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.

Workflow explained by Creative Multi-Dimensional Specialist, Tony Hou: This short was created with the AI powered 3D workflow which utilized traditional 3D processes and Luma’s Ray3.14 Modify video. We are at a point where AI integration is no longer a binary but is flexible to the artist’s needs. This... show more

Luma | Dream Lab

3,363 subscribers

31,553 views • 7 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This might be the craziest workflow you'll see this week. From #VR greyboxing to 3D worlds with the help of #AI. The 2 tools I used are ShapesXR and Marble from World Labs. Let me tell you why and how. - ShapesXR is the most powerful and fastest way to assemble 3D scenes at scale. - The library of assets + ability to sketch from procedural primitives gives the perfect balance between speed and freedom. - ShapesXR allows you to export your creation as a glTF that can be used as a "3D prompt" into Marble - Marble now allows you to create a panorama using a 3D scene as input increasing DRAMATICALLY the control you have during the creation process - Through the workflow you can adjust textures and objects in the scene using AI inpainting - There are tons of options on how to use the final output (create a #GaussianSplatting, export collision mesh and even a detailed mesh 🤯) This is the perfect examples of how VR creative tools improve and accelerate the design process... so make sure to follow me if that's your jam 😉.

This might be the craziest workflow you'll see this week. From #VR greyboxing to 3D worlds with the help of #AI. The 2 tools I used are ShapesXR and Marble from World Labs. Let me tell you why and how. - ShapesXR is the most powerful and fastest way to assemble 3D scenes at scale. - The library of assets + ability to sketch from procedural primitives gives the perfect balance between speed and freedom. - ShapesXR allows you to export your creation as a glTF that can be used as a "3D prompt" into Marble - Marble now allows you to create a panorama using a 3D scene as input increasing DRAMATICALLY the control you have during the creation process - Through the workflow you can adjust textures and objects in the scene using AI inpainting - There are tons of options on how to use the final output (create a #GaussianSplatting, export collision mesh and even a detailed mesh 🤯) This is the perfect examples of how VR creative tools improve and accelerate the design process... so make sure to follow me if that's your jam 😉.

Gabriele Romagnoli

20,126 views • 10 months ago

A level of realism you could never achieve with traditional 3d. A level of control you could never get with text to video. This is the type of workflows I'm most excited about.. the type that allows us to paint, sculpt, act and direct worlds into existence.

A level of realism you could never achieve with traditional 3d. A level of control you could never get with text to video. This is the type of workflows I'm most excited about.. the type that allows us to paint, sculpt, act and direct worlds into existence.

Martin Nebelong

49,301 views • 1 year ago

Here's a look behind the scenes of how I used a 3d model, generated from an image, as a "driver" for ai animation. In the near future we'll see more 3d tools that support these types of workflows, with much more emphasis on enhancing user input instead of just letting the ai do everything. I used the 3d model to generate keyframes that I then animated in Luma Dream. By using a 3d model with a diffusion "layer" done with Krea, I got quite high quality frames with a relatively high consistency as well since the AI didn't have to "hallucinate" that much. I upscaled and detailed the frames using Magnific. Using semi-detailed 3d models as drivers for gen ai is very powerful, and it allows us to use models that are sculpted in a more free-flowing type of workflow that doesn't rely so much on high surface detailing or very time-consuming finish, but instead relies more on gestural 3d sculpting. #art #ai

Here's a look behind the scenes of how I used a 3d model, generated from an image, as a "driver" for ai animation. In the near future we'll see more 3d tools that support these types of workflows, with much more emphasis on enhancing user input instead of just letting the ai do everything. I used the 3d model to generate keyframes that I then animated in Luma Dream. By using a 3d model with a diffusion "layer" done with Krea, I got quite high quality frames with a relatively high consistency as well since the AI didn't have to "hallucinate" that much. I upscaled and detailed the frames using Magnific. Using semi-detailed 3d models as drivers for gen ai is very powerful, and it allows us to use models that are sculpted in a more free-flowing type of workflow that doesn't rely so much on high surface detailing or very time-consuming finish, but instead relies more on gestural 3d sculpting. #art #ai

Martin Nebelong

48,280 views • 2 years ago

Googles Omni Flash model is such a great combination with Dreams 3d artwork. For most of the generations here, simple prompts like these were all it took: "Wrap the video in stark realism" or "Wrap the video in the realism of the provided image". Reposting with the correct edit of the video. Ai workflows that allows us to push, pull, shape and move elemenrs around. Like clay, but powered by underlying world knowledge.. that's why I was excited about generative ai from the beginning - because I know there's plenty of room for us to raise the ceiling in our creative tools and workflows . I know I've been pushing this type of workflows for years and it's pretty crazy to see that the Ai systems we use are now at a level where this sort of workflow seems to be within reach.

Googles Omni Flash model is such a great combination with Dreams 3d artwork. For most of the generations here, simple prompts like these were all it took: "Wrap the video in stark realism" or "Wrap the video in the realism of the provided image". Reposting with the correct edit of the video. Ai workflows that allows us to push, pull, shape and move elemenrs around. Like clay, but powered by underlying world knowledge.. that's why I was excited about generative ai from the beginning - because I know there's plenty of room for us to raise the ceiling in our creative tools and workflows . I know I've been pushing this type of workflows for years and it's pretty crazy to see that the Ai systems we use are now at a level where this sort of workflow seems to be within reach.

Martin Nebelong

12,408 views • 3 months ago

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 views • 1 year ago

🚀 React Server Components are coming to every platform with Expo Router! To showcase all the new possibilities, I wrote the most powerful demo AI app I could think of—took less than a day to write, and it runs everywhere! Unlike traditional AI apps, which stream plain-text, Expo RSC can server render interactive native views and animations. This is the future of mobile apps.

🚀 React Server Components are coming to every platform with Expo Router! To showcase all the new possibilities, I wrote the most powerful demo AI app I could think of—took less than a day to write, and it runs everywhere! Unlike traditional AI apps, which stream plain-text, Expo RSC can server render interactive native views and animations. This is the future of mobile apps.

Evan Bacon 🥓

170,925 views • 2 years ago

I tried to see how far I could push my current AI + 3D workflow and build a playable 3D game prototype in just 3 days😶 Not by asking AI to make the whole game in one prompt. I had my own idea, knew what I wanted to build, and used AI as a tool: - for concepting, - asset generation & texturing, - gameplay logic with the new UE 5.8 MCP + Claude Code. And honestly, it is crazy how far you can get now with the right workflow. Full video - #UE5 #ClaudeCode #AI3D #3DAI

I tried to see how far I could push my current AI + 3D workflow and build a playable 3D game prototype in just 3 days😶 Not by asking AI to make the whole game in one prompt. I had my own idea, knew what I wanted to build, and used AI as a tool: - for concepting, - asset generation & texturing, - gameplay logic with the new UE 5.8 MCP + Claude Code. And honestly, it is crazy how far you can get now with the right workflow. Full video - #UE5 #ClaudeCode #AI3D #3DAI

Stefan 3D AI

21,406 views • 2 months ago

$Traditional coffee commercials usually cost $20,000–$80,000+, need studios, full crews, and days of filming. This one: just a simple cup of coffee turned into a premium commercial with Ima Studio ☕ No cameras. No expensive production. Just pure AI-powered creativity — finished fast and at a fraction of the cost. While traditional ads are still stuck in the old expensive workflow… This is how high-quality commercials get mass-produced today. Officially joining the Ima Studio Challenge and competing for a share of the $10,000 USD prize pool. Try Ima Studio → Join the challenge → Would you believe this was made with AI? 👀 #ImaStudio #GAICSeason2 #AICommercial #Coffee #ContentCreation$

Traditional coffee commercials usually cost $20,000–$80,000+, need studios, full crews, and days of filming. This one: just a simple cup of coffee turned into a premium commercial with Ima Studio ☕ No cameras. No expensive production. Just pure AI-powered creativity — finished fast and at a fraction of the cost. While traditional ads are still stuck in the old expensive workflow… This is how high-quality commercials get mass-produced today. Officially joining the Ima Studio Challenge and competing for a share of the $10,000 USD prize pool. Try Ima Studio → Join the challenge → Would you believe this was made with AI? 👀 #ImaStudio #GAICSeason2 #AICommercial #Coffee #ContentCreation

Sadia

185,161 views • 1 month ago

🇺🇸DAVID FRIEDBERG: AI VIDEO GENERATORS ARE SET TO CHANGE ENTERTAINMENT 'Genesis renders the actual 3D objects into a 3D environment rather than rendering a two-dimensional set of pixels to look like a video. Suddenly, you can actually render in real-time: a video game, a movie, a visual experience. And it goes to this point that we're unleashing the capacity for human imagination and creativity with these systems because it's no longer just a look-a-like 2-dimensional image. Source: The All-In Podcast, david friedberg

🇺🇸DAVID FRIEDBERG: AI VIDEO GENERATORS ARE SET TO CHANGE ENTERTAINMENT 'Genesis renders the actual 3D objects into a 3D environment rather than rendering a two-dimensional set of pixels to look like a video. Suddenly, you can actually render in real-time: a video game, a movie, a visual experience. And it goes to this point that we're unleashing the capacity for human imagination and creativity with these systems because it's no longer just a look-a-like 2-dimensional image. Source: The All-In Podcast, david friedberg

Mario Nawfal

82,293 views • 1 year ago

A player in Where Winds Meet made a Keanu Reeves character and played See You Again with Kong Hou. Yes, you can basically do anything in this Wuxia open world RPG with MMO features. For those curious, Kong Hou is an Chinese harp-like instrument from the Tang Dynasty. There are 2 versions, one is the modern Kong Hou, which is basically a western harp but with 2 rows of strings. The traditional Tang dynasty version looks similar to the one in this video with a single row of strings. The strings are attached to the hollow structure at the top of the Kong Hou, which creates a very unique sound.

A player in Where Winds Meet made a Keanu Reeves character and played See You Again with Kong Hou. Yes, you can basically do anything in this Wuxia open world RPG with MMO features. For those curious, Kong Hou is an Chinese harp-like instrument from the Tang Dynasty. There are 2 versions, one is the modern Kong Hou, which is basically a western harp but with 2 rows of strings. The traditional Tang dynasty version looks similar to the one in this video with a single row of strings. The strings are attached to the hollow structure at the top of the Kong Hou, which creates a very unique sound.

Zhao DaShuai 东北进修🇨🇳

230,538 views • 9 months ago

Elon Musk: To really be intelligent, AI has to make predictions that are in line with reality. “It's incredibly important for an AI model to be grounded in reality. I have a saying, which is physics is the law and everything else is a recommendation. I'm not suggesting people break the laws made by humans, we should generally obey the laws of humans. But I've seen many people break human made laws, but I have not seen anyone break the laws of physics. So, for any given AI, grounding it against reality and reality, for example, as you mentioned with the car, it needs to drive safely and correctly. The humanoid robot Optimus needs to perform the task that it's being asked to perform. These are things that are very helpful for ensuring that the model is truthful and accurate because it has to adhere to the laws of physics. So I think that's actually maybe somewhat overlooked or at least not talked about enough is that to really be intelligent it's got to make predictions that are in line with reality. In other words, physics.” Conversation with Satya Nadella, May 19, 2025

Elon Musk: To really be intelligent, AI has to make predictions that are in line with reality. “It's incredibly important for an AI model to be grounded in reality. I have a saying, which is physics is the law and everything else is a recommendation. I'm not suggesting people break the laws made by humans, we should generally obey the laws of humans. But I've seen many people break human made laws, but I have not seen anyone break the laws of physics. So, for any given AI, grounding it against reality and reality, for example, as you mentioned with the car, it needs to drive safely and correctly. The humanoid robot Optimus needs to perform the task that it's being asked to perform. These are things that are very helpful for ensuring that the model is truthful and accurate because it has to adhere to the laws of physics. So I think that's actually maybe somewhat overlooked or at least not talked about enough is that to really be intelligent it's got to make predictions that are in line with reality. In other words, physics.” Conversation with Satya Nadella, May 19, 2025

ELON CLIPS

30,805 views • 4 months ago

Elon Musk: To really be intelligent, AI has to make predictions that are in line with reality. “It's incredibly important for an AI model to be grounded in reality. I have a saying, which is physics is the law and everything else is a recommendation. I'm not suggesting people break the laws made by humans, we should generally obey the laws of humans. But I've seen many people break human made laws, but I have not seen anyone break the laws of physics. So, for any given AI, grounding it against reality and reality, for example, as you mentioned with the car, it needs to drive safely and correctly. The humanoid robot Optimus needs to perform the task that it's being asked to perform. These are things that are very helpful for ensuring that the model is truthful and accurate because it has to adhere to the laws of physics. So I think that's actually maybe somewhat overlooked or at least not talked about enough is that to really be intelligent it's got to make predictions that are in line with reality. In other words, physics.” Conversation with Satya Nadella, May 19, 2025

Elon Musk: To really be intelligent, AI has to make predictions that are in line with reality. “It's incredibly important for an AI model to be grounded in reality. I have a saying, which is physics is the law and everything else is a recommendation. I'm not suggesting people break the laws made by humans, we should generally obey the laws of humans. But I've seen many people break human made laws, but I have not seen anyone break the laws of physics. So, for any given AI, grounding it against reality and reality, for example, as you mentioned with the car, it needs to drive safely and correctly. The humanoid robot Optimus needs to perform the task that it's being asked to perform. These are things that are very helpful for ensuring that the model is truthful and accurate because it has to adhere to the laws of physics. So I think that's actually maybe somewhat overlooked or at least not talked about enough is that to really be intelligent it's got to make predictions that are in line with reality. In other words, physics.” Conversation with Satya Nadella, May 19, 2025

ELON CLIPS

680,153 views • 8 months ago

We are thrilled to announce a $7M raise to become the leading Open-Access AI Cloud 🤘🏼🌪️ At Hyperbolic, we’re building an open AI ecosystem and economy where everyone who contributes is rewarded. Our goal is not to merely optimize AI performance to compete with traditional Web2 services, but to create an inclusive AI economy accessible to all. The future of AI is collaborative. Join us.

We are thrilled to announce a $7M raise to become the leading Open-Access AI Cloud 🤘🏼🌪️ At Hyperbolic, we’re building an open AI ecosystem and economy where everyone who contributes is rewarded. Our goal is not to merely optimize AI performance to compete with traditional Web2 services, but to create an inclusive AI economy accessible to all. The future of AI is collaborative. Join us.

Hyperbolic

931,340 views • 2 years ago

I gave an AI video workflow a real creative brief—not one prompt, but a character, product references, camera beats, a 3D layout and multiple versions. Seedance 2.5 launches globally first on Dreamina. It’s from the same parent company as TikTok, and Dreamina is built to be the most optimized, cost-effective place to run it.

I gave an AI video workflow a real creative brief—not one prompt, but a character, product references, camera beats, a 3D layout and multiple versions. Seedance 2.5 launches globally first on Dreamina. It’s from the same parent company as TikTok, and Dreamina is built to be the most optimized, cost-effective place to run it.

Parul Gautam

47,544 views • 1 month ago

$China’s booming ultra-short drama industry is being reshaped by the rapid rise of AI-generated video. In Zhengzhou, one of the country’s major production hubs, directors, actors, crews, and film bases that once fueled the industry’s explosive growth are now facing shrinking budgets, fewer shoots, and an uncertain future. Meanwhile, in other cities like Wuxi, AI studios are embracing the same technology to produce dramas faster and at a fraction of the traditional cost. As the two worlds increasingly converge, the question is no longer whether AI will change filmmaking, but what role humans will have in it.$

China’s booming ultra-short drama industry is being reshaped by the rapid rise of AI-generated video. In Zhengzhou, one of the country’s major production hubs, directors, actors, crews, and film bases that once fueled the industry’s explosive growth are now facing shrinking budgets, fewer shoots, and an uncertain future. Meanwhile, in other cities like Wuxi, AI studios are embracing the same technology to produce dramas faster and at a fraction of the traditional cost. As the two worlds increasingly converge, the question is no longer whether AI will change filmmaking, but what role humans will have in it.

Sixth Tone

432,533 views • 1 month ago

I told an AI to build a 3D racing game. And it actually understood the entire idea. It created the terrain, racers, obstacles, collisions, different environments AND even the leaderboard. I barely touched the 3D workflow. This is what an all-in-one AI 3D Agent should feel like. The game's map keeps changing with: → Mountains → boulders → Rainforests → thorns & trees → Ice → slippery chaos → Cherry blossoms → roadblocks & cars And you can literally tackle other riders and make them fall. But be careful because the game resets when you get hit by a car or boulder. All built with Hi3D Agent. Most 3D AI tools just create 3D models but Hi3D goes next level by creating 3D games.

I told an AI to build a 3D racing game. And it actually understood the entire idea. It created the terrain, racers, obstacles, collisions, different environments AND even the leaderboard. I barely touched the 3D workflow. This is what an all-in-one AI 3D Agent should feel like. The game's map keeps changing with: → Mountains → boulders → Rainforests → thorns & trees → Ice → slippery chaos → Cherry blossoms → roadblocks & cars And you can literally tackle other riders and make them fall. But be careful because the game resets when you get hit by a car or boulder. All built with Hi3D Agent. Most 3D AI tools just create 3D models but Hi3D goes next level by creating 3D games.

Darshal Jaitwar

42,079 views • 5 days ago

"Hah - generative ai can't even make an image of a hand with the right number of fingers.." "Stop pushing this slop" It's way past the point now where it must be clear to everyone, that generative ai is here to stay AND that the quality will continue to increase. I've been talking about this trajectory for years now, and I've been working towards finding ways to combine the strength of these models, with the best of what I love about "old-school" creation. Building with my hands, moving a pencil across the paper and seeing shapes emerge, moving a building slightly to the right to get just that composition I had in mind. Being fully immersed in a scene I'm building in VR, being inspired by the immersion to take the story in a new direction. For years I've been talking about how powerful the combination of 3d and generative ai is, be it traditional 3d, SDF volumes in Dreams or Gaussian splats - with experiments around using V2V as a "render pass" or with experiments around realtime ai. Enough talk you might think, where's the proof? It's all around us these days honestly and here's a small test I did during some OOO. Blender MPC + Fable - a pretty powerful combination! With a bit of Google Omni Fast on top as a "render" pass. What do you think of where this is heading? Hopeful, disheartened, inspired or the opposite? Can you imagine working with tools like this in a way where we still retain the human "spark" and the creative nerve that makes each persons creation unique?

"Hah - generative ai can't even make an image of a hand with the right number of fingers.." "Stop pushing this slop" It's way past the point now where it must be clear to everyone, that generative ai is here to stay AND that the quality will continue to increase. I've been talking about this trajectory for years now, and I've been working towards finding ways to combine the strength of these models, with the best of what I love about "old-school" creation. Building with my hands, moving a pencil across the paper and seeing shapes emerge, moving a building slightly to the right to get just that composition I had in mind. Being fully immersed in a scene I'm building in VR, being inspired by the immersion to take the story in a new direction. For years I've been talking about how powerful the combination of 3d and generative ai is, be it traditional 3d, SDF volumes in Dreams or Gaussian splats - with experiments around using V2V as a "render pass" or with experiments around realtime ai. Enough talk you might think, where's the proof? It's all around us these days honestly and here's a small test I did during some OOO. Blender MPC + Fable - a pretty powerful combination! With a bit of Google Omni Fast on top as a "render" pass. What do you think of where this is heading? Hopeful, disheartened, inspired or the opposite? Can you imagine working with tools like this in a way where we still retain the human "spark" and the creative nerve that makes each persons creation unique?

Martin Nebelong

49,689 views • 2 months ago

Tried DeeVid AI with a video idea I had and now I understand why people are experimenting with AI video tools. What I liked most was being able to start with an idea instead of worrying about every little production step. The result was much better than I expected from such a simple workflow. If you’re creating content with the goal of eventually monetizing it, this is definitely something worth experimenting with. #DeeVidAI #AIVideo

Tried DeeVid AI with a video idea I had and now I understand why people are experimenting with AI video tools. What I liked most was being able to start with an idea instead of worrying about every little production step. The result was much better than I expected from such a simple workflow. If you’re creating content with the goal of eventually monetizing it, this is definitely something worth experimenting with. #DeeVidAI #AIVideo

Jennifer Thompson

18,628 views • 16 days ago