energy meets Rio Carnival? 💃🦜 AI is coming for Mollywood too 🤯 30-second continuous music video featuring MB using Seedance 2.5. • 1 ref image• and prompt Full Video+ audio & vocal generation from seedance • Sand, forest, and feather wing physics • 0 cutaways AI cinema isn't slowing down. sound on 🔊👇

Dheepan Ratnam

142,706 views • 9 days ago

A 30s High energy Single shot music video with seedance 2.5 😍
0:30
Dheepanratnam's profile picture

A 30s High energy Single shot music video with seedance 2.5 😍

Dheepan Ratnam

174,200 views • 11 days ago

Testing Seedance 2.5 on a full kollywood South Indian group dance 🤯 30s continuous single-shot, music, 4K cinema look. Look at the synchronization, the footwork, and the camera movement all generated from a single prompt. AI video just keeps leveling up 🎬✨
0:30
Dheepanratnam's profile picture

Testing Seedance 2.5 on a full kollywood South Indian group dance 🤯 30s continuous single-shot, music, 4K cinema look. Look at the synchronization, the footwork, and the camera movement all generated from a single prompt. AI video just keeps leveling up 🎬✨

Dheepan Ratnam

74,029 views • 6 days ago

Classical Indian dance is the ultimate stress test for AI video and Seedance 2.5 just nailed it 🤯💃 30s single continuous take. Visuals + original synchronized soundtrack generated together. Look at the mudra precision, jewelry physics, and facial micro-expressions on the zoom-ins. Zero cutaways. Sound ON for this one 🔊🎬
0:30
Dheepanratnam's profile picture

Classical Indian dance is the ultimate stress test for AI video and Seedance 2.5 just nailed it 🤯💃 30s single continuous take. Visuals + original synchronized soundtrack generated together. Look at the mudra precision, jewelry physics, and facial micro-expressions on the zoom-ins. Zero cutaways. Sound ON for this one 🔊🎬

Dheepan Ratnam

94,735 views • 9 days ago

When classic temple aesthetics meet Next-Gen AI 🌸✨ 30s single-shot generation of bollywood dance in Seedance 2.5
0:30
Dheepanratnam's profile picture

When classic temple aesthetics meet Next-Gen AI 🌸✨ 30s single-shot generation of bollywood dance in Seedance 2.5

Dheepan Ratnam

35,815 views • 7 days ago

Kollywood directors on a tight budget can use AI for real Testing Seedance 2.5 with a duo this time 💃💃 Full 30s continuous shot synchronized footwork, hand mudras, and zero drift between the two dancers. Single prompt. 🎬✨
0:30
Dheepanratnam's profile picture

Kollywood directors on a tight budget can use AI for real Testing Seedance 2.5 with a duo this time 💃💃 Full 30s continuous shot synchronized footwork, hand mudras, and zero drift between the two dancers. Single prompt. 🎬✨

Dheepan Ratnam

26,980 views • 6 days ago

From high-energy mass kuthu to pure 90s Bollywood nostalgia ✨ What if we brought back the "Ladki Badi Hai" era? 30s uninterrupted shot generated entirely with Seedance 2.5 Good Morning Vibes set for tuesday 😍
0:30
Dheepanratnam's profile picture

From high-energy mass kuthu to pure 90s Bollywood nostalgia ✨ What if we brought back the "Ladki Badi Hai" era? 30s uninterrupted shot generated entirely with Seedance 2.5 Good Morning Vibes set for tuesday 😍

Dheepan Ratnam

28,299 views • 7 days ago

30 seconds. One continuous single-take. 4K cinematic. Bollywood group routine. 🤯 I just tested Seedance 2.5 for a dance sequence and the results are wild timing, footwork, and camera motion… all generated from one prompt with music. If you’re curious how close AI video is getting to What should I test next: solo, duet, or bigger group choreography? #Seedance25 #AIVideo
0:30
Dheepanratnam's profile picture

30 seconds. One continuous single-take. 4K cinematic. Bollywood group routine. 🤯 I just tested Seedance 2.5 for a dance sequence and the results are wild timing, footwork, and camera motion… all generated from one prompt with music. If you’re curious how close AI video is getting to What should I test next: solo, duet, or bigger group choreography? #Seedance25 #AIVideo

Dheepan Ratnam

17,152 views • 6 days ago

Bollywood meets flamenco and AI made the whole thing 🤯💃 1 reference image • 1 prompt • 1 single 30s generation with Seedance 2.5 16 scenes, 16 different moves, and every cut and ankle bell came out of one run. No editing. 🎬 What global fusion should I test next?
0:30
Dheepanratnam's profile picture

Bollywood meets flamenco and AI made the whole thing 🤯💃 1 reference image • 1 prompt • 1 single 30s generation with Seedance 2.5 16 scenes, 16 different moves, and every cut and ankle bell came out of one run. No editing. 🎬 What global fusion should I test next?

Dheepan Ratnam

12,445 views • 9 days ago

You asked for more Bollywood choreo so I leveled up to 3 dancers in one shot 👀💃 30s uninterrupted studio take using Seedance 2.5. 3 reference images • 1 text prompt • 0 cutaways Keeping motion coherent across three separate styles in a continuous 30-second run is wild. Who killed the routine? 👇
0:30
Dheepanratnam's profile picture

You asked for more Bollywood choreo so I leveled up to 3 dancers in one shot 👀💃 30s uninterrupted studio take using Seedance 2.5. 3 reference images • 1 text prompt • 0 cutaways Keeping motion coherent across three separate styles in a continuous 30-second run is wild. Who killed the routine? 👇

Dheepan Ratnam

12,757 views • 10 days ago

Real world + anime stickers = pure chaos Magic marker turns streets into cartoons. Zebra crossings, baby T-Rexes, flying fish, and your shadow becoming the final boss. Gemini Omni delivered 🔥" Built this in Gemini Omni with one shared prompt block across 5 clips. Live-action street vlog meets flat 2D anime stickers. Marker goes “Biu!” and everything transforms while keeping perfect physics and perspective. The result? This. Mind officially blown."
0:50
Dheepanratnam's profile picture

Real world + anime stickers = pure chaos Magic marker turns streets into cartoons. Zebra crossings, baby T-Rexes, flying fish, and your shadow becoming the final boss. Gemini Omni delivered 🔥" Built this in Gemini Omni with one shared prompt block across 5 clips. Live-action street vlog meets flat 2D anime stickers. Marker goes “Biu!” and everything transforms while keeping perfect physics and perspective. The result? This. Mind officially blown."

Dheepan Ratnam

50,055 views • 3 months ago

Overthinking feels like progress. One minute better - Episode 3🟣 Great for instagram & tiktok /youtube short video channels Google gemini omni flash model cost around 90 credits for making this Google Flow
1:00
Dheepanratnam's profile picture

Overthinking feels like progress. One minute better - Episode 3🟣 Great for instagram & tiktok /youtube short video channels Google gemini omni flash model cost around 90 credits for making this Google Flow

Dheepan Ratnam

43,515 views • 3 months ago

GPT 2 Images X Seedance 2.0 Animation with 30 second storyboard Don’t ask AI to “make a video.”Give it a production board. image/video Prompts and guide in the thread🧵 I made a 30-second animated video from a short sentence using only 3 steps: The trick is simple: Start with a short story, then turn both parts into one clean cinematic storyboard. Animate with seedance 2.0
0:30
Dheepanratnam's profile picture

GPT 2 Images X Seedance 2.0 Animation with 30 second storyboard Don’t ask AI to “make a video.”Give it a production board. image/video Prompts and guide in the thread🧵 I made a 30-second animated video from a short sentence using only 3 steps: The trick is simple: Start with a short story, then turn both parts into one clean cinematic storyboard. Animate with seedance 2.0

Dheepan Ratnam

68,861 views • 5 months ago

stop prompting AI video generators with just text. it’s basically gambling. if you want actual cinematic control, you have to treat the AI like a human animation studio. exact prompt in the replies 🧵👇 Chat gpt2.0 images /midjourney v 8.1 / seedance 2.0 I wanted a 15-second noir hand-to-hand combat scene. Text-only prompt = messy slop. Visual storyboard + Seedance 2.0 = flawless choreography. Dreamina AI #DreaminaCpp
0:30
Dheepanratnam's profile picture

stop prompting AI video generators with just text. it’s basically gambling. if you want actual cinematic control, you have to treat the AI like a human animation studio. exact prompt in the replies 🧵👇 Chat gpt2.0 images /midjourney v 8.1 / seedance 2.0 I wanted a 15-second noir hand-to-hand combat scene. Text-only prompt = messy slop. Visual storyboard + Seedance 2.0 = flawless choreography. Dreamina AI #DreaminaCpp

Dheepan Ratnam

56,185 views • 5 months ago

whatever life throws at you... duck and let it hit someone else full 12-shot seedance 2.5 prompt below 👇
0:30
Dheepanratnam's profile picture

whatever life throws at you... duck and let it hit someone else full 12-shot seedance 2.5 prompt below 👇

Dheepan Ratnam

15,662 views • 1 month ago

i created 4 different style videos with Gemini Omni Flash😻 will explore more and share the results Episode 1 - 4 styles 1- Papercraft 2- Origami 3-Claymation 4-Plush world PROMPTS’ in the comments and I’ll paste every prompt I used so you can test them yourself.
0:40
Dheepanratnam's profile picture

i created 4 different style videos with Gemini Omni Flash😻 will explore more and share the results Episode 1 - 4 styles 1- Papercraft 2- Origami 3-Claymation 4-Plush world PROMPTS’ in the comments and I’ll paste every prompt I used so you can test them yourself.

Dheepan Ratnam

43,719 views • 4 months ago

30 seconds of pure summer vibes ✨ CITRUS MOCKTAIL + STREET TACO ASSEMBLY ChatGPT 2.0 images + Seedance animation style delivered again 🔥 Full reference boards + prompts dropping now 👇
0:28
Dheepanratnam's profile picture

30 seconds of pure summer vibes ✨ CITRUS MOCKTAIL + STREET TACO ASSEMBLY ChatGPT 2.0 images + Seedance animation style delivered again 🔥 Full reference boards + prompts dropping now 👇

Dheepan Ratnam

42,561 views • 5 months ago

AI video is moving way too fast. This entire sequence was generated using just the Seedance 2.0 x ChatGPT combo. 🎬 Anime Fight Previz (testing choreography & camera beats) ✨ Fashion Lookbook Motion (turning static fits into runway clips) I'm dropping the exact prompts in the comments below. 👇
0:30
Dheepanratnam's profile picture

AI video is moving way too fast. This entire sequence was generated using just the Seedance 2.0 x ChatGPT combo. 🎬 Anime Fight Previz (testing choreography & camera beats) ✨ Fashion Lookbook Motion (turning static fits into runway clips) I'm dropping the exact prompts in the comments below. 👇

Dheepan Ratnam

33,387 views • 5 months ago

Instead of prompting with text only, create reference sheets first. Prompts in the comments 👇👇 For a yoga / wellness influencer video, I build: First 15 seconds - Motion sheet - the exact routine, poses, timing, transitions Character sheet - same face, body, outfit, expressions Location sheet -studio, lighting, props, mood, camera fee second 15 seconds - i put all 3 in one image. see the difference. 3 different sheets works better
0:30
Dheepanratnam's profile picture

Instead of prompting with text only, create reference sheets first. Prompts in the comments 👇👇 For a yoga / wellness influencer video, I build: First 15 seconds - Motion sheet - the exact routine, poses, timing, transitions Character sheet - same face, body, outfit, expressions Location sheet -studio, lighting, props, mood, camera fee second 15 seconds - i put all 3 in one image. see the difference. 3 different sheets works better

Dheepan Ratnam

31,313 views • 5 months ago