Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

My new favourite thing is using image edit models like 3D shaders, letting you add textures, effects and materials to practically anything We’ve been busy training a whole bunch of them and will be dropping them over on SYSTMS over the coming weeks 🫡

ingi_erlingsson's profile picture

Ingi Erlingsson 🪄

7,997 subscribers

31,958 Aufrufe • vor 8 Monaten •via X (Twitter)

KunstBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

CSM 3D AI: New image-to-3D AI program AI is reshaping the future of 3D design. This amazing tool transforms still images into 3D models, and the best part? You can animate them effortlessly using AI. Link in comment!
0:13

CSM 3D AI: New image-to-3D AI program AI is reshaping the future of 3D design. This amazing tool transforms still images into 3D models, and the best part? You can animate them effortlessly using AI. Link in comment!

el.cine

54,393 Aufrufe • vor 1 Jahr

Going 3D meant I've had to learn OpenGL to make Fastest-lap look like a video game! To date, I am able to import models and move them around. Colors, textures, and decals coming next! This will be a game changer in vehicle dynamics! Analyses will be way clearer and enjoyable
0:14

Going 3D meant I've had to learn OpenGL to make Fastest-lap look like a video game! To date, I am able to import models and move them around. Colors, textures, and decals coming next! This will be a game changer in vehicle dynamics! Analyses will be way clearer and enjoyable

Juan 🏎️

47,562 Aufrufe • vor 3 Jahren

💀thanks claude It made all materials and the whole widget in 15 minutes from scratch. Other then me asking it to make a cartoony shop with 8 offers using bouncy effects and glints wherever they would fit. It took over my pc and correctly itself a bunch of time. This is getting crazy #uefn
0:13

💀thanks claude It made all materials and the whole widget in 15 minutes from scratch. Other then me asking it to make a cartoony shop with 8 offers using bouncy effects and glints wherever they would fit. It took over my pc and correctly itself a bunch of time. This is getting crazy #uefn

Duuk

22,186 Aufrufe • vor 1 Monat

Ported over the getup tasks from playground to mjlab for my thesis defense. Will make them available in a separate repo so others can repro and build on top in the coming weeks.
0:12

Ported over the getup tasks from playground to mjlab for my thesis defense. Will make them available in a separate repo so others can repro and build on top in the coming weeks.

Kevin Zakka

24,836 Aufrufe • vor 5 Monaten

okay! my whole pipeline for getting fable and sol to be able to 3d model good topology hard surface game models without using any additional paid services is WORKING... we just need to dial in their lowpoly geometry and baking techniques some more, the pipeline is images > trellis > model creates the lowpoly themselves with direct headless blender interaction > bake ... this will work with both of them because you can replace sol's gptimage2 imagegen in fable's version with z-image-turbo or another quality local image model
0:15

okay! my whole pipeline for getting fable and sol to be able to 3d model good topology hard surface game models without using any additional paid services is WORKING... we just need to dial in their lowpoly geometry and baking techniques some more, the pipeline is images > trellis > model creates the lowpoly themselves with direct headless blender interaction > bake ... this will work with both of them because you can replace sol's gptimage2 imagegen in fable's version with z-image-turbo or another quality local image model

Utah teapot 🫖

11,905 Aufrufe • vor 2 Monaten

New adventure, new Tems! Delightful new creatures are waiting to meet you down below. This is just a small showcase of some of them, but there will be over 200 Tems in Temtem: Pioneers, between the previous ones and the new ones! Like what you see? Want to know more? Our Kickstarter campaign is live! 🏕️
0:16

New adventure, new Tems! Delightful new creatures are waiting to meet you down below. This is just a small showcase of some of them, but there will be over 200 Tems in Temtem: Pioneers, between the previous ones and the new ones! Like what you see? Want to know more? Our Kickstarter campaign is live! 🏕️

Temtem 🏕️ Wishlist Pioneers!

15,284 Aufrufe • vor 5 Monaten

AI compositing is alr taking over now you can edit video like editing image using Seedance 2.0 on Higgsfield, it auto select any object, edit separately and.. even blend in the scene perfectly its just faster, cheaper and more accurate here's how to do + prompts:
0:17

AI compositing is alr taking over now you can edit video like editing image using Seedance 2.0 on Higgsfield, it auto select any object, edit separately and.. even blend in the scene perfectly its just faster, cheaper and more accurate here's how to do + prompts:

el.cine

83,524 Aufrufe • vor 5 Monaten

Introducing OpenVPP 2.0. Electric reimagined. Over the past quarter we’ve added 300+ electric vehicles, growing 750% QoQ and tokenizing $25M in RWAs. We’ve now proven out the first at-scale global virtual power plant. The next chapter of OpenVPP starts today — $OVPP is moving to Base. Over the coming weeks we will be releasing more of our future roadmap from product to partnerships and beyond. Look out for updates here on next steps and get ready for what will become the new age of electricity. The Internet of Energy.
0:11

Introducing OpenVPP 2.0. Electric reimagined. Over the past quarter we’ve added 300+ electric vehicles, growing 750% QoQ and tokenizing $25M in RWAs. We’ve now proven out the first at-scale global virtual power plant. The next chapter of OpenVPP starts today — $OVPP is moving to Base. Over the coming weeks we will be releasing more of our future roadmap from product to partnerships and beyond. Look out for updates here on next steps and get ready for what will become the new age of electricity. The Internet of Energy.

OpenVPP

17,178 Aufrufe • vor 6 Monaten

AI is the craziest thing I kicked off a bunch of agents before leaving to the gym, i had them work on this game idea I've been toying around with. I get back home and I've completely forgotten about it and I hear a bunch of explosions going off from my office. I look at my PC and find a bunch of tanks in that the agent generated battling each other and lagging like crazy🤣
0:11

AI is the craziest thing I kicked off a bunch of agents before leaving to the gym, i had them work on this game idea I've been toying around with. I get back home and I've completely forgotten about it and I hear a bunch of explosions going off from my office. I look at my PC and find a bunch of tanks in that the agent generated battling each other and lagging like crazy🤣

kvick

27,550 Aufrufe • vor 3 Monaten

The video in the QT is quite literally a CATASTROPHE If you’re going to do Bent Over Barbell Rows and you actually want them to be effective… Try checking your ego at the door and performing them like this:
0:14

The video in the QT is quite literally a CATASTROPHE If you’re going to do Bent Over Barbell Rows and you actually want them to be effective… Try checking your ego at the door and performing them like this:

Dean Turner

2,395,558 Aufrufe • vor 7 Monaten

Literally every team and developer who has tested our tool over the past months has continued working with us and asked to keep using it. Not a single one has stopped, and the feedback is that it is by far the strongest tool they have used. Over the coming weeks, we will show you why.
0:13

Literally every team and developer who has tested our tool over the past months has continued working with us and asked to keep using it. Not a single one has stopped, and the feedback is that it is by far the strongest tool they have used. Over the coming weeks, we will show you why.

BailSec

20,918 Aufrufe • vor 1 Monat

Today, we released Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by: ✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences ✅ Using self-augmented training to correct its own temporal drifting. Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications. ➡️ Learn more: 📄 Read the paper:
0:15

Today, we released Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by: ✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences ✅ Using self-augmented training to correct its own temporal drifting. Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications. ➡️ Learn more: 📄 Read the paper:

NVIDIA AI Developer

438,154 Aufrufe • vor 5 Monaten

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.
0:13

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.

Michael Black

22,182 Aufrufe • vor 9 Monaten

I’ve been craving a video editor with motion baked in, designed to work with my own AI agents. Claude, Codex, whatever I want to use. I don’t want to be blocked by someone else’s credit system for every little interaction. I also wanted a Figma-like canvas/editor for when I want to jump in and tweak any little detail. So we built it: Video & audio editing: cut, zoom, speed up, add B-roll. Motion, animation, 3D, custom shaders & effects, custom 3D models, dynamic components & templates, audio and beat matching. And it’s all programmable. Design your own assets directly on the canvas, bring them in from Figma or the web, or just let the agent find them, mock them up, or record what it needs automatically. You can even drop in your screen recordings and just let loose. Supercut users: yes, it’ll have first-class support for your recordings, but it’ll work with anything. I’m going to be dropping a lot more examples and tutorials, so follow along. DM me for early access if you’re willing to give feedback. We’ll open it up to everyone very soon.
0:19

I’ve been craving a video editor with motion baked in, designed to work with my own AI agents. Claude, Codex, whatever I want to use. I don’t want to be blocked by someone else’s credit system for every little interaction. I also wanted a Figma-like canvas/editor for when I want to jump in and tweak any little detail. So we built it: Video & audio editing: cut, zoom, speed up, add B-roll. Motion, animation, 3D, custom shaders & effects, custom 3D models, dynamic components & templates, audio and beat matching. And it’s all programmable. Design your own assets directly on the canvas, bring them in from Figma or the web, or just let the agent find them, mock them up, or record what it needs automatically. You can even drop in your screen recordings and just let loose. Supercut users: yes, it’ll have first-class support for your recordings, but it’ll work with anything. I’m going to be dropping a lot more examples and tutorials, so follow along. DM me for early access if you’re willing to give feedback. We’ll open it up to everyone very soon.

Neil

23,042 Aufrufe • vor 1 Monat

Magic Quill: A Free AI Image Editor That Feels Like Magic This tool is incredibly useful and free to use now! It lets you select parts of an image and edit them with just a text prompt. Mostly I’ve gotten exactly what I needed on the first try! Here’s how to use it:
0:15

Magic Quill: A Free AI Image Editor That Feels Like Magic This tool is incredibly useful and free to use now! It lets you select parts of an image and edit them with just a text prompt. Mostly I’ve gotten exactly what I needed on the first try! Here’s how to use it:

el.cine

197,108 Aufrufe • vor 1 Jahr

🎶 David Moyes’ Claret & Blue army 🎶 Sung with pride and appreciation towards the end of a game that symbolised the end of an era. We’ve been provided with experiences to last a lifetime over the last three years, and we will never forget them ❤️⚒️
0:15

🎶 David Moyes’ Claret & Blue army 🎶 Sung with pride and appreciation towards the end of a game that symbolised the end of an era. We’ve been provided with experiences to last a lifetime over the last three years, and we will never forget them ❤️⚒️

West Ham Unofficial

17,830 Aufrufe • vor 2 Jahren

Another big drop from Hunyuan3D by Tencent. Hunyuan3D-Buffalo 1.0 is not just another text-to-3D model. The more interesting part is its approach to 3D understanding and editing. It can understand separate parts of a complete asset, extract them, remove or replace them with prompts, and edit only the selected region while keeping the rest of the geometry unchanged. That feels like a much more useful direction for 3D AI in general: not just generating a mesh once, but actually understanding its structure and letting you continue working with it. The model combines Qwen-VL, TRELLIS and Hunyuan3D, and was trained on an impressive dataset of 87 million 3D samples. Source:
0:18

Another big drop from Hunyuan3D by Tencent. Hunyuan3D-Buffalo 1.0 is not just another text-to-3D model. The more interesting part is its approach to 3D understanding and editing. It can understand separate parts of a complete asset, extract them, remove or replace them with prompts, and edit only the selected region while keeping the rest of the geometry unchanged. That feels like a much more useful direction for 3D AI in general: not just generating a mesh once, but actually understanding its structure and letting you continue working with it. The model combines Qwen-VL, TRELLIS and Hunyuan3D, and was trained on an impressive dataset of 87 million 3D samples. Source:

Stefan 3D AI

36,034 Aufrufe • vor 1 Monat