Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Do you remember that famous hallway sequence from Oldboy? I did something similar, but in anime style and with monsters. What you can do with Kling 2.6 is absolutely spectacular. Prompt: Chaotic anime corridor fight, narrow space overrun with grotesque creatures, close-quarters brutality, elbows, kicks and blades striking at... show more

OscarAI

57,941 subscribers

72,102 views • 9 months ago •via X (Twitter)

Comedy Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

3D $ANIME ? Using 3D in anime or a complete series in 3D style, how does this affect the anime industry? Probably the most hated anime after which people hated 3D in anime was Berserk in 2016, it was really terrible, but 3D in anime is no longer what it was in 2010-20. Let's look at the pros and cons of 3D in anime and what series can be called good 3D anime Pros of 3D Animation: 🟢Dynamic camera angles & smooth motion 🟢Saves time & production costs 🟢Consistent character proportions Cons of 3D Animation: 🔴Can look stiff or "plastic" 🔴Limited facial expressions 🔴Often disliked by traditional anime fans Top 3D $ANIME series in my opinion: 🔵Houseki no Kuni – stunning visuals & fluid animation 🔵Dorohedoro – dark, gritty style perfectly fits CGI 🔵Beastars – expressive character animation 🔵Trigun: Stampede – cinematic action & high-quality CGI The best studio that combines 2D and 3D well is, I think, Ufotable Ufotable blends 2D & 3D seamlessly: 🟡3D backgrounds + 2D character animation 🟡Anime-style shading makes 3D look hand-drawn 🟡Frame-by-frame touch-ups for smooth motion 🟡Mixing 2D effects (fire, water) with 3D for impact Example: "Demon Slayer" – epic battle scenes like Tanjiro’s Water Breathing, using 3D camera movement while preserving 2D aesthetics. Which 3D $ANIME impressed you the most?

3D $ANIME ? Using 3D in anime or a complete series in 3D style, how does this affect the anime industry? Probably the most hated anime after which people hated 3D in anime was Berserk in 2016, it was really terrible, but 3D in anime is no longer what it was in 2010-20. Let's look at the pros and cons of 3D in anime and what series can be called good 3D anime Pros of 3D Animation: 🟢Dynamic camera angles & smooth motion 🟢Saves time & production costs 🟢Consistent character proportions Cons of 3D Animation: 🔴Can look stiff or "plastic" 🔴Limited facial expressions 🔴Often disliked by traditional anime fans Top 3D $ANIME series in my opinion: 🔵Houseki no Kuni – stunning visuals & fluid animation 🔵Dorohedoro – dark, gritty style perfectly fits CGI 🔵Beastars – expressive character animation 🔵Trigun: Stampede – cinematic action & high-quality CGI The best studio that combines 2D and 3D well is, I think, Ufotable Ufotable blends 2D & 3D seamlessly: 🟡3D backgrounds + 2D character animation 🟡Anime-style shading makes 3D look hand-drawn 🟡Frame-by-frame touch-ups for smooth motion 🟡Mixing 2D effects (fire, water) with 3D for impact Example: "Demon Slayer" – epic battle scenes like Tanjiro’s Water Breathing, using 3D camera movement while preserving 2D aesthetics. Which 3D $ANIME impressed you the most?

Kvintestar⛩️ Anime Artist

15,666 views • 1 year ago

Gemini Omni's motion control is f*cking cracked i just figured out how to turn 1 reference video into 50+ AI videos with the exact same movements... you have a video of someone eating, dancing, using a product, doing whatever complex motion you need. you feed it to Gemini Omni and it recreates that exact motion with a completely new AI character in literally one prompt i've tested this against Kling motion control and it's not even close. Kling falls apart the moment you try anything complex. eating scenes look weird, hand movements get mangled, anything multi-step breaks down completely. Gemini Omni handles all of it if you're still using kling motion control or paying creators to split test your videos, this replaces that entire workflow here's the thing though. you can't just prompt this out of the box. if you try to do motion transfer with default prompting you're going to get errors or the motion won't transfer properly. there's a specific prompting method that makes it work every time so i packaged up the whole system.. here's what you're getting: > full step by step video breakdown > how to find the best reference videos to use > the exact prompting system that allows for motion control transfer so you never get errors > the workflow for batching this out at scale (1 video → 50+) RT + reply "MOTION" and i'll send it over (must follow so i can dm)

Gemini Omni's motion control is f*cking cracked i just figured out how to turn 1 reference video into 50+ AI videos with the exact same movements... you have a video of someone eating, dancing, using a product, doing whatever complex motion you need. you feed it to Gemini Omni and it recreates that exact motion with a completely new AI character in literally one prompt i've tested this against Kling motion control and it's not even close. Kling falls apart the moment you try anything complex. eating scenes look weird, hand movements get mangled, anything multi-step breaks down completely. Gemini Omni handles all of it if you're still using kling motion control or paying creators to split test your videos, this replaces that entire workflow here's the thing though. you can't just prompt this out of the box. if you try to do motion transfer with default prompting you're going to get errors or the motion won't transfer properly. there's a specific prompting method that makes it work every time so i packaged up the whole system.. here's what you're getting: > full step by step video breakdown > how to find the best reference videos to use > the exact prompting system that allows for motion control transfer so you never get errors > the workflow for batching this out at scale (1 video → 50+) RT + reply "MOTION" and i'll send it over (must follow so i can dm)

Miko

61,633 views • 2 months ago

He picked the wrong baddie to mess with. Made with seedance 2.5 Prompt : Create a 13-second ultra-realistic cinematic action sequence set inside a messy, atmospheric urban apartment/studio filled with books, posters, scattered furniture, old equipment and warm practical lamps. Two young women in realistic casual streetwear are engaged in an intense hand-to-hand fight. Begin with a wide establishing shot showing the entire room as the confrontation starts. One woman suddenly attacks with a long wooden object, while the other quickly blocks and dodges the attack. Build the sequence with fast, believable choreography: blocking, punches, evasive movements, close-range grappling, aggressive shoves and a powerful takedown. The fighters should move naturally with realistic weight, balance and physical impact. Clothing, hair and bodies should react naturally to every movement. Use dynamic handheld cinematic camera movement, alternating between wide shots, medium tracking shots, low-angle shots and tight close-ups during impacts. Add subtle camera shake and realistic motion blur during fast movements, but keep the characters clearly visible. The room should remain consistent throughout the sequence. Bright cool daylight streams through large windows while warm orange lamps illuminate parts of the room, creating a gritty cinematic teal-and-orange contrast. Use realistic shadows, volumetric light, dust particles and reflections on the slightly polished floor. Toward the final seconds, the fight becomes more intense. One woman loses balance and is thrown to the floor. The other remains standing in the foreground, breathing heavily and maintaining a strong defensive stance as the camera settles into a dramatic final shot. Ultra-realistic human movement, authentic fight choreography, detailed facial expressions, natural skin texture, realistic hair physics, cinematic depth of field, 35mm film look, high dynamic range, realistic motion blur, dramatic practical lighting, premium Hollywood action-film cinematography, no cartoon look, no exaggerated physics, no unnatural body deformation.

He picked the wrong baddie to mess with. Made with seedance 2.5 Prompt : Create a 13-second ultra-realistic cinematic action sequence set inside a messy, atmospheric urban apartment/studio filled with books, posters, scattered furniture, old equipment and warm practical lamps. Two young women in realistic casual streetwear are engaged in an intense hand-to-hand fight. Begin with a wide establishing shot showing the entire room as the confrontation starts. One woman suddenly attacks with a long wooden object, while the other quickly blocks and dodges the attack. Build the sequence with fast, believable choreography: blocking, punches, evasive movements, close-range grappling, aggressive shoves and a powerful takedown. The fighters should move naturally with realistic weight, balance and physical impact. Clothing, hair and bodies should react naturally to every movement. Use dynamic handheld cinematic camera movement, alternating between wide shots, medium tracking shots, low-angle shots and tight close-ups during impacts. Add subtle camera shake and realistic motion blur during fast movements, but keep the characters clearly visible. The room should remain consistent throughout the sequence. Bright cool daylight streams through large windows while warm orange lamps illuminate parts of the room, creating a gritty cinematic teal-and-orange contrast. Use realistic shadows, volumetric light, dust particles and reflections on the slightly polished floor. Toward the final seconds, the fight becomes more intense. One woman loses balance and is thrown to the floor. The other remains standing in the foreground, breathing heavily and maintaining a strong defensive stance as the camera settles into a dramatic final shot. Ultra-realistic human movement, authentic fight choreography, detailed facial expressions, natural skin texture, realistic hair physics, cinematic depth of field, 35mm film look, high dynamic range, realistic motion blur, dramatic practical lighting, premium Hollywood action-film cinematography, no cartoon look, no exaggerated physics, no unnatural body deformation.

Noor 🌸

14,473 views • 3 days ago

Bitcoin is going to RALLY so VIOLENTLY that Greg from three doors down walks over holding the leaf blower he financed at 26.99 percent APR to ask you, with genuine curiosity, what a satoshi is. So violently that the HOA letter about your mailbox color arrives and you frame it. So violently that the guy who called it tulips in 2017 opens every sentence at the block party with "well, I always said the technology itself was interesting." So violently that your Target Date 2055 fund, which parked 41 percent of your one life in bonds because an actuary in Malvern decided you were fragile, finally gets to rest. So violently that Applebee's 2 for $25 becomes a story you tell your grandchildren and they assume you are describing a prison. So violently that men in their forties feel something real in the Menards rebate aisle and have to sit in the truck for a minute with the engine off. So violently that someone laughs out loud in the Q3 all hands when they say "we're like a family here," and instead of getting fired he becomes the CEO. So violently that the $7,400 deductible your employer calls a High Deductible Health Plan With A Savings Component gets cleared in the time it takes to microwave a Hot Pocket. So violently that your brother in law, who has explained blockchain to you at four consecutive Thanksgivings while holding a Coors Light and getting it wrong in a new way each time, texts you at 2:14 a.m. asking how Coinbase works. So violently that the entire Stanley tumbler economy vaporizes in a single afternoon and the resale market moves to eBay, where it belongs. So violently that the boomer who bought his house in 1987 for $61,000 and calls you entitled becomes extremely interested in what exactly it is you do for work. So violently that "just 11 more years and I retire at 67" dissolves into the air alongside the Wells Fargo $12 monthly maintenance fee, which they waive if you maintain a $1,500 average daily balance, a sentence 1 human wrote and 7 humans approved. So violently that the 78 month auto loan joins leeches and the draft in the museum of things we agreed to when we were confused. So violently that Chase mails you a pre-approved Sapphire offer and you use it as a coaster in a house you own outright. The middle class was always a payment plan with a lifestyle stapled to the front. You read the prepayment clause. It was blank. Stay humble. Stack sats.

Bitcoin is going to RALLY so VIOLENTLY that Greg from three doors down walks over holding the leaf blower he financed at 26.99 percent APR to ask you, with genuine curiosity, what a satoshi is. So violently that the HOA letter about your mailbox color arrives and you frame it. So violently that the guy who called it tulips in 2017 opens every sentence at the block party with "well, I always said the technology itself was interesting." So violently that your Target Date 2055 fund, which parked 41 percent of your one life in bonds because an actuary in Malvern decided you were fragile, finally gets to rest. So violently that Applebee's 2 for $25 becomes a story you tell your grandchildren and they assume you are describing a prison. So violently that men in their forties feel something real in the Menards rebate aisle and have to sit in the truck for a minute with the engine off. So violently that someone laughs out loud in the Q3 all hands when they say "we're like a family here," and instead of getting fired he becomes the CEO. So violently that the $7,400 deductible your employer calls a High Deductible Health Plan With A Savings Component gets cleared in the time it takes to microwave a Hot Pocket. So violently that your brother in law, who has explained blockchain to you at four consecutive Thanksgivings while holding a Coors Light and getting it wrong in a new way each time, texts you at 2:14 a.m. asking how Coinbase works. So violently that the entire Stanley tumbler economy vaporizes in a single afternoon and the resale market moves to eBay, where it belongs. So violently that the boomer who bought his house in 1987 for $61,000 and calls you entitled becomes extremely interested in what exactly it is you do for work. So violently that "just 11 more years and I retire at 67" dissolves into the air alongside the Wells Fargo $12 monthly maintenance fee, which they waive if you maintain a $1,500 average daily balance, a sentence 1 human wrote and 7 humans approved. So violently that the 78 month auto loan joins leeches and the draft in the museum of things we agreed to when we were confused. So violently that Chase mails you a pre-approved Sapphire offer and you use it as a coaster in a house you own outright. The middle class was always a payment plan with a lifestyle stapled to the front. You read the prepayment clause. It was blank. Stay humble. Stack sats.

Adam Livingston

53,067 views • 21 days ago

The world sees beauty first. She makes you remember the strength behind it. GPT Image 2 + Seedance 2.0 on @thankyouai_hq prompt A cinematic, high-intensity fight sequence in a dark, gritty industrial warehouse at night with dim overhead lights, green peeling walls, chain-link fences, metal scaffolding, and scattered debris. A beautiful East Asian woman with long flowing black hair, visible facial scratches and intense determined expressions, is engaged in a raw, dynamic hand-to-hand combat against a male attacker in dark clothing. She wears a delicate, flowing baby pink dress (instead of her original jacket) that contrasts dramatically with the violent action — the soft pink fabric billows, swirls, and tears slightly during the fierce movements, hair whipping wildly. The sequence includes: close-ups of her fierce face and flowing hair, powerful punches and kicks with motion blur, grappling, throwing the man down, dramatic spins, hair flips, kneeling over the defeated attacker, then rising victoriously while breathing heavily. Moody teal-green color grading, realistic particle effects like dust and fabric motion, intense choreography, dramatic camera angles (handheld, tracking shots, low angles), high detail, filmic lighting, 4K cinematic quality, emotional and empowering tone. write hook captions for this

The world sees beauty first. She makes you remember the strength behind it. GPT Image 2 + Seedance 2.0 on @thankyouai_hq prompt A cinematic, high-intensity fight sequence in a dark, gritty industrial warehouse at night with dim overhead lights, green peeling walls, chain-link fences, metal scaffolding, and scattered debris. A beautiful East Asian woman with long flowing black hair, visible facial scratches and intense determined expressions, is engaged in a raw, dynamic hand-to-hand combat against a male attacker in dark clothing. She wears a delicate, flowing baby pink dress (instead of her original jacket) that contrasts dramatically with the violent action — the soft pink fabric billows, swirls, and tears slightly during the fierce movements, hair whipping wildly. The sequence includes: close-ups of her fierce face and flowing hair, powerful punches and kicks with motion blur, grappling, throwing the man down, dramatic spins, hair flips, kneeling over the defeated attacker, then rising victoriously while breathing heavily. Moody teal-green color grading, realistic particle effects like dust and fabric motion, intense choreography, dramatic camera angles (handheld, tracking shots, low angles), high detail, filmic lighting, 4K cinematic quality, emotional and empowering tone. write hook captions for this

Sharon Riley

65,849 views • 2 months ago

Phoebe Chibi can fight really well Made with Seedance 2.0 on Yapper Tutorial below 👇🏻 Prompt Cinematic 15-Second WuWa-Style Anime Video Prompt (With Cut Scenes) Highly detailed 15-second video in the visual style of Wuthering Waves anime 3D gameplay. Vibrant, high-saturation color palette with glowing teal, purple, gold, and electric blue accents. Strong cinematic bloom, particle effects, motion trails, and dynamic lighting. Smooth 60fps, 4K resolution, vertical format (9:16). Fast-paced meme edit with clean transitions, slow-motion beats, subtle screen shake, and stylized VFX. PART 1 (0–4s) — Exploration + Soft HookWide cinematic shot of an anime-style female character standing on a glowing open-world cliff at sunset. Wind flows through her hair and outfit, particles floating in the air.Cut → tracking shot as she begins running forward, light trails forming behind her 2.4s: soft Korean-style “ee ee” voice plays as she tilts her head slightly, subtle cute expression. PART 2 (4–8s) — Action Build-UpCut → mid-air dash sequence with dynamic camera following from behind.Cut → side angle slow-motion as she flips and draws her weapon, glowing energy forming around it.Cut → close-up of her eyes sharpening with focus, reflections of neon particles intensify, environment reacting with slight distortion. PART 3 (8–12.7s) — Power MomentCut → wide combat shot as she unleashes a flashy ability, spinning with bright teal and purple energy trails.Cut → top-down shot showing circular AoE effects expanding outward.Cut → slow-motion impact moment with bloom lighting and screen shake.Everything builds visually toward a peak. PART 4 (12.7–13.5s) — Punchline ShiftSudden tonal switch.Close-up zoom on her face with exaggerated cute expression.Warm pastel overlay replaces previous dramatic 12.7s: voice line “hah baby jovi” plays, synced with a slight head bob and playful eye movement. PART 5 (13.5–15s) — Meme Loop EndingCut → chibi-style or softened version of the character.She makes a silly or adorable expression (puffed cheeks or blink loop).Text or subtle bounce animation.Voice repeats: “baby chubi baby chubi” in sync with rhythmic head movement. Overall Style NotesSeamless quick cuts (every 0.5–1.5s), energetic pacing, balanced mix of cinematic and meme humor.Strong contrast between epic action build-up and cute comedic payoff.Consistent lighting transitions from dramatic neon to soft pastel at the punchline. #WutheringWaves #流萤 #Firefly #ホタル #HonkaiStarRail📷 #崩壊スターレイル #AIイラスト #AIart️️️️️️️️️️️️️️️️️️️️️ #ArknightsEndfield #phoebechibi #seedance2

Phoebe Chibi can fight really well Made with Seedance 2.0 on Yapper Tutorial below 👇🏻 Prompt Cinematic 15-Second WuWa-Style Anime Video Prompt (With Cut Scenes) Highly detailed 15-second video in the visual style of Wuthering Waves anime 3D gameplay. Vibrant, high-saturation color palette with glowing teal, purple, gold, and electric blue accents. Strong cinematic bloom, particle effects, motion trails, and dynamic lighting. Smooth 60fps, 4K resolution, vertical format (9:16). Fast-paced meme edit with clean transitions, slow-motion beats, subtle screen shake, and stylized VFX. PART 1 (0–4s) — Exploration + Soft HookWide cinematic shot of an anime-style female character standing on a glowing open-world cliff at sunset. Wind flows through her hair and outfit, particles floating in the air.Cut → tracking shot as she begins running forward, light trails forming behind her 2.4s: soft Korean-style “ee ee” voice plays as she tilts her head slightly, subtle cute expression. PART 2 (4–8s) — Action Build-UpCut → mid-air dash sequence with dynamic camera following from behind.Cut → side angle slow-motion as she flips and draws her weapon, glowing energy forming around it.Cut → close-up of her eyes sharpening with focus, reflections of neon particles intensify, environment reacting with slight distortion. PART 3 (8–12.7s) — Power MomentCut → wide combat shot as she unleashes a flashy ability, spinning with bright teal and purple energy trails.Cut → top-down shot showing circular AoE effects expanding outward.Cut → slow-motion impact moment with bloom lighting and screen shake.Everything builds visually toward a peak. PART 4 (12.7–13.5s) — Punchline ShiftSudden tonal switch.Close-up zoom on her face with exaggerated cute expression.Warm pastel overlay replaces previous dramatic 12.7s: voice line “hah baby jovi” plays, synced with a slight head bob and playful eye movement. PART 5 (13.5–15s) — Meme Loop EndingCut → chibi-style or softened version of the character.She makes a silly or adorable expression (puffed cheeks or blink loop).Text or subtle bounce animation.Voice repeats: “baby chubi baby chubi” in sync with rhythmic head movement. Overall Style NotesSeamless quick cuts (every 0.5–1.5s), energetic pacing, balanced mix of cinematic and meme humor.Strong contrast between epic action build-up and cute comedic payoff.Consistent lighting transitions from dramatic neon to soft pastel at the punchline. #WutheringWaves #流萤 #Firefly #ホタル #HonkaiStarRail📷 #崩壊スターレイル #AIイラスト #AIart️️️️️️️️️️️️️️️️️️️️️ #ArknightsEndfield #phoebechibi #seedance2

Sharon Riley

12,700 views • 5 months ago

How do you turn a scene idea into a Prompt? All you need to do is roughly describe what's in your head to an LLM. It doesn't have to be perfect or highly detailed. Once it understands the core idea, it can help turn it into a well-structured prompt. In my case, I use a custom skill file that I built myself. After I provide the idea, it generates both a storyboard and video prompts for me. I then review the outputs and refine them through iteration, giving feedback like "make this shot wider," "change this action," or "move the camera here." After a few rounds of adjustments, I usually arrive at the final result. The process is much closer to directing than writing a perfect prompt from scratch. The Idea: Two characters face each other. Serenity fights like a Wing Chun master. She unleashes a rapid barrage of punches into Ruk's abdomen. The fight should feel highly energetic and sakuga-driven, with exaggerated action beats and dynamic choreography. Use 14 panels. The final attack should show Serenity launching high into the sky, then diving straight down at extreme speed. She lands with both feet on Ruk's head, driving him deep into the ground and burying him on impact. All other scenes should be equally creative and visually inventive. Emphasize fast pacing, flash cuts, burst cuts, sudden perspective changes, dramatic impact moments, and imaginative camera angles. Use aggressive screen direction, strong momentum shifts, dynamic framing, and escalating choreography to create a thrilling, high-energy martial arts sequence. This is the final video, you can check the prompts in the replies. Used tools: Midjourney, Codex, GPT Image 2, Seedance 2.0, Suno, Capcut

How do you turn a scene idea into a Prompt? All you need to do is roughly describe what's in your head to an LLM. It doesn't have to be perfect or highly detailed. Once it understands the core idea, it can help turn it into a well-structured prompt. In my case, I use a custom skill file that I built myself. After I provide the idea, it generates both a storyboard and video prompts for me. I then review the outputs and refine them through iteration, giving feedback like "make this shot wider," "change this action," or "move the camera here." After a few rounds of adjustments, I usually arrive at the final result. The process is much closer to directing than writing a perfect prompt from scratch. The Idea: Two characters face each other. Serenity fights like a Wing Chun master. She unleashes a rapid barrage of punches into Ruk's abdomen. The fight should feel highly energetic and sakuga-driven, with exaggerated action beats and dynamic choreography. Use 14 panels. The final attack should show Serenity launching high into the sky, then diving straight down at extreme speed. She lands with both feet on Ruk's head, driving him deep into the ground and burying him on impact. All other scenes should be equally creative and visually inventive. Emphasize fast pacing, flash cuts, burst cuts, sudden perspective changes, dramatic impact moments, and imaginative camera angles. Use aggressive screen direction, strong momentum shifts, dynamic framing, and escalating choreography to create a thrilling, high-energy martial arts sequence. This is the final video, you can check the prompts in the replies. Used tools: Midjourney, Codex, GPT Image 2, Seedance 2.0, Suno, Capcut

Kōda

23,805 views • 3 months ago

Seedance 2.0 1080p Infinite Fight Scenes From One Prompt Created a parametric prompt for epic fight scenes. You can generate unlimited variations just by changing the parameters. Tested one generation in 1080p with Seedance 2.0 on Higgsfield. More examples with prompts are in the replies. Prompt Template: FORMAT: 15s / continuous fight CHARACTERS A: [character_A] B: [character_B] ENVIRONMENT [short description] FIGHT PROFILE STYLE: [brutal / elegant / tactical / chaotic / cinematic] ENERGY: [low / medium / high / explosive] WEAPONS: [none / melee / mixed] INTENT: [duel / assassination / survival / dominance / training] VISUAL Cinematic realism, physical lighting, shallow DOF, subtle grain, natural motion blur. DIRECTIVE No fixed choreography. Fight emerges dynamically from characters, environment, and momentum. BEHAVIOR - Use environment freely (walls, ground, objects) - Allow verticality (climb, wall-run, elevation shifts) - Encourage unexpected but physically valid actions RULES - Momentum chain only, no isolated actions - Clear positioning at all times - Continuous, motivated camera (POV / OTS / wide / low-high as needed) - Environment actively reacts (splashes, debris, sparks) IMPACT Strong contacts: 2-frame hold + brightness spike + micro shake resume MOTION Secondary delay (~2 frames) on hair, fabric, environment. RHYTHM Fast exchanges + micro pauses + 1–2 slow-motion beats (0.5–1s) ESCALATION Intensity rises. Include: - one vertical/environment-driven move - one decisive high-impact action HERO MOMENT (CRITICAL) Generate one standout finishing beat: - visually dominant, clearly readable - uses environment or full-body motion - slow-motion entry → sharp impact → brief aftermath hold - ends with strong silhouette or positional advantage GUARDRAILS - Keep character identity and position consistent (no teleporting) - Respect weight and inertia (no floaty or impossible motion) - Ensure clear cause → effect in every action - Keep camera readable and motivated (no random spins or cuts) - Use environment logically (no clipping or mismatch) - Prioritize clarity and physical realism over complexity OUTPUT Fluid, physical, cinematic fight with clear spatial logic, dynamic camera, environmental interaction, and a memorable final highlight moment.

Kōda

46,065 views • 5 months ago

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)

@levelsio

711,384 views • 1 month ago

If you think this is just another silly demo made with AI, read this post. You might change your mind, because this demo is about MATH. What you see on the screen is not a render from Blender (obviously, it’s not that good). It’s a three.js app built with Toolcraft. Available on the web and rendered in real time(link in the comments). But Blender still has a lot to do with it. Blender has Geometry Nodes - a powerful node-based system for creating and manipulating procedural geometry. In other words, it’s math. And math is a universal language. And who do you think is pretty good at math? >>> AI. Now you can download or buy Blender files from marketplaces, and when they contain Geometry Nodes for procedural animations, objects, surfaces, or effects, you can transfer that logic to the web. Make it real-time, make it interactive. Materials are a separate story, of course. They can still suck unless you use the right tricks: PBR, HDRIs, material blending, displacement, and faked surface relief. So why is Blender important here? Blender is open source, and many tools around it are open source too. An AI trained on their code. That means it can translate the math from one environment to another quite accurately. If you’ve been struggling to reproduce some idea with AI that you had in your head or seen in some references, and it has something to do with Geometry Nodes, and you can find that idea or a close one in the Blender ecosystem - it means you can transfer it to the web. Thank me later.

If you think this is just another silly demo made with AI, read this post. You might change your mind, because this demo is about MATH. What you see on the screen is not a render from Blender (obviously, it’s not that good). It’s a three.js app built with Toolcraft. Available on the web and rendered in real time(link in the comments). But Blender still has a lot to do with it. Blender has Geometry Nodes - a powerful node-based system for creating and manipulating procedural geometry. In other words, it’s math. And math is a universal language. And who do you think is pretty good at math? >>> AI. Now you can download or buy Blender files from marketplaces, and when they contain Geometry Nodes for procedural animations, objects, surfaces, or effects, you can transfer that logic to the web. Make it real-time, make it interactive. Materials are a separate story, of course. They can still suck unless you use the right tricks: PBR, HDRIs, material blending, displacement, and faked surface relief. So why is Blender important here? Blender is open source, and many tools around it are open source too. An AI trained on their code. That means it can translate the math from one environment to another quite accurately. If you’ve been struggling to reproduce some idea with AI that you had in your head or seen in some references, and it has something to do with Geometry Nodes, and you can find that idea or a close one in the Blender ecosystem - it means you can transfer it to the web. Thank me later.

Alex Barashkov

28,300 views • 2 months ago

Made with Seednace 2 on OpenArt Prompt: CAMERA: Handheld DV 16mm camcorder aesthetic, first-person/selfie POV. CHASE always holds the camera. Natural hand shake, imperfect framing, delayed autofocus, clumsy zooms, occasional face cropping. The camcorder is never visible. LOOK: Soft vintage DV tape quality with slight blur, subtle tape noise, mild highlight bloom, flickering auto-exposure, muted contrast, natural skin tones. STYLE: Bright, playful K-pop idol vlog. Genuine smiles, eye contact, candid energy, quick handheld shots with backstage excitement. CHARACTER: CHASE, Korean female idol in her 20s. Long straight black hair, dewy skin, elegant Korean features, coral lips, large eyes, slim curvy figure. Wearing a stylish stage outfit with subtle glam makeup and sparkly earrings. SETTING: Backstage hallway of a music show studio with dressing room doors, CHASE's name tag on one door, snack table, overhead PA speaker, and blurred staff passing by. SEQUENCE: 1. Selfie: peeks into the hallway. "Hey guys, we're backstage!" 2. Whip pan down the corridor. "This hallway is so long!" 3. Stops at her dressing room, points at her name tag. "That's me!" 4. Close-up of the name tag as she taps it. Ambient audio only. 5. Quick outfit check with a spin near a mirror. "How do I look?" 6. At the snack table, grabs a snack. "Don't mind if I do." 7. Mid-bite, PA announcement interrupts. She laughs: "Wait—" 8. Selfie ending: hears the countdown, waves, makes a hand heart, then runs toward the stage. "That's my cue—see you after the stage!"

Made with Seednace 2 on OpenArt Prompt: CAMERA: Handheld DV 16mm camcorder aesthetic, first-person/selfie POV. CHASE always holds the camera. Natural hand shake, imperfect framing, delayed autofocus, clumsy zooms, occasional face cropping. The camcorder is never visible. LOOK: Soft vintage DV tape quality with slight blur, subtle tape noise, mild highlight bloom, flickering auto-exposure, muted contrast, natural skin tones. STYLE: Bright, playful K-pop idol vlog. Genuine smiles, eye contact, candid energy, quick handheld shots with backstage excitement. CHARACTER: CHASE, Korean female idol in her 20s. Long straight black hair, dewy skin, elegant Korean features, coral lips, large eyes, slim curvy figure. Wearing a stylish stage outfit with subtle glam makeup and sparkly earrings. SETTING: Backstage hallway of a music show studio with dressing room doors, CHASE's name tag on one door, snack table, overhead PA speaker, and blurred staff passing by. SEQUENCE: 1. Selfie: peeks into the hallway. "Hey guys, we're backstage!" 2. Whip pan down the corridor. "This hallway is so long!" 3. Stops at her dressing room, points at her name tag. "That's me!" 4. Close-up of the name tag as she taps it. Ambient audio only. 5. Quick outfit check with a spin near a mirror. "How do I look?" 6. At the snack table, grabs a snack. "Don't mind if I do." 7. Mid-bite, PA announcement interrupts. She laughs: "Wait—" 8. Selfie ending: hears the countdown, waves, makes a hand heart, then runs toward the stage. "That's my cue—see you after the stage!"

WasifAI

281,799 views • 2 months ago

MiniMax H3 Instead of sharing the prompts for each of these videos, I thought it would be more useful to share how I created that prompts. All of the videos were generated with text-to-video. First, find an image with the kind of scene, composition and mood you want to recreate. I used a few YouTube playlist thumbnails as references but Pinterest is also a great place to find inspiration. You can even use your own old or nostalgic photographs. Then upload the image to ChatGPT and ask it to describe the scene. The description it gives you can essentially become your text-to-video prompt. From there, you can generate completely new scenes with a similar composition, atmosphere and cinematic language. You can of course use the reference image directly with image-to-video or as a first frame. But if the original image isn't yours, I prefer using it only as visual inspiration and recreating the scene through text-to-video. This is the prompt I use with ChatGPT: "Describe the scene in this image in English, focusing primarily on what is happening, the characters, their actions and body language, the setting and the overall atmosphere. Also briefly describe the composition, framing, camera angle, approximate lens choice, lighting, color palette and cinematic aesthetic. Keep it concise and scene-focused rather than overly technical."

MiniMax H3 Instead of sharing the prompts for each of these videos, I thought it would be more useful to share how I created that prompts. All of the videos were generated with text-to-video. First, find an image with the kind of scene, composition and mood you want to recreate. I used a few YouTube playlist thumbnails as references but Pinterest is also a great place to find inspiration. You can even use your own old or nostalgic photographs. Then upload the image to ChatGPT and ask it to describe the scene. The description it gives you can essentially become your text-to-video prompt. From there, you can generate completely new scenes with a similar composition, atmosphere and cinematic language. You can of course use the reference image directly with image-to-video or as a first frame. But if the original image isn't yours, I prefer using it only as visual inspiration and recreating the scene through text-to-video. This is the prompt I use with ChatGPT: "Describe the scene in this image in English, focusing primarily on what is happening, the characters, their actions and body language, the setting and the overall atmosphere. Also briefly describe the composition, framing, camera angle, approximate lens choice, lighting, color palette and cinematic aesthetic. Keep it concise and scene-focused rather than overly technical."

Kōda

55,398 views • 1 month ago

Thank you Anna Ann YuDan(🦄,🦄) for the magical evening 🦄🌈 Great pleasure to chat with BULL 0xAndy.eth and Michelle from X Layer (indeed looking interesting to expand our ICM ecosystem into alongside BNB Chain), and what moved me the most was Ann’s sincere and heartfelt talk: “The reason why I have been putting myself into this, is because I have something that I really want to do.” “I want to build something truly meaningful, with people who believe in me, and our shared ideals.” Keep going Ann 💜 The journey of pursuing dream and ideals may be filled with trails and tears, but one thing I can assure you, is that we will never be alone in this journey. Keep shining keep building, keep following your heart and kindred spirits will gather around and shape the better world we envision together. Even in this industry. Idealism and longtermism will win. I truly believe that. “For the future beyond our imagination.”🦄🌈

Thank you Anna Ann YuDan(🦄,🦄) for the magical evening 🦄🌈 Great pleasure to chat with BULL 0xAndy.eth and Michelle from X Layer (indeed looking interesting to expand our ICM ecosystem into alongside BNB Chain), and what moved me the most was Ann’s sincere and heartfelt talk: “The reason why I have been putting myself into this, is because I have something that I really want to do.” “I want to build something truly meaningful, with people who believe in me, and our shared ideals.” Keep going Ann 💜 The journey of pursuing dream and ideals may be filled with trails and tears, but one thing I can assure you, is that we will never be alone in this journey. Keep shining keep building, keep following your heart and kindred spirits will gather around and shape the better world we envision together. Even in this industry. Idealism and longtermism will win. I truly believe that. “For the future beyond our imagination.”🦄🌈

Natsuki Freya

20,821 views • 11 months ago

Seedance 2.0 on Nadoupro Prompt: "CAMERA: Handheld DV 16mm camcorder aesthetic, first-person/selfie POV. CHASE always holds the camera. Natural hand shake, imperfect framing, delayed autofocus, clumsy zooms, occasional face cropping. The camcorder is never visible. LOOK: Soft vintage DV tape quality with slight blur, subtle tape noise, mild highlight bloom, flickering auto-exposure, muted contrast, natural skin tones. STYLE: Bright, playful K-pop idol vlog. Genuine smiles, eye contact, candid energy, quick handheld shots with backstage excitement. CHARACTER: CHASE, Korean female idol in her 20s. Long straight black hair, dewy skin, elegant Korean features, coral lips, large eyes, slim curvy figure. Wearing a stylish stage outfit with subtle glam makeup and sparkly earrings. SETTING: Backstage hallway of a music show studio with dressing room doors, CHASE's name tag on one door, snack table, overhead PA speaker, and blurred staff passing by. SEQUENCE: 1. Selfie: peeks into the hallway. "Hey guys, we're backstage!" 2. Whip pan down the corridor. "This hallway is so long!" 3. Stops at her dressing room, points at her name tag. "That's me!" 4. Close-up of the name tag as she taps it. Ambient audio only. 5. Quick outfit check with a spin near a mirror. "How do I look?" 6. At the snack table, grabs a snack. "Don't mind if I do." 7. Mid-bite, PA announcement interrupts. She laughs: "Wait—" 8. Selfie ending: hears the countdown, waves, makes a hand heart, then runs toward the stage. "That's my cue—see you after the stage!""

Seedance 2.0 on Nadoupro Prompt: "CAMERA: Handheld DV 16mm camcorder aesthetic, first-person/selfie POV. CHASE always holds the camera. Natural hand shake, imperfect framing, delayed autofocus, clumsy zooms, occasional face cropping. The camcorder is never visible. LOOK: Soft vintage DV tape quality with slight blur, subtle tape noise, mild highlight bloom, flickering auto-exposure, muted contrast, natural skin tones. STYLE: Bright, playful K-pop idol vlog. Genuine smiles, eye contact, candid energy, quick handheld shots with backstage excitement. CHARACTER: CHASE, Korean female idol in her 20s. Long straight black hair, dewy skin, elegant Korean features, coral lips, large eyes, slim curvy figure. Wearing a stylish stage outfit with subtle glam makeup and sparkly earrings. SETTING: Backstage hallway of a music show studio with dressing room doors, CHASE's name tag on one door, snack table, overhead PA speaker, and blurred staff passing by. SEQUENCE: 1. Selfie: peeks into the hallway. "Hey guys, we're backstage!" 2. Whip pan down the corridor. "This hallway is so long!" 3. Stops at her dressing room, points at her name tag. "That's me!" 4. Close-up of the name tag as she taps it. Ambient audio only. 5. Quick outfit check with a spin near a mirror. "How do I look?" 6. At the snack table, grabs a snack. "Don't mind if I do." 7. Mid-bite, PA announcement interrupts. She laughs: "Wait—" 8. Selfie ending: hears the countdown, waves, makes a hand heart, then runs toward the stage. "That's my cue—see you after the stage!""

Saul Goodman

17,307 views • 2 months ago

I show you my new model before bed, Aria Monroe 🔥💛 you already saw her but I will show you her more times from today😉ps:better doesn’t make her angry!😅👇🏻 Good night, sleep well!✨ GPT Image 2.0 and Seedance 2.0 Mini 🎬 👉🏻Subscribe for more content⚡️ Video Prompt: Cinematic Korean action sequence in a narrow sunlit urban alleyway lined with brick buildings, air conditioning units, wooden pallets, and a prominent GS25 convenience store. A young athletic woman with long blonde hair tied in a high ponytail wears a form-fitting pink long-sleeve athletic crop top with a deep square neckline and matching fitted pink athletic leggings paired with clean pink athletic sneakers. Her face, neck, and upper chest have a light sheen of sweat, emphasizing that she has just finished training, while her expression remains calm, focused, and determined. She faces a group of aggressive young men wearing black tracksuits and hoodies. Without hesitation, she charges forward using precise, powerful martial arts techniques with lightning-fast punches, spinning kicks, elbow strikes, knee attacks, sweeps, and perfectly executed throws, taking down each attacker one by one with fluid, realistic choreography. The handheld camera follows closely through the narrow alley with dynamic movement, subtle camera shake, realistic motion blur, and rapid perspective shifts that heighten the intensity of every impact. Bodies crash onto the pavement as the fight escalates with cinematic momentum. In the background, three Korean schoolgirls in neat school uniforms stand near the GS25 entrance, watching the confrontation in stunned silence. Bright natural daylight casts crisp shadows across the brick walls and stacked wooden pallets, highlighting dust, debris, and realistic environmental details. The sequence concludes as the final attacker collapses beside the stacked pallets. The woman pauses, calmly adjusts her fighting stance, straightens her pink athletic crop top, and confidently walks away down the sunlit alley. Hyper-realistic live-action style, Korean action film aesthetic, high-energy choreography, sharp facial detail, physically accurate movement, cinematic handheld camera work, natural lighting, realistic textures, and feature-film quality.

I show you my new model before bed, Aria Monroe 🔥💛 you already saw her but I will show you her more times from today😉ps:better doesn’t make her angry!😅👇🏻 Good night, sleep well!✨ GPT Image 2.0 and Seedance 2.0 Mini 🎬 👉🏻Subscribe for more content⚡️ Video Prompt: Cinematic Korean action sequence in a narrow sunlit urban alleyway lined with brick buildings, air conditioning units, wooden pallets, and a prominent GS25 convenience store. A young athletic woman with long blonde hair tied in a high ponytail wears a form-fitting pink long-sleeve athletic crop top with a deep square neckline and matching fitted pink athletic leggings paired with clean pink athletic sneakers. Her face, neck, and upper chest have a light sheen of sweat, emphasizing that she has just finished training, while her expression remains calm, focused, and determined. She faces a group of aggressive young men wearing black tracksuits and hoodies. Without hesitation, she charges forward using precise, powerful martial arts techniques with lightning-fast punches, spinning kicks, elbow strikes, knee attacks, sweeps, and perfectly executed throws, taking down each attacker one by one with fluid, realistic choreography. The handheld camera follows closely through the narrow alley with dynamic movement, subtle camera shake, realistic motion blur, and rapid perspective shifts that heighten the intensity of every impact. Bodies crash onto the pavement as the fight escalates with cinematic momentum. In the background, three Korean schoolgirls in neat school uniforms stand near the GS25 entrance, watching the confrontation in stunned silence. Bright natural daylight casts crisp shadows across the brick walls and stacked wooden pallets, highlighting dust, debris, and realistic environmental details. The sequence concludes as the final attacker collapses beside the stacked pallets. The woman pauses, calmly adjusts her fighting stance, straightens her pink athletic crop top, and confidently walks away down the sunlit alley. Hyper-realistic live-action style, Korean action film aesthetic, high-energy choreography, sharp facial detail, physically accurate movement, cinematic handheld camera work, natural lighting, realistic textures, and feature-film quality.

KeorUnreal

18,346 views • 1 month ago

Would you fight for your survival? Made by using Nano Banana 2 + Seedance 2.0 on TapNow prompt A dynamic, cinematic action sequence in a futuristic sci-fi arena with sleek metallic walls, geometric concrete barriers, glowing blue holographic elements, and dramatic god rays streaming through large windows creating haze and lens flares. A beautiful Western woman with long wavy blonde hair in a high ponytail, fair skin, athletic build, wearing a fitted white tank top and black leggings, is fighting multiple advanced humanoid combat robots with shiny silver armor and glowing blue visors/eyes. Start with a medium close-up of her standing confidently facing camera, robots positioned behind her in formation. Cut to fast-paced action: she sprints and dodges at high speed through the arena (motion blur), leaps and performs acrobatic maneuvers. Intense hand-to-hand combat — she punches and kicks robots, creating bright sparks and metal debris. She disarms a robot, grabs its large futuristic rifle, and fires back while evading. Quick cuts between close combat, wide tracking shots, and slow-motion impacts. Climax shows her standing victorious in the center of the arena as defeated robots lie broken and smoking on the floor around her, dramatic low-angle wide shot with strong backlighting and atmospheric smoke. High-energy, Hollywood-style action like Atomic Blonde meets sci-fi, 8-second loopable clip, realistic lighting, detailed textures, 4K cinematic quality.

Would you fight for your survival? Made by using Nano Banana 2 + Seedance 2.0 on TapNow prompt A dynamic, cinematic action sequence in a futuristic sci-fi arena with sleek metallic walls, geometric concrete barriers, glowing blue holographic elements, and dramatic god rays streaming through large windows creating haze and lens flares. A beautiful Western woman with long wavy blonde hair in a high ponytail, fair skin, athletic build, wearing a fitted white tank top and black leggings, is fighting multiple advanced humanoid combat robots with shiny silver armor and glowing blue visors/eyes. Start with a medium close-up of her standing confidently facing camera, robots positioned behind her in formation. Cut to fast-paced action: she sprints and dodges at high speed through the arena (motion blur), leaps and performs acrobatic maneuvers. Intense hand-to-hand combat — she punches and kicks robots, creating bright sparks and metal debris. She disarms a robot, grabs its large futuristic rifle, and fires back while evading. Quick cuts between close combat, wide tracking shots, and slow-motion impacts. Climax shows her standing victorious in the center of the arena as defeated robots lie broken and smoking on the floor around her, dramatic low-angle wide shot with strong backlighting and atmospheric smoke. High-energy, Hollywood-style action like Atomic Blonde meets sci-fi, 8-second loopable clip, realistic lighting, detailed textures, 4K cinematic quality.

Sharon Riley

32,759 views • 2 months ago

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.

Dheepan Ratnam

46,015 views • 6 months ago