📢MoRight: Motion Control Done Right "What if your video... model actually understood cause and effect?" Existing motion-controlled video models entangle camera and object motion, and treat everything as kinematic displacement. MoRight changes both. 🔥 Motion Causality — MoRight decomposes motion into actions & consequences. Give an action → MoRight predicts consequences (aka motion simulation) . Give a desired outcome → MoRight recovers the driving action (aka motion planning). Not merely displacing pixels. 🎬 Disentangled Control — MoRight separates camera and object motion, allowing users to independently control each of them. No entanglement. Project Page: Paper:show more

🎬 Motion Control has arrived! Take full control of... your AI videos with 12 dynamic camera shots — from smooth Dolly moves to dramatic Cranes and VFX like Explosions and Disintegration. Perfect for adding cinematic flare, stock footage, product ads, or just experimenting with storytelling. ✨ How it works: 1️⃣ Head to the new Video creation tool 2️⃣ Enter your prompt 3️⃣ Pick your camera shot from the Motion Control panel 4️⃣ (Optional) Add a Style or inspiration image as a start frame 💡Want extra consistency? Train an Element, generate your key stills, and animate them for a fully guided scene. More features are coming soon — including End Frames 👀 So stay tuned, and let us know what you create! 🎥 Lights, camera... Motion! Try it now on the Video page 👉🏻show more

Super excited about Hydra-0 from Hongyu Li and team!... The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.show more

Kling 2.6 Motion Control is absolutely insane 🤯 Take... any reference video and transfer the exact motion onto an AI character: full-body sync, facial expressions, hand gestures, everything. All with just a few clicks. Perfect for e-comm brands and agencies creating AI video ads that don't look like AI. Here's the problem: AI-generated video ads still look robotic. The movements are stiff, the expressions are flat. Your audience clocks it as AI instantly and keeps scrolling. Kling 2.6 Motion Control fixes it: → Start with any reference clip (stock footage, existing UGC, motion reference) → Upload to Kling → Map the exact movement onto any AI character → Full-body motion, hand gestures, facial expressions—all transferred → Generate up to 30 seconds of video No stiff AI movements, no uncanny valley, no instant "skip this ad" reaction. What this unlocks: - Use one winning UGC motion → swap in different AI creators - Pull reference clips from anywhere → generate branded variations - Create dynamic AI video ads with real human movement - Test multiple "creators" without filming anyone new I recorded a quick walkthrough showing how to do this step-by-step. Want access? > Comment "KLING" > Like this post And I'll send it over (must be following so I can DM)show more

🚀New paper out - We present Video-MSG (Multimodal Sketch... Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵show more

🔥 AI video creation is finally evolving beyond basic... motion prompts. Try out Depth Map Control right here: Historically, the hardest part of the process has been maintaining scene consistency: • camera movement • object placement • spatial relationships Thanks to PixVerse Depth Map Control, you can now grab depth data from a reference video and merge it with a fresh image to explore highly directed video generation. The final outcome? Much smoother camera tracking. Highly cohesive visual scenes. It is a powerful workflow that hands creators actual authority over how their AI visuals shift and flow over time. 🎬show more

MiniMax H3 is now on Magnific and honestly, there’s... a lot you can do with it. You can mix text, images, videos and audio in a single prompt up to 9 images, 3 videos and 3 audio references. Start creating now: It can generate up to 15s of 2K video with synced sound, including voice, music and effects. And you can go beyond generation too: edit clips, remove objects, transfer motion, and control the camera, character and voice. But the multi-reference workflow is probably my favorite. Give it your product, character, environment and motion references, and H3 pulls everything together. It feels like a much easier way to go from an idea to an actual finished video.show more

OSAKA If you want to turn these into a... video you can use this Seedance 2.0 prompt: Use the provided image board @[image1]. Do not treat the full grid as a single image. Treat each panel as a separate shot or cut, and animate them as a short nostalgic cinematic sequence. Bring each panel to life with smooth motion, subtle camera movement, soft transitions, and consistent subject, mood, lighting and style across all shots. No textshow more

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN... SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.show more

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN... SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.show more

Here are more results from #RigidFormer: predicting physical dynamics... with purely neural simulators — an attempt to learn physical dynamics in a scalable manner. 🤖 1) Controllable Articulated Body Simulation — More Results Additional Unitree G1 humanoid rollouts under controlled motion. Each sample uses a different initial state and control signal (direction and velocity). 🏺 2) Object Fragmentation Simulating the cracking and fragmentation process of objects. Thanks Žiga Kovačič for suggesting this experiment! 🎬 3) Combining Rigidformer with Diffusion-as-Shader for controllable video generation. Note: the meshes shown here are only for visualization — the network takes point clouds as input and predicts the updated state of each point.show more

Seedance 2.0 is officially LIVE on Pollo AI:)🚀 I... tried Seedance 2.0 on Pollo AI, and honestly—it’s a big upgrade. The motion feels much smoother, and generating audio + visuals together makes everything more polished and in sync. What stood out most is the control—you can tweak performance, lighting, and camera angles to level up your storytelling. 🔥 Plus, get 60% OFF for a limited time—perfect for anyone getting into AI video creation.show more

I believe that StoryDiffusion has the potential to be... Animatediff's complex motion sister-model! While AD is amazing for granular control, micro-motion and all kinds of abstract motion, it fails at complex realistic motion - walking, human movements, cars, etc. StoryDiffusion seems very promising for this + also has characteristics that will likely make the community very receptive to it and likely to extend its capabilities: 2) Appealing base-model results - likely to get the community excited - feels like significantly better realistic motion than AD 2) Modular - their approach is built with a number of components that can be combined and taken apart - it works by generating consistent images, then animating them together - each of these stages can likely be upgraded, used and influenced in different ways. 3) Flexible - they demonstrate a bunch of different conditioning options 4) Likely easy on RAM - it's based on SD 1.5 + authors mention precautions to reduce RAM consumption 5) Built to plug into the existing ecosystem - e.g. the fact that it works with the SD1.5 ecosystem will give it a huge advantage! While it's very early to say - e.g. the video model hasn't even been released yet! - it does seem very promising. With 9 months of SD1.5/Animatediff-esque progress improving every element of it, I can see an an extremely extended version of this beating Sora + running for a fraction of the compute resources on a consumer GPU. Together with Animatediff to drive the micro-motions and abstract stuff, it could produce be extraordinary/otherworldly/insane/beautiful stuff. This is the first open video model I've been excited about since Animatediff - though cautiously optimistic! Link here:show more

Seedance 2.0 is now LIVE on the Pollo AI... App (iOS & Android) I’ve actually tried Seedance 2.0 on Pollo AI, and I can say it’s a solid upgrade. The motion feels more natural, and having audio and visuals generated together makes the whole output more cohesive. What stood out for me most is the level of control — being able to adjust performance, lighting, and camera really changes how you approach storytelling. 🔥 Plus, grab 60% OFF for a limited time on Pollo AI! Perfect for anyone diving into AI video creation.show more

Rita AI now supports Seedance 2.0. If you're looking... for a platform that combines AI image generation, AI video generation, and workflow orchestration, this one is worth checking out. In addition to Seedance 2.0, it also supports Kling 3.0 and Motion Control, making dynamic camera moves, controllable motion, and video generation much easier. Link: I tested it with the following prompt, and the result felt very cinematic: A fearless young woman rides a skateboard at high speed through the crowded streets of New York City, weaving through pedestrians, darting past street vendors, yellow taxis, and cyclists with breathtaking agility. She rockets through intersections, skims past towering skyscrapers and iconic storefronts, and launches over curbs, street cracks, and scattered obstacles with stylish precision. Every movement feels bold, controlled, and exhilarating. Shot like a cinematic action sequence, the scene features fast-paced tracking shots, dramatic low-angle close-ups of the skateboard wheels scraping the asphalt, sweeping side-follow shots, and occasional slow-motion hero moments as she lands tricks and cuts through traffic. Dynamic motion blur heightens the sensation of speed, while golden hour sunlight bathes the city in a warm glow, reflecting off glass facades, metal surfaces, and the street below. Steam drifts from subway vents, traffic lights flicker, and the soundless visual energy of New York creates a pulsing urban backdrop. Ultra-realistic, intense, stylish, and immersive, with the visual tone of a high-end action film, capturing speed, confidence, danger, and freedom in the heart of the city.show more

You are not ready for how quickly the content... pipelines will change in 2026. This post isn't a gimmick. It's a heads up. This n8n automation alone can make you $50k/mo, and it's not a theory anymore. Arcads now lets you make any static image move like it was shot on camera. Subtle head turns, body sway, eye motion, emotion. Everything looks production-grade. Using Kling 2.6 motion control inside Arcads, you can turn any image into: → Influencer-style video clips → Smooth B-roll for ads → Emotional, lifelike portraits → High-end motion visuals in minutes Static creatives are about to feel very outdated. Here's the exact workflow: → Go to Arcads → Select Composer → Choose 'Animate Actor' → Upload a reference video → Upload a character image → Generate If you want to be a beast at content, media, attention, and distribution, this n8n should be worth thousands of dollars for you. But we're in the era of abundance, so I am giving it away for free. RT + comment "n8n" and I'll send it to you for free 📥show more

The video smooth zoom on the Samsung Galaxy S26... Ultra is still the closest thing to a professional camcorder experience in the smartphone industry today. In fact, it’s even easier to control than the iPhone. On many other phones, video zooming requires constant finger movement and very precise control. The zoom speed can easily become inconsistent, suddenly speeding up or slowing down. Samsung works differently. You simply hold your finger at a certain position, and the phone continues zooming at a constant speed. The entire process feels extremely stable and linear. It genuinely resembles the powered zoom control of a professional video camera. This logic is fundamentally related to Samsung’s AI slow motion technology. They share the same core foundation: real time control over motion trajectories, speed transitions, and frame interpolation. What you’re seeing here was shot in very windy conditions using Samsung’s Pro Video mode, continuously zooming from 5x to 25x. Aside from some slight stutter during optical lens switching points, the continuous zoom transition within digital zoom ranges is arguably the closest thing to a professional camera currently available on a smartphone. So if the future Samsung Galaxy S27 Ultra really removes the 3x telephoto camera, it could actually improve the video zoom experience further. Fewer optical switching points would theoretically reduce transition jumps and stutters, making the entire zoom range feel even more natural and continuous.show more

MiniMax H3 is now 50% OFF on Magnific for... 2K video, only until September 1. 🔥 I’ve been trying MiniMax H3 on Magnific, and it feels like a big upgrade for AI video creation. It’s not just about turning text into videos. You can use text, images, videos, and audio together in one prompt, giving you more control over the final video. Here’s what makes it stand out: - Multimodal: Use text, images, video, and audio in one prompt. - Multiple references: Add up to 9 images, 3 videos, and 3 audio files. - 2K video: Create videos up to 15 seconds long. - Built-in sound: Generate voice, music, and sound effects with the video. - Easy editing: Remove objects or transfer motion easily. - More control: Control the camera, characters, and voice. You can use it to turn posters into videos, moodboards into short films, and product images into ads. It also helps bring your ideas to life with realistic movement, lighting, reflections, and sound. The workflow is simple: give it your references → generate → edit → refine. Try MiniMax H3 on Magnific:show more

MiniMax H3 Character Introduction Prompt: Use @[char ref] as... the sole character reference. Preserve the exact identity, face, body proportions, hairstyle, outfit, colors, materials and overall silhouette of the character throughout the entire video. Do not redesign, simplify or replace any defining visual features. Create a cinematic character introduction focused on presence, silhouette, attitude and controlled motion. 0–4s Begin with a close shot of a defining lower-body or detail element such as boots, shoes, feet, hands, clothing hem or an important accessory. The character enters frame or settles into position. The camera slowly tracks upward while hair, clothing and secondary elements move naturally in the wind or environment. 4–8s Reveal more of the body with a medium or medium-wide shot from the back, side or three-quarter angle. The character stands in a calm, composed way inside the environment. The camera makes a smooth orbit, arc or lateral move to gradually reveal the character’s face and silhouette. 8–12s Move into a tight cinematic portrait or upper-body shot. The character performs one subtle signature action that fits their personality, such as lifting the chin, turning the head, adjusting clothing, brushing hair aside, opening a hand, looking toward camera, or shifting posture. Keep the motion minimal and intentional. The expression should match the character’s vibe. 12–15s End with a strong full-body hero shot that clearly presents the entire design and silhouette. Use a low-angle, eye-level or slightly dramatic framing depending on the character’s personality. The character settles into a natural final pose and holds it confidently for a clean final reveal. VISUAL DIRECTION Premium cinematic presentation. Match the visual medium and rendering style of @[char ref]. Emphasize clean silhouette, elegant staging, subtle secondary motion, believable hair and cloth movement, strong composition, atmospheric depth and polished lighting. The scene should feel like a high-end anime, game or film character introduction. CAMERA Use a clear progression from detail reveal to partial reveal to face reveal to full-body hero reveal. Camera movement should be smooth, controlled and intentional. Avoid chaotic motion. ENVIRONMENT Place the character in a fitting environment that supports their identity and mood. The background should enhance the character without distracting from them.show more

HOLY SH*T, THE WIRING FROM A DEAD FLY’S BRAIN... IS NOW DRIVING A TINY ROBOT. not a simulation trapped inside a computer. a physical machine receiving camera input and turning it into movement. scientists reconstructed a fly brain containing: 166,700 neurons roughly 125 million synapses the circuits behind vision, motion and behavior developers then built a loop: camera frame → modeled neural activity → movement command → robot turns, walks or avoids an obstacle the camera supplies the pixels. the fly’s neural wiring decides which pixels matter. this does not mean the fly was revived. the robot is not conscious. it does not understand its surroundings. and there is no tiny mind trapped inside the machine. but the control system is based on biological wiring that evolution spent millions of years refining. the fly is dead. its solution to movement is now walking around in another body. I broke down how 166,700 neurons became a physical controller below ↓show more

Two flames rise. Neither will yield. Midjourney + GPT... Image 2 + Seedance 2.0 Instead of treating each storyboard panel as an individual shot, grouped them into consecutive motion phrases. This allows the video to flow through the key poses rather than stopping at every panel, with cuts occurring only at the boundaries between phrases. The camera preserves the physical direction and momentum of the action as it moves through the panel compositions, making the sequence feel like a continuous sakuga choreography rather than a slideshow of storyboard frames. You can check the prompts in the replies.show more