Загрузка видео...

Не удалось загрузить видео

На главную

At this point, Three.js is probably the best graphics stack for AI-generated games. Not because it magically produces better visuals, but because models are extremely good at reasoning directly over JavaScript, scene graphs, shaders, procedural geometry, physics integrations, and fast browser iteration. The examples here make the case pretty...

TokenGremlin's profile picture

Token Gremlin

6,054 subscribers

12,038 просмотров • 2 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

GPT-6.1 Sol, running in Ultra mode, has been autonomously iterating on this project for more than 16 hours now. It’s using Blender and Three.js, and the entire thing runs directly in the browser. Like I said earlier, this model is genuinely impressive. OpenAI built something here that feels extremely capable, surprisingly cheap, and now fast enough to make long-running agentic workflows much more practical. (The project is still in progress...)
1:24

GPT-6.1 Sol, running in Ultra mode, has been autonomously iterating on this project for more than 16 hours now. It’s using Blender and Three.js, and the entire thing runs directly in the browser. Like I said earlier, this model is genuinely impressive. OpenAI built something here that feels extremely capable, surprisingly cheap, and now fast enough to make long-running agentic workflows much more practical. (The project is still in progress...)

Token Gremlin

18,553 просмотров • 28 дней назад

ok added a proper crowd sim as well to my destruction game prototype! is this too evil? 👽 generated the human models and rigged them in Omma AI with the new rigging suite, the crowd sim is made efficiently in three.js & physics are in Box3D. What else is missing?
0:49

ok added a proper crowd sim as well to my destruction game prototype! is this too evil? 👽 generated the human models and rigged them in Omma AI with the new rigging suite, the crowd sim is made efficiently in three.js & physics are in Box3D. What else is missing?

Marco Fugaro

13,868 просмотров • 3 месяцев назад

img2threejs 1.5.1 is out 🚀 Checkout: This release introduces a new approach to image → 3D → Three.js. Image → Tripo → img2threejs → reconstructed geometry → Three.js Instead of using the generated 3D model as the final asset, img2threejs uses it as a reference to rebuild the character into a representation that can be generated and rendered directly in Three.js. No Blender workflow, and no GLB required as the final output. The animation in the demo is still a bit rough because this release is focused on reconstruction, not animation. I’ll be improving that in the next release. Still experimental, but this is a big step toward where I want img2threejs to go.
1:02

img2threejs 1.5.1 is out 🚀 Checkout: This release introduces a new approach to image → 3D → Three.js. Image → Tripo → img2threejs → reconstructed geometry → Three.js Instead of using the generated 3D model as the final asset, img2threejs uses it as a reference to rebuild the character into a representation that can be generated and rendered directly in Three.js. No Blender workflow, and no GLB required as the final output. The animation in the demo is still a bit rough because this release is focused on reconstruction, not animation. I’ll be improving that in the next release. Still experimental, but this is a big step toward where I want img2threejs to go.

Nick

117,760 просмотров • 2 месяцев назад

Fable 5 built this real-time ocean scene directly in the browser using Three.js, WebGPU and TSL, with no engine and no baked assets. The interesting part is not just that the water looks good. The whole system is being simulated: wave spectrum, GPU FFT, foam generation and refracted-ray caustics, all running live. This is exactly where frontier models start becoming genuinely useful for technical graphics work. Not by replacing years of rendering research, but by compressing the path from complex math to a working interactive result. A small, focused scene, but technically very serious. Cc: Adem Vessell
0:12

Fable 5 built this real-time ocean scene directly in the browser using Three.js, WebGPU and TSL, with no engine and no baked assets. The interesting part is not just that the water looks good. The whole system is being simulated: wave spectrum, GPU FFT, foam generation and refracted-ray caustics, all running live. This is exactly where frontier models start becoming genuinely useful for technical graphics work. Not by replacing years of rendering research, but by compressing the path from complex math to a working interactive result. A small, focused scene, but technically very serious. Cc: Adem Vessell

Token Gremlin

21,731 просмотров • 3 месяцев назад

Still tweaking the API, but baking lightprobe volumes is fast and the results are looking great. Aiming to ship this in Three.js r184 later this month.
1:11

Still tweaking the API, but baking lightprobe volumes is fast and the results are looking great. Aiming to ship this in Three.js r184 later this month.

mrdoob

27,362 просмотров • 7 месяцев назад

GPT-6 Astra + Three.js is insane. We are way beyond static models. We are engineering living worlds in code now. There are no "3D model files" in this demo. Both trains are generated at runtime from Typescript/Three.js code using dimensions, profiles, and geometry functions. Wheel motion and explode/reassemble animations are also entirely code-driven. Runs super smooth inside the browser.
0:22

GPT-6 Astra + Three.js is insane. We are way beyond static models. We are engineering living worlds in code now. There are no "3D model files" in this demo. Both trains are generated at runtime from Typescript/Three.js code using dimensions, profiles, and geometry functions. Wheel motion and explode/reassemble animations are also entirely code-driven. Runs super smooth inside the browser.

Tom Krcha

686,285 просмотров • 1 месяц назад

Astra built this three.js game with gorgeous graphics, then recreated every scene in Blender and made the trailer too. It feels like a massive upgrade from Sol for 3D graphics and front-end design. The UI feels way more polished and less like AI slop. The rocks, trees, monuments, and characters are all procedural code, keeping the game under 2 MB before the image and music assets. The level of autonomy is unbelievable. It needed very little steering, though I still had to keep pushing it to work harder on the details. The UI icons, buttons, and ornaments were made as transparent PNGs with GPT Image 2.
1:13

Astra built this three.js game with gorgeous graphics, then recreated every scene in Blender and made the trailer too. It feels like a massive upgrade from Sol for 3D graphics and front-end design. The UI feels way more polished and less like AI slop. The rocks, trees, monuments, and characters are all procedural code, keeping the game under 2 MB before the image and music assets. The level of autonomy is unbelievable. It needed very little steering, though I still had to keep pushing it to work harder on the details. The UI icons, buttons, and ornaments were made as transparent PNGs with GPT Image 2.

Meng To

138,264 просмотров • 1 месяц назад

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!
0:23

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!

CyrilXBT

14,405 просмотров • 1 месяц назад

I'm playing around with generative AI tools and stitching them together into visual stories. Here I took the first few sentences of Pride and Prejudice and made it into a video. The gen stack used for this one: - Anthropic Claude took the first chapter, generated the scenes and the individual prompts to to the image generator. - Ideogram took the prompts and generate the images - Luma took the images and animated them - for narration - VEED | AI Video Creation to stitch it together (Many of these choices are just what I happened to use for this one while exploring a bunch of things). Anyway honestly it was pretty messy and there is a ton of copy pasting between all of the tools, and even this little video with 3 scenes took me about an hour. There is a huge storytelling opportunity here for whoever can make this convenient. Who is building the first 100% AI-native movie maker?
0:28

I'm playing around with generative AI tools and stitching them together into visual stories. Here I took the first few sentences of Pride and Prejudice and made it into a video. The gen stack used for this one: - Anthropic Claude took the first chapter, generated the scenes and the individual prompts to to the image generator. - Ideogram took the prompts and generate the images - Luma took the images and animated them - for narration - VEED | AI Video Creation to stitch it together (Many of these choices are just what I happened to use for this one while exploring a bunch of things). Anyway honestly it was pretty messy and there is a ton of copy pasting between all of the tools, and even this little video with 3 scenes took me about an hour. There is a huge storytelling opportunity here for whoever can make this convenient. Who is building the first 100% AI-native movie maker?

Andrej Karpathy

611,323 просмотров • 2 лет назад

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!
0:22

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!

MIKE

217,108 просмотров • 1 месяц назад

Week 9 of building a fishing game almost entirely with AI The AI workflow has changed again since Opus 5.5 arrived. Opus now handles most of the coding and even sound design. With access to ElevenLabs, it generates sounds and places them directly into the game, followed by manual adjustments where needed. Astra is mostly used for all-in-one visual tasks like generating textures and integrating them into the game. TripoAI generates the new 3D characters, while Blender MCP handles model fixes. The project itself now has 30+ fish in the first zone, redesigned characters, textured harbours, updated UI and a new moral dilemma system. The agent setup is probably the most interesting part: separate Claude sessions handle fishing, shaders, sound and other systems, while one Manager session coordinates all of them. The agents are basically running 24/7 at this point. Week 9, and the project is now going through Steam verification with a public demo planned in the next few weeks.
3:15

Week 9 of building a fishing game almost entirely with AI The AI workflow has changed again since Opus 5.5 arrived. Opus now handles most of the coding and even sound design. With access to ElevenLabs, it generates sounds and places them directly into the game, followed by manual adjustments where needed. Astra is mostly used for all-in-one visual tasks like generating textures and integrating them into the game. TripoAI generates the new 3D characters, while Blender MCP handles model fixes. The project itself now has 30+ fish in the first zone, redesigned characters, textured harbours, updated UI and a new moral dilemma system. The agent setup is probably the most interesting part: separate Claude sessions handle fishing, shaders, sound and other systems, while one Manager session coordinates all of them. The agents are basically running 24/7 at this point. Week 9, and the project is now going through Steam verification with a public demo planned in the next few weeks.

Hakimi Eiqbal

29,876 просмотров • 1 месяц назад

"The more that you let them think about things, the better the results will be." The newest AI agents are more capable because they are designed to take time, reason through problems, and make a plan. Our latest AI Explainer breaks down why giving agents more time produces proportionally better results.
1:32

"The more that you let them think about things, the better the results will be." The newest AI agents are more capable because they are designed to take time, reason through problems, and make a plan. Our latest AI Explainer breaks down why giving agents more time produces proportionally better results.

Box

2,974,585 просмотров • 4 месяцев назад

It cost me $15 on the Epic Games Store and a few million AI tokens to build this web-native grass simulation. Demo in the comments. Epic Games owns Quixel, a collection of high-quality Megascans. You can use them in Three.js, which is exactly what we did in this demo. The butterflies, flowers, and surfaces all come from Megascans. The long grass and wind simulation were converted from Blender Geometry Nodes simulations, which is why it feels so good. Then add an HDRI, set up the lighting, and boom—you have highly realistic grass rendered fully on the web. While it’s something built with AI, a non-designer without a certain set of skills would never be able to do this. You still need the knowledge, terminology, and understanding required to glue all these technologies together.
0:28

It cost me $15 on the Epic Games Store and a few million AI tokens to build this web-native grass simulation. Demo in the comments. Epic Games owns Quixel, a collection of high-quality Megascans. You can use them in Three.js, which is exactly what we did in this demo. The butterflies, flowers, and surfaces all come from Megascans. The long grass and wind simulation were converted from Blender Geometry Nodes simulations, which is why it feels so good. Then add an HDRI, set up the lighting, and boom—you have highly realistic grass rendered fully on the web. While it’s something built with AI, a non-designer without a certain set of skills would never be able to do this. You still need the knowledge, terminology, and understanding required to glue all these technologies together.

Alex Barashkov

16,700 просмотров • 3 месяцев назад

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.
1:26

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.

Meng To

583,147 просмотров • 1 месяц назад

AI art is extremely controversial and most artists are on the left. This [video below] is the current sentiment and it’s unfortunately way too broad and limiting But yeah, because art is top of mind for them, the sentiment towards AI in every domain stems from it
1:09

AI art is extremely controversial and most artists are on the left. This [video below] is the current sentiment and it’s unfortunately way too broad and limiting But yeah, because art is top of mind for them, the sentiment towards AI in every domain stems from it

Jules

55,227 просмотров • 1 год назад

Can we call this AI directing? 😂 Seedance 2.0 with the Omni Reference feature honestly feels like a total game changer. Summer Trip is one of my film which I made used Omni Reference, not only start frame anymore and for the first time, it genuinely feels like I’m directing the AI instead of just prompting it. The reasoning in Seedance 2.0 is seriously impressive. It understands intent in a way that feels collaborative. Of course, in production it still needs proper touch-ups in post, grading, timing, polishing details, but the foundation it gives is strong. Like it or not, we’re already here. And to be honest, my workflow has to evolve too. I can’t approach this the same way I did before. It’s less about generating random shots and more about guiding, refining, and thinking like a director from the start. Personally, I see this as a shift, not replacing filmmaking, but reshaping the role of the filmmaker. Now the question isn’t “Can AI make it?” but “How well can you direct it?”
2:19

Can we call this AI directing? 😂 Seedance 2.0 with the Omni Reference feature honestly feels like a total game changer. Summer Trip is one of my film which I made used Omni Reference, not only start frame anymore and for the first time, it genuinely feels like I’m directing the AI instead of just prompting it. The reasoning in Seedance 2.0 is seriously impressive. It understands intent in a way that feels collaborative. Of course, in production it still needs proper touch-ups in post, grading, timing, polishing details, but the foundation it gives is strong. Like it or not, we’re already here. And to be honest, my workflow has to evolve too. I can’t approach this the same way I did before. It’s less about generating random shots and more about guiding, refining, and thinking like a director from the start. Personally, I see this as a shift, not replacing filmmaking, but reshaping the role of the filmmaker. Now the question isn’t “Can AI make it?” but “How well can you direct it?”

Dinda Prasetyo

29,385 просмотров • 8 месяцев назад

Can't believe in less than 24 hours I created my own game with Claude and Three.js. Running in a browser at 120 FPS. All I had to do was give Claude the repo for Threejs and describe an MMO-like game for it to build from scratch. All the assets and mechanics you see are all from a prompt. As you can see, it is far from done but the progress is insane. Everyone should be using Three.js now without a doubt!
0:59

Can't believe in less than 24 hours I created my own game with Claude and Three.js. Running in a browser at 120 FPS. All I had to do was give Claude the repo for Threejs and describe an MMO-like game for it to build from scratch. All the assets and mechanics you see are all from a prompt. As you can see, it is far from done but the progress is insane. Everyone should be using Three.js now without a doubt!

NeilXbt

23,504 просмотров • 2 месяцев назад

GPT-6 Astra is cracked at making games. This runs in the browser with three.js. It even modeled the cars in Blender. The next GTA will be made by AI.
0:52

GPT-6 Astra is cracked at making games. This runs in the browser with three.js. It even modeled the cars in Blender. The next GTA will be made by AI.

Shikhar

586,417 просмотров • 1 месяц назад