Nano is a depth-aware atmospheric haze plugin that uses... ML depth estimation to add physically accurate fog and light scattering to your footage. Works *best* on log footage with visible light sources - it analyzes scene highlights then creates airlight (atmospheric scatter) and halation (light bloom) that responds to actual depth in the scene. Pretty clever approach to getting that cinematic haze look without having to pump a fog machine on set. Makes the OG Trapcode Shine look extremely dated (basically 2D light streaks masked by luminance values), and is yet way more controllable than the current crop of generative AI video-to-video tools.show more

If you use curves on a gray canvas to... make the highlights, and then blur according to the proximity of the light source, the skin will look much smoother and realistic 🩷 With that simple step your 2D art will look more 3D!show more

Depth Any Video with Scalable Synthetic Data AI physicists... and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.show more

Seedance 2.0 is now live on our website. ⚠️... Warning: The following video is extremely unsettling. If you’re sensitive to horror content, consider watching without sound or skipping it. prompt： one-take cinematic horror scene, old apartment hallway at night, one young woman holding a phone light, slow tracking shot, tense silence. first step: ceiling light suddenly goes out, brief blackout, light returns, hallway seems normal. second step: light goes out again, slightly longer blackout, faint strange sound, light returns, bathroom door is now more open, her breathing becomes faster. third step: she hesitates in fear, then takes one more step, longest blackout, eerie low laugh in darkness, light snaps back on, a pale inhuman figure is suddenly standing motionless directly in front of her face, intense dread, cut to black. realistic, oppressive, restrained, psychological horror, cold green and dirty yellow lighting, shallow depth of field, film grain, high-end horror movie quality.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

Video diffusion models have strong implicit representations of 3D... shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.show more

Depth video workflows have been getting a lot of... attention lately, so I tested one myself. Combined with Seedance 2.0, it produced more natural motion-transfer results than using Kling Motion Control directly. Why use a depth video? 1. It removes the original character and scene details, reducing copyright and sensitive-content risks. 2. It preserves the original motion, timing, and spatial structure. This separates motion extraction from visual generation, allowing you to recreate the movement with better models and any reference character. We’ve also launched a free online tool that converts regular videos into depth videos—no local setup required: In the example below, we converted a dance video from Douyin into a depth video, then regenerated it with a reference character using Seedance 2.0. The original choreography and timing are preserved, while the lighting adapts naturally to the new character and scene.show more

FSD 12.5 runs a red light I want to... share this to have a healthy discussion regarding this situation. This isn't in anyway an attempt to hate on FSD 12.5, I still believe this is the best release of FSD so far. Yesterday on my drive FSD for the first time ever (for me) decided to proceed on a VERY stale (red?) light. I was a bit surprised about its decision to do this, and I am wondering if perhaps the traffic light being set back (before the intersection starts there's a light on my left) has anything to do with this? Technically the car passes the light/stop line as it is still yellow. As a human driver I may have proceeded on this light if I was in a rush, but I am not sure if a robotaxi should make that same decision. Tesla AI ΛI DRIVR Dirty Tesla Sawyer Merritt Elon Musk Nick Arek Sredzki Srihari Sampathkumar Any opinons on this folks?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

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

A'TIN, you truly understood the assignment. 💙💜 As thousands... of ELESBI lights illuminated the MOA Arena, a breathtaking sea of purple came to life—each light symbolizing unwavering support, shared dreams, and a love that continues to grow stronger with every milestone. This glow is more than a tribute to SB19. It's a celebration of OPM, a testament to the power of music, and proof that when A'TIN stands united, they can light up not just an arena, but an entire movement. Tonight, the ocean is purple, shining with pride, passion, and the collective spirit of a fandom that continues to make its mark on the OPM scene. ✨💜 OWN THE MOMENT SB19 SB19 Official #SB19 Watsons Philippines #SB19atWatsonsPlaylist2026 #WatsonsPlaylist2026 #OwnTheMoment #WatsonsPH #ASWatson185show more

Come with all your shame, come with your swollen... heart. I have never seen anything more beautiful than you. Bring the scars that sting and the nights that felt too long. Bring the trembling hands and the tears that fell in silence. Every broken piece is a note in a song only you could sing, Every quiet fear is a light waiting to be seen. Do not hide, do not apologize, do not shrink. I will meet you here, where the world does not judge Where your weight is not a burden but a testament, to the depth you carry and the strength you cannot yet name. Come as you are, raw and unafraid, for in your presence I find a beauty that has no mirror.show more

🚨 SCIENTISTS JUST SHOWED THAT LIGHT CAN TWIST MATTER... USING ITS MAGNETIC FIELD. For a long time, physicists assumed the magnetic component of light was far too weak to have any meaningful effect on matter compared to its electric field. New experiments are challenging that view. Researchers have demonstrated that intense, properly structured light can induce magnetization and even mechanical twisting in materials through its magnetic field alone. This is an extension of the inverse Faraday effect, but observed with greater strength and control than many expected. Why this matters: • It opens new ways to control magnetism and material properties using only light • Could lead to faster, more energy-efficient magnetic memory and spintronic devices • Offers a new tool for manipulating matter at the nanoscale without physical contact • Bridges optics and magnetism in ways that were previously difficult to achieve The deeper implication: Light is not just an information carrier under the right conditions, its magnetic field can directly reshape the magnetic and mechanical state of matter. This blurs the line between electromagnetic waves and material control. If these effects can be scaled and made practical, we may eventually use light itself as a precise tool to write magnetic information or mechanically actuate tiny structures, rather than relying solely on electric currents or physical forces. We’re discovering that light still has hidden capabilities we haven’t fully exploited. How do you think being able to control matter with light’s magnetic field could change technology in the next decade? Follow for more frontier optics, quantum materials, and light-matter physics.show more

Some updates on the multiview vistadream pipeline with Rerun!... Rerun came in extremely useful here, as being able to visualize depths at each stage of the pipeline allowed me to debug some nasty bugs. Since the last time, I was only working with a single image input. I've added in VGGT as my multiview pose + depth estimator. It works REALLY well for getting camera poses, but the depths are not that great. To try and fix that, I estimated depth maps from MoGeV2 for each of the views, and scale+shift aligned them so that they would match up to the confident sections of VGGT's depth predictions. You can see in the video just how much sharper the visualized 2d depth maps are! The biggest issue continues to be the multiview consistency 🫠 That's up next, along with actually training the Gaussian splat. Lots of work went into actually understanding inputs+outputs for VGGT. I had some funky bugs where the confidence values would all collapse to true I'm also really excited for this pipeline to use Difix3D+ Nvidia instead of Flux Inpainting, it seems like a better suited for a multiview pipeline.show more

Today, we launched Karuna in Hyderabad with Jishnu Dev... Varma, Hon’ble Governor of Telangana. When you hold this book in your hands, I hope you feel both fire and light—a spark of motivation and a deep sense of responsibility. Karuna is not just a book to be read; it is a call to action. A reminder that compassion must be shared to truly grow. I also had the privilege of an in-depth conversation with Professor @ShantaSinha1 at the Hyderabad Literature Fest today.show more

The Panama alien meteorite story is still alive! (Pardon... the pun). Despite saying it was for entertainment, then removing that reference and a subsequent video that said he was forced to say it wasn't real (both deleted), he's posting more and saying the 'creature' has now outgrown the safe. This video is one of his latest, showing it moving in the freezer. It seems pretty hokey, once you increase the brightness of the video (which I did in the second clip), but that's the update. He continues with extremely low light video conditions (red flag numbers #1-459) Entertainment? Absolutely. Real? Doubt it. But MILLIONS continue to watch on...show more

The Universe marvels at quasars, not at human beings... — not out of arrogance, but because we have not yet learned to shine, neither physically nor humanely. : The author imagines the Universe gazing in awe at quasars, those blazing engines of light and power, while passing over humanity without a second glance. Not from cosmic arrogance, but from quiet truth. We have not yet learned to shine. Physically, we remain dim: our reach is still confined to one small world, our energy faint against the galaxy’s roar. Humanely, we are even dimmer. Wars, cruelty, indifference dull the light we could emit. Quasars burn with unrelenting brilliance. Humanity flickers. The marvel is withheld not as punishment but as invitation. The Universe waits for us to grow bright enough to deserve its wonder. We can shine physically by mastering the stars, turning matter into sustained light across the void. We can shine humanely by making compassion, justice, and care the default of our kind. When both lights burn steady, the Universe will look at us the way it looks at quasars. Until then, the silence is patient. The invitation remains open.show more

When a nuclear reactor powers on for the first... time, the core fills with a deep blue glow that feels almost unreal as it rises through the water in a quiet surge of energy. The light is Cherenkov radiation, created when charged particles move through the water faster than light can travel in that medium, a discovery made in the 1930s that revealed a new way to see high energy reactions. Every appearance of this glow is a reminder of how powerful atomic reactions can be, showing a rare moment where raw physics becomes something visible and strangely beautiful.show more

cmon... this is so fun. Prompt here if you... want to steal it: Continuous shot with no scene cuts. Camera is traveling forward between trees kanopes and different things are on the tree branches. The light is low, it comes through tall trees and the foliage of leaves casts an interesting patterned shadow and light on to the scene. First we see a tamarin monkey looking very close to the lens, mostly it's face is visible and on of the hand trying to reach through the lens, then a man on his laptop in brown suit and yellow ties with red baseball hat, then a yellow giant snake around a branch, we see the texture of the snake and it's wet skin from a macro view. Then an orangutan taking a selfie then lanterns hanging from the branches then a bunch an area where fluffy clouds mixing with the tree leafs where a plane wreck is smoking and slightly on fire. Handheld documentary style. Natural camera shake. Raw indie film aesthetic. Heavy grain. Natural lighting only. Unpolished, authentic look. Low budget realism. Observational feel.show more

“Pure heart” is the key to ascension and immortality... in every religion. So how can you purify your heart? It’s easier said than done, but the most important thing is the following... In ancient Egypt, the heart needed to be lighter than a feather in order to achieve the immortal Akh. And what makes your heart heavy? What makes you feel pressure in your chest and abdomen, and what makes your heart float with butterflies in your stomach? Holding grudges, hatred, jealousy, etc. makes you anxious, and you feel it in your heart, while the opposite feelings, love, forgiveness, and understanding, make you feel light. The most important thing that you can do to make your heart light is forgiveness. As God is forgiving, you also need to forgive, and you need to seek forgiveness. That is the key to making your heart lighter than a feather. In ancient Egypt, if the heart, part of the soul, was heavier than the feather of Maat, the creature Ammit would devour the heart and the soul. If it was lighter, then the part of the soul known as Ba would merge with the life force Ka and achieve the immortal Akh.show more