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.

More Adobe Substance Modeler +AI experiments. Using quick, gestural 3d sketching to drive generative AI with much higher levels of creative control than you could ever get from a text prompt alone. The more detailed your 3d model is, the more you can leave the ai to just finish... show more

Martin Nebelong

33,764 subscribers

56,540 views • 2 years ago •via X (Twitter)

Arts Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Martin Nebelong2 years ago

Details on the process: I sculpt the basic 3d model in Adobe Substance 3D Modeler, using both the non-VR and VR mode of working. I use Krea AI and screen2image to feed the i mage from Modeler, into Krea. Here, I can transform the input image using a text prompt and the AI strength slider. The more detailed your model is, the less AI hallucination you need, which in my mind is where we need to move towards for a really interesting combination of the strength of human creativity AND ai. Once I get an AI version of my model that I feel is close to my creative idea, I send that image to Tripo Ai where the image is converted to a 3d model in a matter of seconds. I then bring that back to Modeler for more refinement. Once I'm happy with the model, I light and compose the scene in Marmoset Toolbag. I'm using Marmoset because of how easy it is to setup my scene here.. it's responsive, realtime and it looks good. The small animated clips are made using Runway and Leonardo Ai.

Justin Maynard2 years ago

Love your workflows. Keep shining. 🔥❤️🔥😊✌️

Ago-ra@AI2 years ago

@krea_ai !!

Lucas Aguirre2 years ago

thx for sharing Martin. Hey this Tripo App is something!!

Christian Sass2 years ago

very soon nothing will be trustworthy

Anthony Rosbottom 🔶2 years ago

It's impressive but the end result is still an 8bit RGB image? I'm not seeing any development in generating PBR texture sets or 10bit EXR files from all these experiments (generally I mean, not just your work). Seems like this all this AI art is heading to an 8bit future

Martin Nebelong2 years ago

I'm sure it won't be long before we see improvements in that as well. The Adobe Substance team recently showcased work that's ongoing I'm implementing Firefly generative images in Substance painter.. That looked very promising.

Stayu Kasabov2 years ago

I still feel this is lacking precise control for a final workflow, but as a concept art process has some validity:)

Martin Nebelong2 years ago

Yeah it's not there yet.. The missing element is being able to gradually or more strongly morph the model towards the AI "amplification" and then being able to mold and shape that in an iterative process.

paul2 years ago

Genius. I say it again: genius.

Related Videos

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai

Martin Nebelong

88,080 views • 2 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 • 2 years ago

3D AI is advancing quicker than we ever thought possible. Right now, we can use it to create individual 3D assets, but soon, building entire virtual worlds with just a text prompt could become a reality. This is from Meta 3D AI team.

3D AI is advancing quicker than we ever thought possible. Right now, we can use it to create individual 3D assets, but soon, building entire virtual worlds with just a text prompt could become a reality. This is from Meta 3D AI team.

el.cine

42,166 views • 1 year ago

Texture any 3D model in seconds 😱 Yes your read it right, using MeshyAI and their generative AI tool. All you need is to import your model, write a prompt, Done. Try it out today, link below 👇

Texture any 3D model in seconds 😱 Yes your read it right, using MeshyAI and their generative AI tool. All you need is to import your model, write a prompt, Done. Try it out today, link below 👇

Linus ✦ Ekenstam

483,599 views • 2 years ago

CAD AI is getting crazier.. this new text to CAD AI lets you generate 3D models with precise control of the dimensions and.. you can even do it on your phone. 3D printing is so much easier now.

CAD AI is getting crazier.. this new text to CAD AI lets you generate 3D models with precise control of the dimensions and.. you can even do it on your phone. 3D printing is so much easier now.

el.cine

173,918 views • 1 year ago

My photoshop is more fun than yours 😜 With a bit of help from Krea ai. It's a crazy feeling to see brushstrokes transformed like this in realtime.. And the feeling of control is magnitudes better than with text prompts. #ai #art

My photoshop is more fun than yours 😜 With a bit of help from Krea ai. It's a crazy feeling to see brushstrokes transformed like this in realtime.. And the feeling of control is magnitudes better than with text prompts. #ai #art

Martin Nebelong

213,840 views • 2 years ago

Using 3D assets with Gen-4 References is a simple way to bring highly detailed and specific models into your generative workflows for even more consistency and control. To do so, simply provide a location plate, a quick comp of your 3D model in that space and a style reference.

Using 3D assets with Gen-4 References is a simple way to bring highly detailed and specific models into your generative workflows for even more consistency and control. To do so, simply provide a location plate, a quick comp of your 3D model in that space and a style reference.

Runway

119,208 views • 1 year ago

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.

Gabriele Romagnoli

2,176,749 views • 1 year ago

omg.. I can't believe this.. this Unreal Engine AI plugin lets you generate 3D model in seconds with text prompt, and even chat with AI to optimise your scene.. A revolutionary AI tool for 3D creation. here's how to get started:

omg.. I can't believe this.. this Unreal Engine AI plugin lets you generate 3D model in seconds with text prompt, and even chat with AI to optimise your scene.. A revolutionary AI tool for 3D creation. here's how to get started:

el.cine

129,956 views • 1 year ago

I see your text prompt and raise you my 3d to anything.. It's all about control if we want Gen ai to be a useful creative tool. Keep reading to see the finished images based on this technique.🧵 #ai #art

I see your text prompt and raise you my 3d to anything.. It's all about control if we want Gen ai to be a useful creative tool. Keep reading to see the finished images based on this technique.🧵 #ai #art

Martin Nebelong

128,979 views • 2 years ago

holy sht.. AI has automated UE5 you can build entire 3D interactive world with text prompt, everything is editable.. and the AI agent can even rig and animate your 3D characters.. you dont need 10 years of 3D skills to build game now

holy sht.. AI has automated UE5 you can build entire 3D interactive world with text prompt, everything is editable.. and the AI agent can even rig and animate your 3D characters.. you dont need 10 years of 3D skills to build game now

el.cine

101,935 views • 1 month ago

Google just released Veo 2, a new state-of-the-art AI video model. In testing, Veo beat OpenAI Sora in BOTH quality and prompt adherence. The video compilation below is 100% created by AI (more details in thread):

Google just released Veo 2, a new state-of-the-art AI video model. In testing, Veo beat OpenAI Sora in BOTH quality and prompt adherence. The video compilation below is 100% created by AI (more details in thread):

Rowan Cheung

249,977 views • 1 year ago

BREAKING: MICROSOFT JUST ANNOUNCED TO BAN ITS OWN ENGINEERS FROM USING AI DUE TO THE COST OF USING IT. VP OF NVIDIA SAID, “THE COST OF AI FOR MY TEAM WAS MORE THAN HUMANS” “AI CAN COST MORE THAN HUMAN WORKERS NOW”

BREAKING: MICROSOFT JUST ANNOUNCED TO BAN ITS OWN ENGINEERS FROM USING AI DUE TO THE COST OF USING IT. VP OF NVIDIA SAID, “THE COST OF AI FOR MY TEAM WAS MORE THAN HUMANS” “AI CAN COST MORE THAN HUMAN WORKERS NOW”

Vivek Sen

17,486,844 views • 1 month ago

How to train a model that actually understands both audio and text like Voxtral from Mistral AI? Here is a quick video walkthrough of the paper.

How to train a model that actually understands both audio and text like Voxtral from Mistral AI? Here is a quick video walkthrough of the paper.

Sophia Yang, Ph.D.

49,801 views • 1 year ago

Today, generative AI can create a 3D race car. Roblox is now working on 4D generative AI, where that race car has an engine, moveable parts and a physics rig that enables it to drive down a track — all generated with just a text or voice prompt.

Today, generative AI can create a 3D race car. Roblox is now working on 4D generative AI, where that race car has an engine, moveable parts and a physics rig that enables it to drive down a track — all generated with just a text or voice prompt.

David Baszucki

467,486 views • 2 years ago

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model

el.cine

142,328 views • 8 months ago

The Rijksmuseum is using generative #AI to create descriptions of its art collection so vivid you can repaint them in your imagination. I loved watching this inspiring story of how AI is creating a more accessible world for the blind and low vision community. #ArtIsForEveryone

The Rijksmuseum is using generative #AI to create descriptions of its art collection so vivid you can repaint them in your imagination. I loved watching this inspiring story of how AI is creating a more accessible world for the blind and low vision community. #ArtIsForEveryone

Brad Smith

16,711 views • 2 years ago

One of the hardest things to achieve with AI is precise character motion. The new model by Kinetix, Kamo-1, is amazing at giving you far more control over your generations. It’s also the first 3D-conditioned model, so it understands the scene in 3D and gives you almost unlimited camera motion. Let me show you how to use it 👇

One of the hardest things to achieve with AI is precise character motion. The new model by Kinetix, Kamo-1, is amazing at giving you far more control over your generations. It’s also the first 3D-conditioned model, so it understands the scene in 3D and gives you almost unlimited camera motion. Let me show you how to use it 👇

Everett World

19,199 views • 7 months ago

Adobe partners with Kling 🎉 This is huge! You can use Kling AI video at Adobe Firefly platform now. I made this video using Kling 2.5 Turbo and I'm in awe how state of the art this AI model is.

Adobe partners with Kling 🎉 This is huge! You can use Kling AI video at Adobe Firefly platform now. I made this video using Kling 2.5 Turbo and I'm in awe how state of the art this AI model is.

Kris Kashtanova

69,277 views • 4 months ago