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.

Example of what AI generation can do in practice currently, from initial image (which is also generated) to a very detailed printable model, the level of detail mostly made possible with the Marigold depth estimation. #ai #3dprinting #dragon #technology

Jukka Seppänen

6,469 subscribers

13,766 views • 2 years ago •via X (Twitter)

Science & Technology #ai #3dprinting #dragon #technology

Anya Rossi• Live Now

Private livecam show

5 Comments

FUERYON2 years ago

Would be interested in seeing this on mmf as it would be great for my cnc router

Jukka Seppänen2 years ago

Would love to see that, gotta check up on MMF how they feel about AI generated content at this point. I can share you the file personally though!

StreamCatcher Chris2 years ago

That’s amazing. Time to play. In a few days. Got responsi… something or other.

🎥 JDL4 | CEO & Co-Founder Mallow.ai 🥳2 years ago

Incredible! This makes me want to buy a 3D printer 😆

Enrico Bassi2 years ago

that's very cool! what's the prompt you used? did you create a specific GPT for that?

Related Videos

Phoenix GenAI’s Img2Motion V2 Beta is now available – this significant upgrade showcases the latest generation of image-to-video AI technology built off of base image generation model FLUX, often dubbed as “Midjourney Killer”, which is also available on Phoenix GenAI. This latest release also utilizes SkyNet’s high performance node cluster, which consists of a combination of Nvidia A100 and H100 GPUs – a testament to SkyNet’s versatility of matching AI tasks with suitable compute resources. $PHB #AI

Phoenix GenAI’s Img2Motion V2 Beta is now available – this significant upgrade showcases the latest generation of image-to-video AI technology built off of base image generation model FLUX, often dubbed as “Midjourney Killer”, which is also available on Phoenix GenAI. This latest release also utilizes SkyNet’s high performance node cluster, which consists of a combination of Nvidia A100 and H100 GPUs – a testament to SkyNet’s versatility of matching AI tasks with suitable compute resources. $PHB #AI

Phoenix AI Labs

32,308 views • 1 year ago

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 views • 1 month ago

The new Hailuo AI (MiniMax) model I2V-01-Live is excellent 🤩 I generated the initial image in Leonardo.Ai, and then, with some very simple prompting, I got these incredible results:

The new Hailuo AI (MiniMax) model I2V-01-Live is excellent 🤩 I generated the initial image in Leonardo.Ai, and then, with some very simple prompting, I got these incredible results:

Alex Patrascu

45,726 views • 1 year ago

What happened after the invention of the spreadsheet is a great example of job creation from new technology and is likely what will happen with AI.

What happened after the invention of the spreadsheet is a great example of job creation from new technology and is likely what will happen with AI.

tae kim

19,952 views • 1 month ago

In collaboration with Intel, our Depth Fusion showcases the power of our LDM3D diffusion model in generating 360° views from text prompts provided by the user. The LDM3D diffusion model generates a 2D RGB image and its corresponding relative depth map providing a complete RGBD representation corresponding to the text prompt. The LDM 3D model is a specialized version of the stable diffusion V 1.4 model that has been modified to fit both image and depth map data.The model was then fine tuned on a subset of the Laion400M data set - large scale image caption data set. The depth maps used to fine tune our model were generated by the DPTBeiT large 512 depth estimation model that provides highly accurate relative depth estimates for each pixel. We take the generated 2D RGB image and depth map and use them to compute a 360° projection using touchdesigner. Touchdesigner is a versatile platform that allows for the creation of immersive and interactive multimedia experiences. Our application harnesses the power of touchdesigner to bring the generated 360° views to life, providing users with a unique and engaging way to experience their text prompts, whether it’s a description of a tranquil forest, a noisy cityscape or a futuristic sci fi world. Our depth fusion can bring these concepts to life in a vivid and immersive detail. - Scottie Fox, VP Engineering Blockade Labs ScottieFox #AI #VR #3D #gamedev #stablediffusion

In collaboration with Intel, our Depth Fusion showcases the power of our LDM3D diffusion model in generating 360° views from text prompts provided by the user. The LDM3D diffusion model generates a 2D RGB image and its corresponding relative depth map providing a complete RGBD representation corresponding to the text prompt. The LDM 3D model is a specialized version of the stable diffusion V 1.4 model that has been modified to fit both image and depth map data.The model was then fine tuned on a subset of the Laion400M data set - large scale image caption data set. The depth maps used to fine tune our model were generated by the DPTBeiT large 512 depth estimation model that provides highly accurate relative depth estimates for each pixel. We take the generated 2D RGB image and depth map and use them to compute a 360° projection using touchdesigner. Touchdesigner is a versatile platform that allows for the creation of immersive and interactive multimedia experiences. Our application harnesses the power of touchdesigner to bring the generated 360° views to life, providing users with a unique and engaging way to experience their text prompts, whether it’s a description of a tranquil forest, a noisy cityscape or a futuristic sci fi world. Our depth fusion can bring these concepts to life in a vivid and immersive detail. - Scottie Fox, VP Engineering Blockade Labs ScottieFox #AI #VR #3D #gamedev #stablediffusion

Blockade Labs

11,439 views • 3 years ago

I was at a Twin Peaks in San Antonio with a buddy this weekend and I mentioned AI image generation & what it can do. "Have it create our server" he said, so I sort of did. This AI generated song I made in an hour is about 85% as good as what is on the country charts right now.

I was at a Twin Peaks in San Antonio with a buddy this weekend and I mentioned AI image generation & what it can do. "Have it create our server" he said, so I sort of did. This AI generated song I made in an hour is about 85% as good as what is on the country charts right now.

West Bestern 🛡️

18,741 views • 1 year ago

"Instead of an AI generated image being an embed inside of a presentation, you're going to start to see the entire presentation slide as generated." Stephen Balaban, Lambda CEO discusses the future power of AI generation

"Instead of an AI generated image being an embed inside of a presentation, you're going to start to see the entire presentation slide as generated." Stephen Balaban, Lambda CEO discusses the future power of AI generation

Bloomberg TV

37,044 views • 1 year ago

Can you tell which one is AI? Spoiler in the comments. This was made with Bytedance's internal AI model.

Can you tell which one is AI? Spoiler in the comments. This was made with Bytedance's internal AI model.

⚡AI Search⚡

12,604 views • 4 months ago

AI just made a body for themselves🤯 Meet Lucy, (Probably) the 1st AI-generated AI #Robot🤖 1️⃣AI Generated Image 2️⃣AI Generated 3D Model by #Rodin 3️⃣RL-based Learning in Simulation 4️⃣3D Printing 5️⃣Lucy in the real world More AI-generated Robots coming Soon. #Robotics

AI just made a body for themselves🤯 Meet Lucy, (Probably) the 1st AI-generated AI #Robot🤖 1️⃣AI Generated Image 2️⃣AI Generated 3D Model by #Rodin 3️⃣RL-based Learning in Simulation 4️⃣3D Printing 5️⃣Lucy in the real world More AI-generated Robots coming Soon. #Robotics

Hyper3D by Deemos

45,322 views • 8 months ago

Want to see how much AI has advanced in two months? Here is an AI-generated person with a (now realistic) AI-generated voice delivering the beginning of a lecture titled “Do not fear AI, puny humans” where all of the content & slides are made by AI. More:

Want to see how much AI has advanced in two months? Here is an AI-generated person with a (now realistic) AI-generated voice delivering the beginning of a lecture titled “Do not fear AI, puny humans” where all of the content & slides are made by AI. More:

Ethan Mollick

494,474 views • 3 years 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

48,200 views • 1 year ago

Big day! I am launching episode one of my new podcast "Dreamlabs: Creativity & Consciousness in the Age of AI" Today I explore what's now possible in AI generated music. I was blown away by what you can now do - listen for example outputs. I'll include a link to Spotify below!

Big day! I am launching episode one of my new podcast "Dreamlabs: Creativity & Consciousness in the Age of AI" Today I explore what's now possible in AI generated music. I was blown away by what you can now do - listen for example outputs. I'll include a link to Spotify below!

evan stites-clayton

18,922 views • 10 months ago

KATANA // AI short film made with Higgsfield AI 🧩 & Kling AI KATANA is a cyberpunk sci-fi short film set in a neon-drenched dystopia where a lethal operative discovers her ancient katana is haunted by an AI with intimate knowledge of her forgotten past. Produced & Directed by: SoloFilms AI & DO KWEEN 👑 (AI CTO 100B) 4K Resolution available in link below AI Tools used: Midjourney V7 // image generations - Higgsfield AI 🧩 // image-to-video generation Kling AI // image-to-video generation // voice generation Topaz Labs // 1080p to 4k upscaling

KATANA // AI short film made with Higgsfield AI 🧩 & Kling AI KATANA is a cyberpunk sci-fi short film set in a neon-drenched dystopia where a lethal operative discovers her ancient katana is haunted by an AI with intimate knowledge of her forgotten past. Produced & Directed by: SoloFilms AI & DO KWEEN 👑 (AI CTO 100B) 4K Resolution available in link below AI Tools used: Midjourney V7 // image generations - Higgsfield AI 🧩 // image-to-video generation Kling AI // image-to-video generation // voice generation Topaz Labs // 1080p to 4k upscaling

Solo 👑

69,302 views • 1 year ago

HOLY SHIT! Sparc 3D is INSANE! All they need to do now is enable PBR texture support, object separation and decimation and this in my opinion completely replaces photogrammetry. The quality of the reconstruction of these 3D objects from a single image is mind blowing to me. Yes, the model is insanely dense to allow all of this detail but the fact that AI can generate with this level of fidelity is CRAZY!!! You can try it for free on Huggingface

HOLY SHIT! Sparc 3D is INSANE! All they need to do now is enable PBR texture support, object separation and decimation and this in my opinion completely replaces photogrammetry. The quality of the reconstruction of these 3D objects from a single image is mind blowing to me. Yes, the model is insanely dense to allow all of this detail but the fact that AI can generate with this level of fidelity is CRAZY!!! You can try it for free on Huggingface

Travis Davids

18,230 views • 11 months ago

Loneliness is an epidemic—one that is exacerbated by technology, but which can also be solved by technology. On this week’s episode of Possible, we talk about how AI can unite the generations and solve one of the century’s most pressing issues.

Loneliness is an epidemic—one that is exacerbated by technology, but which can also be solved by technology. On this week’s episode of Possible, we talk about how AI can unite the generations and solve one of the century’s most pressing issues.

Reid Hoffman

17,234 views • 1 year ago

With human-made art becoming trendy again and in-depth breakdowns more appreciated these days, here’s another video with no AI and not a single stock image used. ⛔ For the love of every genuine detail.

With human-made art becoming trendy again and in-depth breakdowns more appreciated these days, here’s another video with no AI and not a single stock image used. ⛔ For the love of every genuine detail.

Adham.

129,832 views • 1 month ago

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Yang You

245,732 views • 2 years ago

AI is moving fast. And OpenAI's new image model proves it — knowing how to use AI images to your advantage is now crucial for designers. So we teamed up with Nick St. Pierre (The AI Image Master) to walkthrough one of the best AI image generation tools right now, Midjourney, and build a full website using only AI images, in 1 hour. Watch the full breakdown👇

AI is moving fast. And OpenAI's new image model proves it — knowing how to use AI images to your advantage is now crucial for designers. So we teamed up with Nick St. Pierre (The AI Image Master) to walkthrough one of the best AI image generation tools right now, Midjourney, and build a full website using only AI images, in 1 hour. Watch the full breakdown👇

Relume

14,706 views • 1 year ago

Video made by Seedance, an AI model made by Bytedance, the parent company of TikTok. Less than a year ago, to determine whether a video is AI generated, you just need to count the number of fingers.

Video made by Seedance, an AI model made by Bytedance, the parent company of TikTok. Less than a year ago, to determine whether a video is AI generated, you just need to count the number of fingers.

Zhao DaShuai 东北进修🇨🇳 Commentary

370,741 views • 4 months ago