Umesh

@umesh_ai • 48,064 subscribers

Creator, Filmmaker, Developer Adobe Firefly Ambassador

Shorts

Racing through a collapsing world!

Racing through a collapsing world!

535,224 次观看

Imagine how much this would cost, if AI didn’t exist!

Imagine how much this would cost, if AI didn’t exist!

727,880 次观看

Great prompt ⤵️ A dining table version!

Great prompt ⤵️ A dining table version!

136,026 次观看

This from Flux 3 is incredible! Prompt : Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.

This from Flux 3 is incredible! Prompt : Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.

116,049 次观看

No limit to imagination! Prompt ⤵️

No limit to imagination! Prompt ⤵️

35,082 次观看

Prompt : A realistic cinematic scene begins in a vast open field under a warm golden sky during late afternoon. A man dressed in a dark suit stands in the foreground, holding a modern recurve bow. His posture is steady and focused, breath controlled, eyes locked on a distant archery target placed far on the horizon. The environment feels quiet and expansive, with subtle wind moving the grass and soft sunlight creating long shadows. As he releases the string, the arrow launches forward with a sharp snap. The camera immediately accelerates and locks onto the arrow mid flight. The camera tracks directly behind and slightly beside the arrow, maintaining perfect alignment as it cuts through the air. Motion blur surrounds the background while the arrow remains sharp and centered. The sound of rushing wind intensifies as the arrow travels straight and true. The target grows rapidly larger. In the final seconds, the camera closes in tightly as the arrow strikes the bull’s eye dead center. End on an extreme close up of the arrow embedded in the red center, vibrating slightly, with crisp impact sound and dramatic silence.

Prompt : A realistic cinematic scene begins in a vast open field under a warm golden sky during late afternoon. A man dressed in a dark suit stands in the foreground, holding a modern recurve bow. His posture is steady and focused, breath controlled, eyes locked on a distant archery target placed far on the horizon. The environment feels quiet and expansive, with subtle wind moving the grass and soft sunlight creating long shadows. As he releases the string, the arrow launches forward with a sharp snap. The camera immediately accelerates and locks onto the arrow mid flight. The camera tracks directly behind and slightly beside the arrow, maintaining perfect alignment as it cuts through the air. Motion blur surrounds the background while the arrow remains sharp and centered. The sound of rushing wind intensifies as the arrow travels straight and true. The target grows rapidly larger. In the final seconds, the camera closes in tightly as the arrow strikes the bull’s eye dead center. End on an extreme close up of the arrow embedded in the red center, vibrating slightly, with crisp impact sound and dramatic silence.

297,043 次观看

A high-end production house would've billed $100K for this. AI did it for the price of a coffee. One image, one prompt, less than 5 mins! Prompt ⤵️

A high-end production house would've billed $100K for this. AI did it for the price of a coffee. One image, one prompt, less than 5 mins! Prompt ⤵️

44,390 次观看

Would you believe it if someone told you that this video costs $0.15 and 10 seconds to produce? Crazy times! Prompt ⤵️

Would you believe it if someone told you that this video costs $0.15 and 10 seconds to produce? Crazy times! Prompt ⤵️

48,564 次观看

Split-screen test on Flux 3! Prompt : Split-screen video showing the same real-time action from two different camera angles. The screen is divided vertically into two equal halves. On the left side, show a static, wide overhead view from a ceiling-mounted camera in the back corner of the room. The full room layout is visible: a couch, coffee table, rug, bookshelves, and a tall shelf near the wall. The cat is perched on top of the shelf. At the 2-second mark, it suddenly jumps, flips mid-air above the furniture, and lands gracefully on the coffee table. On the right side, show the same action in perfect sync from a side, eye-level camera placed low beside the couch. The view includes the shelf, the space between, and the coffee table. The camera follows the cat’s leap, capturing body motion, twist, and landing.Both sides must be precisely synchronized, showing the exact same event from different angles with consistent lighting, physics, and timing.

Split-screen test on Flux 3! Prompt : Split-screen video showing the same real-time action from two different camera angles. The screen is divided vertically into two equal halves. On the left side, show a static, wide overhead view from a ceiling-mounted camera in the back corner of the room. The full room layout is visible: a couch, coffee table, rug, bookshelves, and a tall shelf near the wall. The cat is perched on top of the shelf. At the 2-second mark, it suddenly jumps, flips mid-air above the furniture, and lands gracefully on the coffee table. On the right side, show the same action in perfect sync from a side, eye-level camera placed low beside the couch. The view includes the shelf, the space between, and the coffee table. The camera follows the cat’s leap, capturing body motion, twist, and landing.Both sides must be precisely synchronized, showing the exact same event from different angles with consistent lighting, physics, and timing.

89,463 次观看

One of the coolest split screen prompts! Tried now with Kling 4.0 Flash.

One of the coolest split screen prompts! Tried now with Kling 4.0 Flash.

22,717 次观看

Prompt : Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.

Prompt : Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.

207,263 次观看

The museum didn’t lose a statue. It just found a replacement. Prompt ⤵️

The museum didn’t lose a statue. It just found a replacement. Prompt ⤵️

28,246 次观看

Flux 3 is here! One of my first tests. Very impressive. Prompt : Hyper realistic blockbuster cinematic 15 second action sequence in one true unbroken continuous shot, with no cuts, no morphing, and no scene transitions. A rally car races along a narrow alpine cliff road in bright cold daylight, escaping a falling avalanche and trying to reach a tunnel before the route is buried. The camera begins high above in a wide aerial view revealing snow peaks, sheer drops, and the winding road, then physically dives toward the car into a close tracking chase. It glides beside the doors, drops low near the spinning tires as snow sprays, rises overhead to reveal the avalanche rushing behind, then arcs outward into a high circling drone like view before descending again into a front facing backward tracking move. The shot remains seamless throughout as the car drifts around icy switchbacks, clips loose snow, and bursts toward the tunnel just ahead of the collapsing slope.

Flux 3 is here! One of my first tests. Very impressive. Prompt : Hyper realistic blockbuster cinematic 15 second action sequence in one true unbroken continuous shot, with no cuts, no morphing, and no scene transitions. A rally car races along a narrow alpine cliff road in bright cold daylight, escaping a falling avalanche and trying to reach a tunnel before the route is buried. The camera begins high above in a wide aerial view revealing snow peaks, sheer drops, and the winding road, then physically dives toward the car into a close tracking chase. It glides beside the doors, drops low near the spinning tires as snow sprays, rises overhead to reveal the avalanche rushing behind, then arcs outward into a high circling drone like view before descending again into a front facing backward tracking move. The shot remains seamless throughout as the car drifts around icy switchbacks, clips loose snow, and bursts toward the tunnel just ahead of the collapsing slope.

64,856 次观看

Video models are going to revolutionize education! You can turn your vision into a prompt and generate a learning experience that once required an entire production team. Made with HailuoAI MiniMax H3 Prompt ⤵️

Video models are going to revolutionize education! You can turn your vision into a prompt and generate a learning experience that once required an entire production team. Made with HailuoAI MiniMax H3 Prompt ⤵️

57,534 次观看

This is absolutely amazing with Flux 3’s split-screen rendering. More power to storytelling! Upscaled with Topaz Astra. Prompt : Split-screen video. Two equal vertical halves. Both halves show the SAME event, at the SAME time, frame-synchronized, filmed by two different cameras. SCENE: A quiet street, daytime. A long tall hedge wall runs along the sidewalk, too tall to see over. There is one narrow gap in the hedge ahead. A woman in a red jacket walks alone along the sidewalk on the near side of the hedge. On the FAR side of the hedge is an open grass field, where a large golden dog runs. LEFT HALF — CAMERA A: ground-level tracking shot on the sidewalk, following the woman from behind at shoulder height. IMPORTANT: from this camera, only the woman, the sidewalk, and the hedge wall are visible. The field, the dog, and anything behind the hedge are NEVER visible in the left half. The street looks calm and empty. RIGHT HALF — CAMERA B: aerial top-down drone shot, directly above, moving with the woman. This view shows BOTH sides of the hedge at once: the woman on the sidewalk, the hedge as a thin green line, and the golden dog sprinting across the field on the other side, on a converging path toward the gap in the hedge. ACTION — identical timing in both halves: 0–8s: The woman walks calmly. LEFT: peaceful, nothing unusual. RIGHT: the dog races closer and closer to the gap, its path and the woman's path clearly about to meet. 8–11s: The woman reaches the gap. The dog bursts through it. LEFT: the dog appears suddenly from nowhere, a total surprise; the woman flinches. RIGHT: the meeting looks perfectly predictable, two paths joining. 11–15s: The dog jumps up joyfully; it is her own dog greeting her. She laughs, kneels, and hugs it. Both halves show this ending. RULES: Same woman, same dog, same timing in both halves. The dog is visible ONLY in the right half until 8s. No cuts, no other people, no cars.

This is absolutely amazing with Flux 3’s split-screen rendering. More power to storytelling! Upscaled with Topaz Astra. Prompt : Split-screen video. Two equal vertical halves. Both halves show the SAME event, at the SAME time, frame-synchronized, filmed by two different cameras. SCENE: A quiet street, daytime. A long tall hedge wall runs along the sidewalk, too tall to see over. There is one narrow gap in the hedge ahead. A woman in a red jacket walks alone along the sidewalk on the near side of the hedge. On the FAR side of the hedge is an open grass field, where a large golden dog runs. LEFT HALF — CAMERA A: ground-level tracking shot on the sidewalk, following the woman from behind at shoulder height. IMPORTANT: from this camera, only the woman, the sidewalk, and the hedge wall are visible. The field, the dog, and anything behind the hedge are NEVER visible in the left half. The street looks calm and empty. RIGHT HALF — CAMERA B: aerial top-down drone shot, directly above, moving with the woman. This view shows BOTH sides of the hedge at once: the woman on the sidewalk, the hedge as a thin green line, and the golden dog sprinting across the field on the other side, on a converging path toward the gap in the hedge. ACTION — identical timing in both halves: 0–8s: The woman walks calmly. LEFT: peaceful, nothing unusual. RIGHT: the dog races closer and closer to the gap, its path and the woman's path clearly about to meet. 8–11s: The woman reaches the gap. The dog bursts through it. LEFT: the dog appears suddenly from nowhere, a total surprise; the woman flinches. RIGHT: the meeting looks perfectly predictable, two paths joining. 11–15s: The dog jumps up joyfully; it is her own dog greeting her. She laughs, kneels, and hugs it. Both halves show this ending. RULES: Same woman, same dog, same timing in both halves. The dog is visible ONLY in the right half until 8s. No cuts, no other people, no cars.

54,424 次观看

More experiments! Imagine turning a lesson idea into a fun, polished video with just a prompt. Video models like MiniMax H3 are making educational content creation easier and more creative than ever. Prompt ⤵️

More experiments! Imagine turning a lesson idea into a fun, polished video with just a prompt. Video models like MiniMax H3 are making educational content creation easier and more creative than ever. Prompt ⤵️

48,502 次观看

Prompt on Seedance 2 : Epic wide-angle shot of a vast ancient battlefield at golden hour, thousands of warriors clashing with swords and shields under a hazy amber sky thick with smoke and ash. A lone archer in weathered bronze armor, face streaked with dirt, draws a longbow with deliberate tension. The arrow releases with a sharp twang. Camera immediately snaps behind the arrow, tracking it in extreme slow motion as it cuts through drifting smoke and falling embers. Shallow depth of field keeps the arrow razor-sharp while the chaotic battlefield blurs behind. The camera pushes closer, tighter, until the wooden shaft fills the frame — revealing intricate carved runes and weathered grain. Seamless transition to macro scale: the arrow's surface becomes a landscape. A microscopic civilization of tiny warriors the size of splinters wages war across the fletching. Miniature catapults hurl fragments of dust. Warriors scale the carved runes like canyon walls. Torches flicker. Banners wave. All rendered with Made on Runway

Prompt on Seedance 2 : Epic wide-angle shot of a vast ancient battlefield at golden hour, thousands of warriors clashing with swords and shields under a hazy amber sky thick with smoke and ash. A lone archer in weathered bronze armor, face streaked with dirt, draws a longbow with deliberate tension. The arrow releases with a sharp twang. Camera immediately snaps behind the arrow, tracking it in extreme slow motion as it cuts through drifting smoke and falling embers. Shallow depth of field keeps the arrow razor-sharp while the chaotic battlefield blurs behind. The camera pushes closer, tighter, until the wooden shaft fills the frame — revealing intricate carved runes and weathered grain. Seamless transition to macro scale: the arrow's surface becomes a landscape. A microscopic civilization of tiny warriors the size of splinters wages war across the fletching. Miniature catapults hurl fragments of dust. Warriors scale the carved runes like canyon walls. Torches flicker. Banners wave. All rendered with Made on Runway

107,461 次观看

When the cat gets bored at night! Prompt ⤵️

When the cat gets bored at night! Prompt ⤵️

45,973 次观看

Wow! Wondering how much it would cost to make this video without AI. Prompt ⤵️

Wow! Wondering how much it would cost to make this video without AI. Prompt ⤵️

182,754 次观看

It’s incredible what’s possible to generate with just a prompt in a few minutes! The progress of video models is astonishing. Imagine the quality and accuracy in the next few years. Prompt ⬇️

It’s incredible what’s possible to generate with just a prompt in a few minutes! The progress of video models is astonishing. Imagine the quality and accuracy in the next few years. Prompt ⬇️

131,458 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

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

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

As surreal as it gets! Incredible prompt ⤵️

As surreal as it gets! Incredible prompt ⤵️

98,473 次观看 • 1 个月前

This entire 30-second ad was generated from just one image and one prompt! Prompt ⤵️

This entire 30-second ad was generated from just one image and one prompt! Prompt ⤵️

65,728 次观看 • 1 个月前

A1 is undeniably the new state-of-the-art for live avatars. Most avatars are limited to small, upper-body movements, but this Vivix.AI demo showcases real-time large full-body movements, environmental interaction, and strict object consistency. In this clip, the character instantly responds to prompts by executing dances and playful movements without any visual glitches. Because the conversation actually drives what happens next, the whole thing feels much more alive. Try it here:

A1 is undeniably the new state-of-the-art for live avatars. Most avatars are limited to small, upper-body movements, but this Vivix.AI demo showcases real-time large full-body movements, environmental interaction, and strict object consistency. In this clip, the character instantly responds to prompts by executing dances and playful movements without any visual glitches. Because the conversation actually drives what happens next, the whole thing feels much more alive. Try it here:

45,931 次观看 • 23 天前

Got early access to Kling 4.0 Flash! One of my first tries. Prompt understanding is awesome. Kling AI #Kling4 Prompt ⤵️

Got early access to Kling 4.0 Flash! One of my first tries. Prompt understanding is awesome. Kling AI #Kling4 Prompt ⤵️

37,221 次观看 • 19 天前

This entire 30-second video was created from a single image and one prompt! Prompt ⤵️

This entire 30-second video was created from a single image and one prompt! Prompt ⤵️

40,515 次观看 • 22 天前

Incredible disaster escape sequence prompt on Seedance 2.5 ⤵️

Incredible disaster escape sequence prompt on Seedance 2.5 ⤵️

18,182 次观看 • 11 天前

A complete 30-second destination film, generated from a single image and a single prompt! Prompt ⤵️

A complete 30-second destination film, generated from a single image and a single prompt! Prompt ⤵️

20,809 次观看 • 20 天前

This entire 30-second nature ad was generated from a single image! Prompt ⤵️

This entire 30-second nature ad was generated from a single image! Prompt ⤵️

28,449 次观看 • 29 天前

When the Earth has had enough! Incredible prompt ⤵️

When the Earth has had enough! Incredible prompt ⤵️

11,119 次观看 • 10 天前

No shoot. No storyboard. Just one image and one prompt. Prompt ⤵️

No shoot. No storyboard. Just one image and one prompt. Prompt ⤵️

23,511 次观看 • 27 天前

You don’t need thousands of dollars to make a cool promo ad! All it takes is the right prompt and a base image. This 30-second vlog-style ad was made using just a single image and a prompt. Prompt ⤵️

You don’t need thousands of dollars to make a cool promo ad! All it takes is the right prompt and a base image. This 30-second vlog-style ad was made using just a single image and a prompt. Prompt ⤵️

14,724 次观看 • 16 天前

Not using AI today is like living in the stone age, especially when it’s useful and relevant. Imagine the cost of producing this without AI. Prompt ⤵️

Not using AI today is like living in the stone age, especially when it’s useful and relevant. Imagine the cost of producing this without AI. Prompt ⤵️

39,603 次观看 • 2 个月前

This cute 30-second low-poly paper-craft video was made with just a single image and prompt! Prompt ⤵️

This cute 30-second low-poly paper-craft video was made with just a single image and prompt! Prompt ⤵️

13,841 次观看 • 18 天前

You can generate a 30-second short film in one shot using a single prompt and image references. Generated using Seedance 2.5 on Runway. Prompt ⤵️

You can generate a 30-second short film in one shot using a single prompt and image references. Generated using Seedance 2.5 on Runway. Prompt ⤵️

36,631 次观看 • 2 个月前

You can create short animated films with consistent characters in no time! I created this in less than an hour! The best part: everything is done on my smartphone! Tools used: Images: Story Illustrator App (MakeMyComics) Video: Hailuo AI Audio: ElevenLabs Editing: InShot Detailed workflow ⤵️

You can create short animated films with consistent characters in no time! I created this in less than an hour! The best part: everything is done on my smartphone! Tools used: Images: Story Illustrator App (MakeMyComics) Video: Hailuo AI Audio: ElevenLabs Editing: InShot Detailed workflow ⤵️

227,533 次观看 • 1 年前

One of the coolest prompts for Seedance 2.5 (30s) ! Prompt ⤵️

One of the coolest prompts for Seedance 2.5 (30s) ! Prompt ⤵️

22,394 次观看 • 2 个月前

City that comes alive! A mind bending prompt ⤵️

City that comes alive! A mind bending prompt ⤵️

13,227 次观看 • 1 个月前

Didn’t expect MiniMax Design to be this good! I just tried creating an animated short using a script and some reference images, and the result came out almost too good to be true. It worked like an agent designed specifically for filmmaking, breaking down the work, asking me to choose between options when needed, and reviewing the results along the way. It’s easily a great tool for commercial content work. #MiniMaxH3 on #MiniMaxDesign

Didn’t expect MiniMax Design to be this good! I just tried creating an animated short using a script and some reference images, and the result came out almost too good to be true. It worked like an agent designed specifically for filmmaking, breaking down the work, asking me to choose between options when needed, and reviewing the results along the way. It’s easily a great tool for commercial content work. #MiniMaxH3 on #MiniMaxDesign

16,241 次观看 • 1 个月前

Grok Extend is pretty cool. In this 20-second clip, the first 10-second render was only partly correct, but Extend used the same prompt and completed it.

Grok Extend is pretty cool. In this 20-second clip, the first 10-second render was only partly correct, but Extend used the same prompt and completed it.

40,426 次观看 • 7 个月前

What if your vehicle changed every 3 seconds?! This is so incredible.

What if your vehicle changed every 3 seconds?! This is so incredible.

14,833 次观看 • 2 个月前