Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

#ComfyUI #Comfy3D @ZHOZHO672070 Yanpei Cao Comfy3D Update: - 3D Visualization for Gaussians & Mesh - First single image to 3D full pipeline - Coordinate system axis re-mapping I know, currently DMTet is not good enough😝 Future Development Roadmap:

Mr. For Example

6,104 subscribers

13,063 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie Bildung Kunst #ComfyUI #Comfy3D

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von R3N

R3Nvor 2 Jahren

@ZHOZHO672070 @yanpei_cao Its possible to use more than one image of reference to create the preview? it is something i miss on the major apps, all focus in just one single image, but use 2 3 4 will be awesome.

Profilbild von Mr. For Example

Mr. For Examplevor 2 Jahren

@ZHOZHO672070 @yanpei_cao Yeah, I have similar though recently, currently the only feasible way that I think of is to perform spatial attention feature injection like in: or

Profilbild von leolee

leoleevor 2 Jahren

@ZHOZHO672070 @yanpei_cao Very interesting and useful node! Awesome. But one question please, I used 120 angle maps and the generated result is not so good, which parameters should I pay attention to?

Profilbild von Mr. For Example

Mr. For Examplevor 2 Jahren

@ZHOZHO672070 @yanpei_cao You can incorporate elevation angle when generate the camera pose. Also, is strange that 3DGS preview looks that fuzzy🤔 did you use the Stable123 to generate multi-view images?

Profilbild von Radiance Fields

Radiance Fieldsvor 2 Jahren

@ZHOZHO672070 @yanpei_cao Could you open your DMs please?

Profilbild von Mr. For Example

Mr. For Examplevor 2 Jahren

@ZHOZHO672070 @yanpei_cao Apologies, it should be open now, I think I closed it at some point the past because I got too many scam on daily basis😅

Profilbild von -Zho-

-Zho-vor 2 Jahren

@yanpei_cao Wow! That’s awesome! I’ll test it in a moment!

Profilbild von Kakachiex2

Kakachiex2vor 2 Jahren

@ZHOZHO672070 @yanpei_cao It is available in your GitHub...?

Profilbild von Albert Papadosifakis

Albert Papadosifakisvor 2 Jahren

@ZHOZHO672070 @yanpei_cao Awesome!

Profilbild von Legend Of Kalimar

Legend Of Kalimarvor 2 Jahren

@ZHOZHO672070 @yanpei_cao Is this a 3d model? I guess you can definetly combine this with something to get a mesh.

Ähnliche Videos

Comfy3D Update: (v0.1.5.alpha, dev branch) - Integrated TripoSG (Plus scribble model) - MV-Adapter for high quality texture gen coming next ‼️NeuralAI We are hiring skilled ML researchers & engineers (VAE, diffusion model, 3D/texture gen/editing) to join us on a mission to revolutionize 3D virtual production 🫰If you want to work on open-source projects (Not only Comfy3D), make an impact in the industry all while getting paid handsomely, hit me up in DM! (English | 中文 | 日本語 🆗) 田中義弘 | taziku CEO / AI × Creative -Zho- toyxyz Tripo🔜SIGGRAPH2026 Robin Huang ComfyUI VAST AI Research Yanpei Cao Neuro

Comfy3D Update: (v0.1.5.alpha, dev branch) - Integrated TripoSG (Plus scribble model) - MV-Adapter for high quality texture gen coming next ‼️NeuralAI We are hiring skilled ML researchers & engineers (VAE, diffusion model, 3D/texture gen/editing) to join us on a mission to revolutionize 3D virtual production 🫰If you want to work on open-source projects (Not only Comfy3D), make an impact in the industry all while getting paid handsomely, hit me up in DM! (English | 中文 | 日本語 🆗) 田中義弘 | taziku CEO / AI × Creative -Zho- toyxyz Tripo🔜SIGGRAPH2026 Robin Huang ComfyUI VAST AI Research Yanpei Cao Neuro

Mr. For Example

14,785 Aufrufe • vor 1 Jahr

🚀Exciting News! Tencent Hunyuan 3D AI Creation Engine v2.5 is here, revolutionizing 3D generation with ultra-high-definition modeling! 1⃣Massive Leap in Precision: Upgraded geometric model with 10B parameters (up from 1B) and 10x more mesh faces, delivering 1024-resolution geometric details—smoother surfaces, sharper edges, and richer visuals! 2⃣High-quality Textures & PBR: Supports high-quality textures and fine-grained bump mapping for lifelike surfaces. Industry-first multi-view PBR generation for realistic lighting and reflections. 3⃣Animation Boost: Optimized skeletal rigging with automatic bone binding and skin weight assignment, streamlining 3D animation workflows. 4⃣Flexible Workflows: New pipeline templates for text-to-3D and image-to-3D mesh reduction, plus multi-view 3D generation, empowering game development, animation, and more with customizable 3D assets. 5⃣Accessible Creation: Generate high-quality 3D models from text or images, slashing complexity. Free daily quota doubled to 20 for the AI Engine, with the API now live on Tencent Cloud! ☀️From games to AR/VR, Hunyuan 3D is redefining 3D AIGC, making creation faster, smarter, and more inclusive. Try it now! Tencent Hunyuan 3D AI Creation Engine: Tencent Hunyuan 3D Open Source:

🚀Exciting News! Tencent Hunyuan 3D AI Creation Engine v2.5 is here, revolutionizing 3D generation with ultra-high-definition modeling! 1⃣Massive Leap in Precision: Upgraded geometric model with 10B parameters (up from 1B) and 10x more mesh faces, delivering 1024-resolution geometric details—smoother surfaces, sharper edges, and richer visuals! 2⃣High-quality Textures & PBR: Supports high-quality textures and fine-grained bump mapping for lifelike surfaces. Industry-first multi-view PBR generation for realistic lighting and reflections. 3⃣Animation Boost: Optimized skeletal rigging with automatic bone binding and skin weight assignment, streamlining 3D animation workflows. 4⃣Flexible Workflows: New pipeline templates for text-to-3D and image-to-3D mesh reduction, plus multi-view 3D generation, empowering game development, animation, and more with customizable 3D assets. 5⃣Accessible Creation: Generate high-quality 3D models from text or images, slashing complexity. Free daily quota doubled to 20 for the AI Engine, with the API now live on Tencent Cloud! ☀️From games to AR/VR, Hunyuan 3D is redefining 3D AIGC, making creation faster, smarter, and more inclusive. Try it now! Tencent Hunyuan 3D AI Creation Engine: Tencent Hunyuan 3D Open Source:

Tencent Hy

58,225 Aufrufe • vor 1 Jahr

Tested this concepting workflow. ▶️ Converting a level design image to a 3D asset gallery image ▶️ re-generating segmented subjects into separate high quality images. ▶️ using these images to generate the 3D meshes. First time using 'for loops' in ComfyUI, works great and the prompts are updated for every segment. I used the Nano Banana 2 API node in ComfyUI to generate the final high quality images. Those SAM3 nodes are crazy btw, just set some points and it creates a mask! For the 3D model generation I used the new Tripo Smart Mesh tool, which is fast! The output is not perfect yet. I think in a lot of cases not production ready right now but that depends on the input image and the goal as well. For pre-production / concepting phase it's perfect and for far distance meshes it’s fine. I’m sure these tools keep improving, curious what we can work with in 3-6 months. Minimal cleanup and scaling in Blender and tested the meshes in UEFN / Unreal Engine. After creating the ComfyUI workflow it took less than an hour to do everything.

Tested this concepting workflow. ▶️ Converting a level design image to a 3D asset gallery image ▶️ re-generating segmented subjects into separate high quality images. ▶️ using these images to generate the 3D meshes. First time using 'for loops' in ComfyUI, works great and the prompts are updated for every segment. I used the Nano Banana 2 API node in ComfyUI to generate the final high quality images. Those SAM3 nodes are crazy btw, just set some points and it creates a mask! For the 3D model generation I used the new Tripo Smart Mesh tool, which is fast! The output is not perfect yet. I think in a lot of cases not production ready right now but that depends on the input image and the goal as well. For pre-production / concepting phase it's perfect and for far distance meshes it’s fine. I’m sure these tools keep improving, curious what we can work with in 3-6 months. Minimal cleanup and scaling in Blender and tested the meshes in UEFN / Unreal Engine. After creating the ComfyUI workflow it took less than an hour to do everything.

Jerome | InsaneUnreal

17,461 Aufrufe • vor 5 Monaten

Introducing WorldView 3D, a first-of-its-kind satellite tasking product that delivers up-to-date 3D ground truth anywhere on Earth. From GPS-denied autonomy and intelligence analysis to consumer-grade mapping and disaster response, the world's most important missions increasingly depend on accurate, up-to-date 3D terrain. But for years, keeping 3D maps current at global scale hasn't been possible. WorldView 3D changes that. Built on Vantor’s trusted spatial foundation, our new tasking capability empowers customers to task and receive updated 3D data within 24 hours of image collection. For missions that require greater fidelity, they can also produce high-definition 3D maps anywhere in the world. 3D is the future of spatial intelligence, and Vantor is leading the change. Our trusted spatial foundation already includes 100 million sq km of the world mapped inhighly accurate 3D. Now customers can update the locations that matter most with the speed, scale, and fidelity required for critical missions. Read the full announcement:

Introducing WorldView 3D, a first-of-its-kind satellite tasking product that delivers up-to-date 3D ground truth anywhere on Earth. From GPS-denied autonomy and intelligence analysis to consumer-grade mapping and disaster response, the world's most important missions increasingly depend on accurate, up-to-date 3D terrain. But for years, keeping 3D maps current at global scale hasn't been possible. WorldView 3D changes that. Built on Vantor’s trusted spatial foundation, our new tasking capability empowers customers to task and receive updated 3D data within 24 hours of image collection. For missions that require greater fidelity, they can also produce high-definition 3D maps anywhere in the world. 3D is the future of spatial intelligence, and Vantor is leading the change. Our trusted spatial foundation already includes 100 million sq km of the world mapped inhighly accurate 3D. Now customers can update the locations that matter most with the speed, scale, and fidelity required for critical missions. Read the full announcement:

Vantor

16,030 Aufrufe • vor 1 Monat

The battle of the Text/Image to 3D Model 👍- To make this fair, I tested the same image across all platforms and used the first generated result. No cherry picking allowed! I also tested what I think are the 4 top services to use right now. Let me know what you think is the best 3D mesh generation from these platforms however I think it's quite obvious that Tencent Hy 2.5 is currently the king 👑 It wins in overall detail and sharpness, accuracy in relation to the input image, as well as texture generation and projection. Tripo 2.5 comes in second and Rodin 3rd with Trellis in 4th place. However, Rodin has the best topology since it can generate a mesh in quads BUT I left all of them in triangles to keep it fair. Hi3DGen can't be counted as it can't even generate textures and it has no multi-image support. Meshy was another option but the results were not great. Is there any other AI 3D Gen services that you know of that you want me to test as well?

The battle of the Text/Image to 3D Model 👍- To make this fair, I tested the same image across all platforms and used the first generated result. No cherry picking allowed! I also tested what I think are the 4 top services to use right now. Let me know what you think is the best 3D mesh generation from these platforms however I think it's quite obvious that Tencent Hy 2.5 is currently the king 👑 It wins in overall detail and sharpness, accuracy in relation to the input image, as well as texture generation and projection. Tripo 2.5 comes in second and Rodin 3rd with Trellis in 4th place. However, Rodin has the best topology since it can generate a mesh in quads BUT I left all of them in triangles to keep it fair. Hi3DGen can't be counted as it can't even generate textures and it has no multi-image support. Meshy was another option but the results were not great. Is there any other AI 3D Gen services that you know of that you want me to test as well?

Travis Davids

61,232 Aufrufe • vor 1 Jahr

Why do we still buy stadium tickets without ever seeing what the view from the seat actually looks like? ☠️ So I prototyped an idea. A 3D seat view experience for a football stadium built with Fable 5 + Three.js, where you can preview exactly what you'll see from your seat before buying. The entire 3D experience was working after the first prompt, and the whole prototype came together in just five prompts. This is the kind of 3D experience I'd love to see more of, tbh. Feels so good. Right now, buying a ticket gives you almost no sense of what the experience will actually feel like. We're still relying on static seat maps, charts, and boring UI layouts, when interactive 3D experiences could make that decision so much easier. If you think, 3D development has the potential to create genuinely useful experiences. This feels like the direction we should be heading. 3D is the future. I can already imagine this for cinemas, cricket stadiums, Wimbledon, concerts, and so many other venues. I'm planning to take this further. What should I build next? More stadium features, or should I try another venue? Let me know :D Code: Live:

Why do we still buy stadium tickets without ever seeing what the view from the seat actually looks like? ☠️ So I prototyped an idea. A 3D seat view experience for a football stadium built with Fable 5 + Three.js, where you can preview exactly what you'll see from your seat before buying. The entire 3D experience was working after the first prompt, and the whole prototype came together in just five prompts. This is the kind of 3D experience I'd love to see more of, tbh. Feels so good. Right now, buying a ticket gives you almost no sense of what the experience will actually feel like. We're still relying on static seat maps, charts, and boring UI layouts, when interactive 3D experiences could make that decision so much easier. If you think, 3D development has the potential to create genuinely useful experiences. This feels like the direction we should be heading. 3D is the future. I can already imagine this for cinemas, cricket stadiums, Wimbledon, concerts, and so many other venues. I'm planning to take this further. What should I build next? More stadium features, or should I try another venue? Let me know :D Code: Live:

The Bugged Dev

1,671,013 Aufrufe • vor 1 Monat

I am happy to be finally able to post what I was able to build over the last few weeks. A full real-time high-frequency state estimation and mapping algorithm completely written line by line from scratch in Rust, which can be used by robots to navigate and reason within the 3D world also in complicated scenarios. TBH this took me longer than expected (which was still super fast :D) but you need to get a lot right: From the sensors over the drivers to their respective estimation pipeline and then fusing everything together - a covariance nightmare - and something that can be refined over years to come (currently using Fisher Information from the real measurements). What you see here is not the output of some structure from motion or Gaussian splatting, these are the points of a tight mesh (high res for the video) that a robot can use in real time to plan a path using any open-source planner. The flight you experience through the world is the actual state estimate of the scanner which is published at IMU rate. Yes, currently we have some artefacts of filtered-out humans (GDPR compliant of course :) ) and moving cars and there is still some calibration that could be improved. Offline refinement with SFM and Gaussian splats is possible as well but currently not on the road map. What is on the road map is an exciting step of now being able to collect data from customers at construction sites and in warehouses (currently handheld in the near future with a robot). This data can then be used by our physical agents to reason within this world and automate any customer’s task related to 3D data. If you have anyone who wastes time manually looking 👀 through 3D data, or cannot collect enough 3D data and interpret: Tell me how to reach them!

I am happy to be finally able to post what I was able to build over the last few weeks. A full real-time high-frequency state estimation and mapping algorithm completely written line by line from scratch in Rust, which can be used by robots to navigate and reason within the 3D world also in complicated scenarios. TBH this took me longer than expected (which was still super fast :D) but you need to get a lot right: From the sensors over the drivers to their respective estimation pipeline and then fusing everything together - a covariance nightmare - and something that can be refined over years to come (currently using Fisher Information from the real measurements). What you see here is not the output of some structure from motion or Gaussian splatting, these are the points of a tight mesh (high res for the video) that a robot can use in real time to plan a path using any open-source planner. The flight you experience through the world is the actual state estimate of the scanner which is published at IMU rate. Yes, currently we have some artefacts of filtered-out humans (GDPR compliant of course :) ) and moving cars and there is still some calibration that could be improved. Offline refinement with SFM and Gaussian splats is possible as well but currently not on the road map. What is on the road map is an exciting step of now being able to collect data from customers at construction sites and in warehouses (currently handheld in the near future with a robot). This data can then be used by our physical agents to reason within this world and automate any customer’s task related to 3D data. If you have anyone who wastes time manually looking 👀 through 3D data, or cannot collect enough 3D data and interpret: Tell me how to reach them!

Benedikt Seidel

16,656 Aufrufe • vor 3 Monaten

Not all automation needs an arm 🦾I That’s right, AmbiRobotics just released their new product - a palletizing gantry system. It’s called AmbiStack, and at first glance, it looks like a 3D tetris. 🥞 It’s a mechanical system designed to automate the stacking and packing of items in warehouses. The system uses Sim2Real reinforcement learning and advanced AI vision technology to optimize how items are sorted and stacked. Even without prior knowledge of their size, shape, or appearance. 📦 AmbiStack can stack items densely onto pallets or into walled containers, maximizing space and reducing warehouse transportation costs. It is a multipurpose solution that can be used for different applications, such as building pallets for retail distribution or stacking items directly on the floor. The system is highly adaptable, able to handle both single-SKU and mixed-SKU cases, and can stack items in any orientation for maximum flexibility. AmbiStack features multi-pick-and-place capabilities, allowing it to pick and place multiple items at once, significantly improving workflow efficiency. P.S. Yes, I know that gantry is technically a three-axis robot.

Not all automation needs an arm 🦾I That’s right, AmbiRobotics just released their new product - a palletizing gantry system. It’s called AmbiStack, and at first glance, it looks like a 3D tetris. 🥞 It’s a mechanical system designed to automate the stacking and packing of items in warehouses. The system uses Sim2Real reinforcement learning and advanced AI vision technology to optimize how items are sorted and stacked. Even without prior knowledge of their size, shape, or appearance. 📦 AmbiStack can stack items densely onto pallets or into walled containers, maximizing space and reducing warehouse transportation costs. It is a multipurpose solution that can be used for different applications, such as building pallets for retail distribution or stacking items directly on the floor. The system is highly adaptable, able to handle both single-SKU and mixed-SKU cases, and can stack items in any orientation for maximum flexibility. AmbiStack features multi-pick-and-place capabilities, allowing it to pick and place multiple items at once, significantly improving workflow efficiency. P.S. Yes, I know that gantry is technically a three-axis robot.

Lukas Ziegler

24,133 Aufrufe • vor 1 Jahr

Krispy Kreme is up ~50% in the past week and become a meme stock. Have no idea if it’s a good investment but do know that its manufacturing process is impressive. They sell 2B+ donuts a year and designed equipment that can crank out 3,000 donuts an hour: ▫️Extruder uses proprietary process of pressurized hot air to form ring-shaped donuts without cutting a hole (donuts are shaped as such for even cooking) ▫️The proofer area has a special conveyor system and heating process for exact temperature and humidity ▫️Custom Siemens control ensures conveyor belt fryer is constant speed and glazing hose pump has same flow rate for consistency (I repeat: “glazing hose pump has same flow rate”) ▫️The conveyor belt is made of special stainless steel mesh that can withstand heat, corrosive sugars and abrasive oils Krispy Kreme also had to design the system for the in-store theatre viewing. Obviously not the healthiest things in the world but some legit engineering decisions and designs were made. *** Full 3D animation from Jared Owen (amazing channel): Food Engineering:

Krispy Kreme is up ~50% in the past week and become a meme stock. Have no idea if it’s a good investment but do know that its manufacturing process is impressive. They sell 2B+ donuts a year and designed equipment that can crank out 3,000 donuts an hour: ▫️Extruder uses proprietary process of pressurized hot air to form ring-shaped donuts without cutting a hole (donuts are shaped as such for even cooking) ▫️The proofer area has a special conveyor system and heating process for exact temperature and humidity ▫️Custom Siemens control ensures conveyor belt fryer is constant speed and glazing hose pump has same flow rate for consistency (I repeat: “glazing hose pump has same flow rate”) ▫️The conveyor belt is made of special stainless steel mesh that can withstand heat, corrosive sugars and abrasive oils Krispy Kreme also had to design the system for the in-store theatre viewing. Obviously not the healthiest things in the world but some legit engineering decisions and designs were made. *** Full 3D animation from Jared Owen (amazing channel): Food Engineering:

Trung Phan

57,456 Aufrufe • vor 1 Jahr

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,841 Aufrufe • vor 11 Monaten

** 3D Engine Update 6 ** New Buffer System. 15-20% Faster !! Using Planes A and B interleaved horizontally we can get the best of all worlds with a near continuous frame buffer for fast Triangle & Quad writes and still use DMA for fast sending of the RAM frame buffer to VRAM. Normally you get one benefit without the other leading to tradeoffs. There is a caveat ofcourse, I lose a spare plane , however thats not a large concern for what im trying to achieve, i still have the full sprite load if i need to simulate ground etc - we can also multiplex sprites if needed. So each plane is full of half fill tiles ( 4 pixels set in each tile row ) , which are then slightly offset to make the full image. Also changed to H40 mode for faster DMA albiet centered view , plenty of Hud options for side panels etc. What is quite cool is the layout in VRAM is very similar to what you see on screen just with some striping . VRAM layout to the right. Theres no more VRAM used verse a normal double buffer , the trick is here to send the buffer in one frame always as theres no room for a double buffer in vram. I have to implement partial ofscreen drawing yet hence the snapping from front to back you see still . #SGDK #SegaGenesis #SegaMegadrive

3D Engine Update 6 New Buffer System. 15-20% Faster !! Using Planes A and B interleaved horizontally we can get the best of all worlds with a near continuous frame buffer for fast Triangle & Quad writes and still use DMA for fast sending of the RAM frame buffer to VRAM. Normally you get one benefit without the other leading to tradeoffs. There is a caveat ofcourse, I lose a spare plane , however thats not a large concern for what im trying to achieve, i still have the full sprite load if i need to simulate ground etc - we can also multiplex sprites if needed. So each plane is full of half fill tiles ( 4 pixels set in each tile row ) , which are then slightly offset to make the full image. Also changed to H40 mode for faster DMA albiet centered view , plenty of Hud options for side panels etc. What is quite cool is the layout in VRAM is very similar to what you see on screen just with some striping . VRAM layout to the right. Theres no more VRAM used verse a normal double buffer , the trick is here to send the buffer in one frame always as theres no room for a double buffer in vram. I have to implement partial ofscreen drawing yet hence the snapping from front to back you see still . #SGDK #SegaGenesis #SegaMegadrive

Shannon Birt

12,052 Aufrufe • vor 3 Monaten

Updated 3D world generated from a reference image with Opus 5. This burned 20% of my weekly quota, but now I can interact with objects in the space and it remembers previous interactions. It started generating indoors but had to stop it (didn't want to burn through my weekly limits). The interesting part was the iterative refinement from Opus 5 subagents. The first pass was not great visually (see the post below), but quality improved dramatically as the agents iterated and validated their own work (really impressed). Its incredible that these agents have subjective assessment on what "visually" appealing looks like. Prompt used with Opus 5 (ultracode) + reference image: Build an explorable 3D world in Three.js based on the attached image. Requirements First-person controls (WASD + mouse look), collision detection, no clipping through geometry AAA visuals: PBR materials, HDRI-based lighting, real shadows, post-processing (tone mapping, bloom, AA) Physics on anything that moves or can be interacted with 60fps on a mid-range GPU Process Split the work into independent streams: terrain, props/geometry, materials/textures, lighting, physics, controls/camera, performance. Assign one sub-agent per stream. Each sub-agent owns its stream end to end and reports what it built plus what is still weak. Integrate, then run a review pass: walk the world, list every visible defect, fix them. Repeat that loop until a full pass produces zero defects, or until 5 loops. Report anything unresolved either way. Deliver a single runnable project plus launch instructions.

Updated 3D world generated from a reference image with Opus 5. This burned 20% of my weekly quota, but now I can interact with objects in the space and it remembers previous interactions. It started generating indoors but had to stop it (didn't want to burn through my weekly limits). The interesting part was the iterative refinement from Opus 5 subagents. The first pass was not great visually (see the post below), but quality improved dramatically as the agents iterated and validated their own work (really impressed). Its incredible that these agents have subjective assessment on what "visually" appealing looks like. Prompt used with Opus 5 (ultracode) + reference image: Build an explorable 3D world in Three.js based on the attached image. Requirements First-person controls (WASD + mouse look), collision detection, no clipping through geometry AAA visuals: PBR materials, HDRI-based lighting, real shadows, post-processing (tone mapping, bloom, AA) Physics on anything that moves or can be interacted with 60fps on a mid-range GPU Process Split the work into independent streams: terrain, props/geometry, materials/textures, lighting, physics, controls/camera, performance. Assign one sub-agent per stream. Each sub-agent owns its stream end to end and reports what it built plus what is still weak. Integrate, then run a review pass: walk the world, list every visible defect, fix them. Repeat that loop until a full pass produces zero defects, or until 5 loops. Report anything unresolved either way. Deliver a single runnable project plus launch instructions.

Prompt

26,349 Aufrufe • vor 23 Tagen

I might loose some followers on this… But this is how I treat my portfolio: Like a mf psychopath…… I just sold $TE at almost breakeven. Could see it running to $6.18 or $5.19. depending on how it closes today. I REALLY like $TE. I’m super bullish on energy/power demand. BUT… no matter what argument, I cannot defend 16% allocated to $TE when they just fired their CAO right before earnings with zero explanation. I’m not buying the “we’re getting a better one” argument. This excuse has been used for 20 years while *files* keep building up. How did that work? Most important lesson in life: money talks. People will do almost anything for enough money. In hindsight of what files are circulating these days, fraud seems like nothing. I know this is contrarian. And I also KNOW there’s no proof of it. But this is EXACTLY why it’s critical to have hard rules for your investments. The RISK is on YOU. The reason I watch my portfolio like a psychopath? To minimize loss. To minimize risk. I’m not betting my hard-earned money. I will NEVER invest in companies with: > Lack of communication > Lack of transparency > Lack of trust I can live with debt. I can live with execution risk. But when management starts shutting out investors or goes radio silent? Just before earnings… That’s the biggest RED FLAG to me. We live in 2026. It takes a CEO 5 minutes to post an update on X or record a video. And no, I don’t buy the CEO is busy either. I manage people myself everyday. It comes down to priorities. It’s not good enough for me. I wish all my fellow $TE the best luck! I sincerely mean that and pray that you all get rich and I’m mistaken 🫶 I’m out. Watching to re-enter $NBIS or $KRKNF now.

I might loose some followers on this… But this is how I treat my portfolio: Like a mf psychopath…… I just sold $TE at almost breakeven. Could see it running to $6.18 or $5.19. depending on how it closes today. I REALLY like $TE. I’m super bullish on energy/power demand. BUT… no matter what argument, I cannot defend 16% allocated to $TE when they just fired their CAO right before earnings with zero explanation. I’m not buying the “we’re getting a better one” argument. This excuse has been used for 20 years while files keep building up. How did that work? Most important lesson in life: money talks. People will do almost anything for enough money. In hindsight of what files are circulating these days, fraud seems like nothing. I know this is contrarian. And I also KNOW there’s no proof of it. But this is EXACTLY why it’s critical to have hard rules for your investments. The RISK is on YOU. The reason I watch my portfolio like a psychopath? To minimize loss. To minimize risk. I’m not betting my hard-earned money. I will NEVER invest in companies with: > Lack of communication > Lack of transparency > Lack of trust I can live with debt. I can live with execution risk. But when management starts shutting out investors or goes radio silent? Just before earnings… That’s the biggest RED FLAG to me. We live in 2026. It takes a CEO 5 minutes to post an update on X or record a video. And no, I don’t buy the CEO is busy either. I manage people myself everyday. It comes down to priorities. It’s not good enough for me. I wish all my fellow $TE the best luck! I sincerely mean that and pray that you all get rich and I’m mistaken 🫶 I’m out. Watching to re-enter $NBIS or $KRKNF now.

Black Panther Capital

71,384 Aufrufe • vor 6 Monaten

Tony Robbins on how to change someone who doesn't want to change: 1. People only change when they link enough pain to staying the same or enough pleasure to changing. Ideally, both at once. This is not a mindset shift. It happens in the nervous system, not the head. Your head can know exactly what you should do, and your gut will override it every single time. 2. Yes, you can change someone who doesn't want to change. But not by forcing them. You find the leverage that makes them change themselves. Everyone has a point that will get them to follow through. For some people, it is not even the threat of their own life. For others, it is their children. For others, it is spiritual growth. The leverage is different for everyone, but it always exists. 3. The food poisoning example. You used to love a food or a drink. Then one night it came back up with enough intensity and enough aroma that to this day you cannot look at it without feeling repelled. No willpower required. Your brain simply rewired what it links pleasure to. That is the entire mechanism of change in one story. 4. Scrooge did not want to change. He was certain he did not need to change. Three ghosts showed up and did one thing: they made him link unbearable pain to his past, his present, and his future simultaneously. When there is nowhere to escape, change happens in a heartbeat. Robbins calls this the Dickens pattern. Lock pain into all three time zones at once, and there is no exit. 5. People avoid changing by escaping to a different time period. If the present is painful, escape to a good memory from the past. If the past was also painful, invent a better future and escape there. As long as one of those three zones offers relief, the pressure to change dissolves. Removing all three exits and change becomes inevitable. 6. Problem is some people have accidentally linked pain to things they actually need: exercise, intimacy, and hard conversations. The association is wrong, but it runs their life anyway. The job is not to build more willpower. It is to change what you have linked pain and pleasure to in the first place.

Tony Robbins on how to change someone who doesn't want to change: 1. People only change when they link enough pain to staying the same or enough pleasure to changing. Ideally, both at once. This is not a mindset shift. It happens in the nervous system, not the head. Your head can know exactly what you should do, and your gut will override it every single time. 2. Yes, you can change someone who doesn't want to change. But not by forcing them. You find the leverage that makes them change themselves. Everyone has a point that will get them to follow through. For some people, it is not even the threat of their own life. For others, it is their children. For others, it is spiritual growth. The leverage is different for everyone, but it always exists. 3. The food poisoning example. You used to love a food or a drink. Then one night it came back up with enough intensity and enough aroma that to this day you cannot look at it without feeling repelled. No willpower required. Your brain simply rewired what it links pleasure to. That is the entire mechanism of change in one story. 4. Scrooge did not want to change. He was certain he did not need to change. Three ghosts showed up and did one thing: they made him link unbearable pain to his past, his present, and his future simultaneously. When there is nowhere to escape, change happens in a heartbeat. Robbins calls this the Dickens pattern. Lock pain into all three time zones at once, and there is no exit. 5. People avoid changing by escaping to a different time period. If the present is painful, escape to a good memory from the past. If the past was also painful, invent a better future and escape there. As long as one of those three zones offers relief, the pressure to change dissolves. Removing all three exits and change becomes inevitable. 6. Problem is some people have accidentally linked pain to things they actually need: exercise, intimacy, and hard conversations. The association is wrong, but it runs their life anyway. The job is not to build more willpower. It is to change what you have linked pain and pleasure to in the first place.

Jaynit

281,133 Aufrufe • vor 2 Monaten

** Sega Genesis 3D Engine Update 8 ** Significant improvements all round as you can see and hear from the last update !! Foremost - A huge thanks to Toni Gálvez - Megastyle - BG. who has joined the project to create a bit of 16bit low poly magic. Toni's an Amiga fan but also crazy about game dev in general, he's worked on GBC, GBA, PC, MD, PSP, C64, CPC, MSX... and others. Gaming titles include War Times, Metal Gear, Rocketman, Tintin & Asterix to name a few. He's provided the great new ship model you see on screen - new striped buildings, all the backgrounds / palettes etc. There's a lot of models he's given me which need to be added, also he will be planning a lot of the level design. Very happy to have him help me turn this into something more than a tech demo as I have my hands tied pushing the MD as far as it can go haha - there is no cpu cycle to be spared. Also many thanks to my good friend CYBERDEOUS - Crouzet Laurent for the Music for this showing , I wanted to have the music load occurring so we have a realistic benchmark for performance and he was only too obliging. If you're into MD chiptunes check him out !! Since last update : New player model , substantially more detailed than the Arwing. Last update had a 23 triangle Arwing , this update has a 39 triangle custom model from Toni. We had several to choose from , others will be used for enemies . 3D Buffer size increased 25% to 256x160. This was quite tricky as I'm close to the DMA limit even with an extended vblank . Spent a few days thinking of how to do this as like anything retro every solution has a drawback, finally got a workable solution. It makes a big difference to have a bit more vertical height . Z Rotation added ( the screen tilting left to right ) , small hit to vertex transform on cpu thanks to look up tables doing the heavy lifting, saving 4 multiplies per vertex. Multiple speed ups in rendering code. Onscreen paths with no range checking used until Z is close enough to cause clipping , partial onscreen drawing pathes that need to check boundaries, quad rendering completely rewritten - was very very painfull to get right . I found out the hard way that things are great when they are not rotating in the Z axis haha . Partial buffer draw optimisations - which have helped with the massive dma load , sending up to a 20kb buffer in a single frame needs a lot of optimisation. Min / Max tile lines are analysed and only sent if dirtied , reducing most buffer swaps substantially. Still some issues to sort out , at times you can see the flicker near top of screen when frames are near full height . I need to optimise that a bit. Due to the onscreen buffer system a full Sprite background had to be implemented almost Neo Geo style. This flips the usual MD rendering system on its head as it uses both foreground and background layers for a foreground 3d plane and sprites for the background. This presents a few issues, one is to get a tilt effect on the background by using narrow sprites (16x32) we run out of sprites when trying to cover the screen. Thankfully the MD is not limited to 80 sprites, to fix this a 114 sprite multiplexor is used to draw the background, its completely made up of 16x32 sprites ! Why do things this way ? speed . Its the interleaved foreground/background layers that allow a double buffered ram system writing to write to vram using dma in a completely linear fashion - virtually no tile translation needed. The negative is you have no planes for the background, that's where the sprites come in . Thanks to H40 mode we still have a few sprites we can use for effects in the forground also . Thankfully we can implement a fairly good tilt still for the background using sprites, in future updates this will be able to move horizontally also and a bit of vertical movement. XGM1 music driver in use to simulate music cpu load, XGM2 unfortunately with the massive DMA needed to shift the 3d buffers would slow down at times rendering it unusable, XGM1 plays at full speed - albiet with a bit more of a cpu hit. Together with the sprite multiplexor and the music driver active theres a 10 % hit to cpu so I've had to play around with draw distances / object heights and other optimisations to offset that. Not to mention the larger buffer takes more cpu to fill also. Everything is placeholder so will be changed with proper stage design. We are averaging 20 FPS in the current video, I'll push for more as always !! Progress continues on my other projects , updates soon on those - retirement can't come quick enough . #SGDK #SegaGenesis #SegaMegadrive

Sega Genesis 3D Engine Update 8 Significant improvements all round as you can see and hear from the last update !! Foremost - A huge thanks to Toni Gálvez - Megastyle - BG. who has joined the project to create a bit of 16bit low poly magic. Toni's an Amiga fan but also crazy about game dev in general, he's worked on GBC, GBA, PC, MD, PSP, C64, CPC, MSX... and others. Gaming titles include War Times, Metal Gear, Rocketman, Tintin & Asterix to name a few. He's provided the great new ship model you see on screen - new striped buildings, all the backgrounds / palettes etc. There's a lot of models he's given me which need to be added, also he will be planning a lot of the level design. Very happy to have him help me turn this into something more than a tech demo as I have my hands tied pushing the MD as far as it can go haha - there is no cpu cycle to be spared. Also many thanks to my good friend CYBERDEOUS - Crouzet Laurent for the Music for this showing , I wanted to have the music load occurring so we have a realistic benchmark for performance and he was only too obliging. If you're into MD chiptunes check him out !! Since last update : New player model , substantially more detailed than the Arwing. Last update had a 23 triangle Arwing , this update has a 39 triangle custom model from Toni. We had several to choose from , others will be used for enemies . 3D Buffer size increased 25% to 256x160. This was quite tricky as I'm close to the DMA limit even with an extended vblank . Spent a few days thinking of how to do this as like anything retro every solution has a drawback, finally got a workable solution. It makes a big difference to have a bit more vertical height . Z Rotation added ( the screen tilting left to right ) , small hit to vertex transform on cpu thanks to look up tables doing the heavy lifting, saving 4 multiplies per vertex. Multiple speed ups in rendering code. Onscreen paths with no range checking used until Z is close enough to cause clipping , partial onscreen drawing pathes that need to check boundaries, quad rendering completely rewritten - was very very painfull to get right . I found out the hard way that things are great when they are not rotating in the Z axis haha . Partial buffer draw optimisations - which have helped with the massive dma load , sending up to a 20kb buffer in a single frame needs a lot of optimisation. Min / Max tile lines are analysed and only sent if dirtied , reducing most buffer swaps substantially. Still some issues to sort out , at times you can see the flicker near top of screen when frames are near full height . I need to optimise that a bit. Due to the onscreen buffer system a full Sprite background had to be implemented almost Neo Geo style. This flips the usual MD rendering system on its head as it uses both foreground and background layers for a foreground 3d plane and sprites for the background. This presents a few issues, one is to get a tilt effect on the background by using narrow sprites (16x32) we run out of sprites when trying to cover the screen. Thankfully the MD is not limited to 80 sprites, to fix this a 114 sprite multiplexor is used to draw the background, its completely made up of 16x32 sprites ! Why do things this way ? speed . Its the interleaved foreground/background layers that allow a double buffered ram system writing to write to vram using dma in a completely linear fashion - virtually no tile translation needed. The negative is you have no planes for the background, that's where the sprites come in . Thanks to H40 mode we still have a few sprites we can use for effects in the forground also . Thankfully we can implement a fairly good tilt still for the background using sprites, in future updates this will be able to move horizontally also and a bit of vertical movement. XGM1 music driver in use to simulate music cpu load, XGM2 unfortunately with the massive DMA needed to shift the 3d buffers would slow down at times rendering it unusable, XGM1 plays at full speed - albiet with a bit more of a cpu hit. Together with the sprite multiplexor and the music driver active theres a 10 % hit to cpu so I've had to play around with draw distances / object heights and other optimisations to offset that. Not to mention the larger buffer takes more cpu to fill also. Everything is placeholder so will be changed with proper stage design. We are averaging 20 FPS in the current video, I'll push for more as always !! Progress continues on my other projects , updates soon on those - retirement can't come quick enough . #SGDK #SegaGenesis #SegaMegadrive

Shannon Birt

34,242 Aufrufe • vor 1 Monat

As promised, another #E2V1 video for #Dec 🌍✌️ This footage is more laid back but in some ways provides a better feel of #E2V1. ⬅️full version It is very important to note that this video is a mixture of #WIP footage taken throughout the year during development & testing of: 1️⃣ 🌴 the implementation and testing of our global biome system 2️⃣ 🌊 our water system which not only looks nice, but spans the entire planet and for the most part handles correct directional flow of water mass 3️⃣ 🍁 the early stages of our seasonal system, facilitating for the transition of vegetation and environments into spring, summer, fall and winter 4️⃣ 🧍 early testing on our NPC system with simple navigation and various states of animation to clearly convey their feeling or current activity 5️⃣ 🐟 early testing of our first animal system spawning various sea animals into bodies of water in various locations 6️⃣ 🚢 further testing of our logistics system, with vehicles and ships moving on, over and through the terrain 7️⃣ 🏢 further testing of our megacity system, pushing the limits for larger megacities with an awesome view distance You will find little bugs if you look hard enough so it's important to understand it's a #WIP! We just thought we would share some of the footage because it came together nicely. All in all we have made some really good progress through 2023 not only via #feature releases on the website but also development & progress on #E2V1. We hope you enjoy & we look forward to our next step, revealing the first look at early game play inside #E2V1 in 2024! If you enjoy the footage & progress don't forget to drop a like & comment on YouTube & sub if you haven't already 👌 Hope you all enjoy the rest of 2023 & I look forward to a very exciting 2024 with you all! #Earth2 #Metaverse #OpenWorld #PlayerDriven #digitalearth #bigthingscoming

As promised, another #E2V1 video for #Dec 🌍✌️ This footage is more laid back but in some ways provides a better feel of #E2V1. ⬅️full version It is very important to note that this video is a mixture of #WIP footage taken throughout the year during development & testing of: 1️⃣ 🌴 the implementation and testing of our global biome system 2️⃣ 🌊 our water system which not only looks nice, but spans the entire planet and for the most part handles correct directional flow of water mass 3️⃣ 🍁 the early stages of our seasonal system, facilitating for the transition of vegetation and environments into spring, summer, fall and winter 4️⃣ 🧍 early testing on our NPC system with simple navigation and various states of animation to clearly convey their feeling or current activity 5️⃣ 🐟 early testing of our first animal system spawning various sea animals into bodies of water in various locations 6️⃣ 🚢 further testing of our logistics system, with vehicles and ships moving on, over and through the terrain 7️⃣ 🏢 further testing of our megacity system, pushing the limits for larger megacities with an awesome view distance You will find little bugs if you look hard enough so it's important to understand it's a #WIP! We just thought we would share some of the footage because it came together nicely. All in all we have made some really good progress through 2023 not only via #feature releases on the website but also development & progress on #E2V1. We hope you enjoy & we look forward to our next step, revealing the first look at early game play inside #E2V1 in 2024! If you enjoy the footage & progress don't forget to drop a like & comment on YouTube & sub if you haven't already 👌 Hope you all enjoy the rest of 2023 & I look forward to a very exciting 2024 with you all! #Earth2 #Metaverse #OpenWorld #PlayerDriven #digitalearth #bigthingscoming

Shane Isaac 🌍2️⃣

30,554 Aufrufe • vor 2 Jahren

Check out our latest #Earth2 #creation the #MotorwayMarauder🌍✌️From #ConceptArt to #gameready, gives me #MadMax & #Terminator vibes - love it! Some #IMPORTANT things to remember about #Earth2 #drops leading up to #E2V1👇 1⃣Acquiring #skins is completely optional 2⃣ Notably, the #skins we drop leading up to the #E2V1 release will more likely have a ‘Limited Supply’, something that rewards our early supporters with increased rarity. These Limited Supply drops will become less frequent in the future being replaced with drops of unlimited supply but restricted availability requiring Players to wait for a skin to become available in the skin store or hope to acquire it via game play inside #E2V1 3⃣ Our goal is not to have these early #skin drops sell out during their maiden release, but rather provide an opportunity for our early supporters to secure skins they like at a discounted price with the welcoming guarantee of an all time Limited Supply. 4⃣ Most of the early #skin drops will naturally allow #Players to resell them, but importantly many will also be assigned with a once ever discount rate. #Skins that have Future Price Reduction assigned with “No” means that if the #skin does not sell out on its maiden drop and subsequently gets listed in store again at a future date, #Earth2 will never resell that #skin at any discounted rate. 5⃣ #Earth2 is building a modular clothing system, meaning that most items of clothing, especially if sold separately, will be interchangeable on avatars making them more useful and giving the #Player more ways to mix up their outfits, look the part & express themselves. 6⃣ The version of the skin you see in store is the base version you receive with the skin, however, there will also be opportunities to tailor outfits in game allowing for the adjustment in fabrics, prints, colours and more (be prepared for a little legwork though, unless you want to take your clothing items to another #Player who specialises in tailoring). 7⃣ #Earth2 is proud to have uniquely designed the #skins you listed in our store & it is important to remember that these #skins are the end result of a long and stringent internal character pipeline we have developed. Each skin starts from concept art which is reviewed and iterated on numerous times before being approved. Once approval is given, it is handed to our 3D modelling team for sculpting into high poly, then low poly, while receiving numerous reviews and adhering to our pipeline protocols. When the low poly version is finished, the 3D team then finishes with UV mapping and texture baking and runs their own QA process. Once the entire 3D sculpting process is approved, the models enter the skinning, rigging and weight painting process and are then passed to the animation team for further testing with various animations and another set of QA such as minimising clipping and identifying any other potential flaws in the model. The model then needs to go through the final process with a game developer to ensure it passed the final tests and is game ready for #E2V1. 8⃣ The above steps only represent a light explanation of our character and clothing pipeline, but as you can see we’re not simply selling static concept art images or a high poly 3D model that lacks any kind of optimisations resulting in little chance of it ever being game ready in its advertised state - there is a lot of work that takes place in order to get these skins to the stage our #Players see them in the video footage. Each skin sold helps support different parts of the development of Earth 2 providing us with new opportunities to further expand our team, speed up development and keep stepping closer to our short and long term goals for #E2V1 and #Earth2. 9⃣ We understand that fashion will become a big part of the #Metaverse, but we want to remind people that while some #Players may decide to set rules for certain skins being required for access or a ticket to entry under certain circumstances, from #Earth2’s perspective these skins are for cosmetic purposes only. 🔟 These skin drops also give #Earth2 the chance to show off our ability and versatility in avatar creation and accessories so even if you’re not keen on picking up a skin, remember to have fun and simply enjoy the progress! Also take heart every time you see a #skindrop, if the #E2V1 pre-alpha was not launching this year I wouldn't be dropping skins. We want to have at least some diversity for #avatars inside #E2V1 from the early stages! #Earth2 #Metaverse #Skins #Fashion #Collectibles #3DWorld #WIP #prealpha2024

Shane Isaac 🌍2️⃣

19,007 Aufrufe • vor 2 Jahren

Big news from OVER! 🚀 We're expanding our Visual Positioning System (VPS) globally integrating open datasets from Mapillary & Panoramax. Precise AR re-localization everywhere. Yes, EVERYWHERE! 🗺️ Mapillary & panoramax offer over 2 BILLION geolocalized images under CC-BY-SA license. Mapillary (recently acquired by Meta) covers the globe, while Panoramax specializes in France. These datasets beautifully complement OVER's community-driven OVRMaps. While they're less dense (about 1-2 orders sparser), their scale is massive. Check out Mapillary’s global coverage here: But leveraging such sparse, varied data isn't easy—think limited overlap, camera distortion, and no metric scaling. Yet, we've cracked the code! 💡 Our recent breakthroughs combining our VPS pipeline with cutting-edge Large Geospatial Models (LGMs) allow us to build accurate 3D digital twins and offer reliable VPS services using these sparse datasets. 📍 Accuracy might be lower than our detailed community maps, but it still blows GPS out of the water! This is HUGE for OVER. It means we’re extending our coverage WAY beyond the 110,000+ locations already mapped by our community. Web3 DePIN + Open Source beats Web2 giants like Niantic! And that's not all—we're also unlocking exciting new possibilities soon: 1️⃣ Faster and easier mapping through our Map2Earn program using 360-degree camera integration. 2️⃣ Integrating datasets from new DePIN partners—like our recent partnership with NATIX Network the OVER ecosystem. Stay tuned! The future of AR Spatial Computing and decentralized mapping is here, and it's open, collaborative, and unstoppable!

Big news from OVER! 🚀 We're expanding our Visual Positioning System (VPS) globally integrating open datasets from Mapillary & Panoramax. Precise AR re-localization everywhere. Yes, EVERYWHERE! 🗺️ Mapillary & panoramax offer over 2 BILLION geolocalized images under CC-BY-SA license. Mapillary (recently acquired by Meta) covers the globe, while Panoramax specializes in France. These datasets beautifully complement OVER's community-driven OVRMaps. While they're less dense (about 1-2 orders sparser), their scale is massive. Check out Mapillary’s global coverage here: But leveraging such sparse, varied data isn't easy—think limited overlap, camera distortion, and no metric scaling. Yet, we've cracked the code! 💡 Our recent breakthroughs combining our VPS pipeline with cutting-edge Large Geospatial Models (LGMs) allow us to build accurate 3D digital twins and offer reliable VPS services using these sparse datasets. 📍 Accuracy might be lower than our detailed community maps, but it still blows GPS out of the water! This is HUGE for OVER. It means we’re extending our coverage WAY beyond the 110,000+ locations already mapped by our community. Web3 DePIN + Open Source beats Web2 giants like Niantic! And that's not all—we're also unlocking exciting new possibilities soon: 1️⃣ Faster and easier mapping through our Map2Earn program using 360-degree camera integration. 2️⃣ Integrating datasets from new DePIN partners—like our recent partnership with NATIX Network the OVER ecosystem. Stay tuned! The future of AR Spatial Computing and decentralized mapping is here, and it's open, collaborative, and unstoppable!

Over the Reality 🌐

1,313,342 Aufrufe • vor 1 Jahr

If an AI can control 1,000 robots to perform 1 million skills in 1 billion different simulations, then it may "just work" in our real world, which is simply another point in the vast space of possible realities. This is the fundamental principle behind why simulation works so effectively for robotics. Real-world teleoperation data scales linearly with human time (< 24 hrs/robot/day). Sim data scales exponentially with compute. There are 3 big trends for simulators in the near future: 1. Massive parallelization on large clusters. Physics equations are "just" matrix math at their core. I hear GPUs are good at matrix math 🔥. One can run 100K copies of simulation on a single GPU. To put this number in perspective: 1 hour of wallclock compute time gives a robot 10 years (!!) of training experience. That's how Neo was able to learn martial arts in a blink of an eye in the Matrix Dojo. 2. Generative graphics pipeline. Traditionally, simulators require a huge amount of manual effort from artists: 3D assets, textures, scene layouts, etc. But every component in the workflow can be automated: text-to-image, text-to-3D mesh, and LLMs that write Universal Scene Description (USD) files as a coding exercise. RoboCasa is one example of a prior work. 3. End2end neural net that acts as simulator itself. This is still bluesky research and quite far from replacing a graphics pipeline, but we are seeing some exciting signs-of-life based on video gen models: Sora, Veo2, CogVideoX, Hunyuan (text-to-video); and action-driven world models: GameNGen, Oasis, Genie-2, etc. Genesis does great on (1) for certain tasks, shows good promises on (2), and could become a data generation tool for reaching (3). Its sim2real capabilities for locomotion are good, but there's still a long way to go for contact-rich, dexterous manipulation. It shows a bold vision and is on the right path to providing a virtual cradle for embodied AI. It is open-source and puts a streamlined user journey at the front and center. I had the privilege to know Zhou Xian and play a small part in his project since a year ago. Xian has been crunching code non-stop on Genesis with a very small group of core devs. He often replied to my messages at 3 am. Zhenjia Xu from our GEAR team helped with sim2real experiments in his spare time. Genesis is truly a grassroot effort with an intense focus on quality engineering. Nothing gives me more joy than seeing the simulation ecosystem bloom. Robotics should be a moonshot initiative owned by all of humanity. Congratulations.

If an AI can control 1,000 robots to perform 1 million skills in 1 billion different simulations, then it may "just work" in our real world, which is simply another point in the vast space of possible realities. This is the fundamental principle behind why simulation works so effectively for robotics. Real-world teleoperation data scales linearly with human time (< 24 hrs/robot/day). Sim data scales exponentially with compute. There are 3 big trends for simulators in the near future: 1. Massive parallelization on large clusters. Physics equations are "just" matrix math at their core. I hear GPUs are good at matrix math 🔥. One can run 100K copies of simulation on a single GPU. To put this number in perspective: 1 hour of wallclock compute time gives a robot 10 years (!!) of training experience. That's how Neo was able to learn martial arts in a blink of an eye in the Matrix Dojo. 2. Generative graphics pipeline. Traditionally, simulators require a huge amount of manual effort from artists: 3D assets, textures, scene layouts, etc. But every component in the workflow can be automated: text-to-image, text-to-3D mesh, and LLMs that write Universal Scene Description (USD) files as a coding exercise. RoboCasa is one example of a prior work. 3. End2end neural net that acts as simulator itself. This is still bluesky research and quite far from replacing a graphics pipeline, but we are seeing some exciting signs-of-life based on video gen models: Sora, Veo2, CogVideoX, Hunyuan (text-to-video); and action-driven world models: GameNGen, Oasis, Genie-2, etc. Genesis does great on (1) for certain tasks, shows good promises on (2), and could become a data generation tool for reaching (3). Its sim2real capabilities for locomotion are good, but there's still a long way to go for contact-rich, dexterous manipulation. It shows a bold vision and is on the right path to providing a virtual cradle for embodied AI. It is open-source and puts a streamlined user journey at the front and center. I had the privilege to know Zhou Xian and play a small part in his project since a year ago. Xian has been crunching code non-stop on Genesis with a very small group of core devs. He often replied to my messages at 3 am. Zhenjia Xu from our GEAR team helped with sim2real experiments in his spare time. Genesis is truly a grassroot effort with an intense focus on quality engineering. Nothing gives me more joy than seeing the simulation ecosystem bloom. Robotics should be a moonshot initiative owned by all of humanity. Congratulations.

Jim Fan

157,343 Aufrufe • vor 1 Jahr