Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Introducing Moonlake's 3D Agent. Our agent acts like a technical artist that can build and reconstruct articulated assets and large-scale editable scenes with hundreds of objects from a single image and can improve its generations continuously. Learn more in the thread below.

Moonlake

10,695 subscribers

1,167,044 görüntüleme • 5 ay önce •via X (Twitter)

Oyun Sanat Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

38 Yorum

Moonlake profil fotoğrafı

Moonlake5 ay önce

Since last month when we released an early preview of our agent, we've been collecting datasets of reasoning trajectories on world-building workflows. Today, we're bringing Blender computer use capabilities to it to automate real work and unlock more time for creative work.

Moonlake profil fotoğrafı

Moonlake5 ay önce

It can model assets from scratch, with separate parts and articulation without relying on any pre-defined rules.

Moonlake profil fotoğrafı

Moonlake5 ay önce

It can reconstruct fully-editable indoor and outdoor scenes from a single image.

Moonlake profil fotoğrafı

Moonlake5 ay önce

It can also learning from a single human demonstration and generalize that workflow to other scenes and assets.

Moonlake profil fotoğrafı

Moonlake5 ay önce

Our agent can integrate natively with your existing pipelines; connect it to your digital asset management system and launch hundreds of jobs in a click. Don't spend hours on checking object states and naming or asset cleanup. Save time for what matters. If you'd like to use our agent, reach out to us at [email protected]

Moonlake profil fotoğrafı

Moonlake5 ay önce

3D reasoning and modeling capabilities represents a 100B+/year category of work in simulations, games, and film/VFX because the verification process depends on having spatial, physical, and geometrical priors of the world. Read more here:

Jimmy Newclaw profil fotoğrafı

Jimmy Newclaw5 ay önce

Let’s goo ! 👀 huge update from MoonLake. This was the first game I ever made on MoonLake … let’s see what I can do now with this 🔥update 😏

devaux.sui profil fotoğrafı

devaux.sui5 ay önce

ok NOW we're talking. the claude one looks garbage.

Aman profil fotoğrafı

Aman5 ay önce

this is crazy from single image to full editable world is wild

jia profil fotoğrafı

jia5 ay önce

lfg!!

James profil fotoğrafı

James5 ay önce

looks like openai wants to take your marketshare via support to blender org and integration

Anoop profil fotoğrafı

Anoop5 ay önce

hollywood is solved

Kimi profil fotoğrafı

Kimi5 ay önce

"That's incredible innovation! The potential for artists and designers to focus on creativity, not tedious tasks, is huge. Can't wait to see how Moonlake's 3D Agent evolves and empowers the community!"

DrewOnAI profil fotoğrafı

DrewOnAI5 ay önce

another "single image to masterpiece" claim? i'll believe it when i see a scene that doesn't fall apart in the second frame

Doxy profil fotoğrafı

Doxy5 ay önce

another ai tool claiming to replace artists? i'll believe it when i see the render times give me a link to the github repo first

Papibeatz profil fotoğrafı

Papibeatz5 ay önce

Aw hell yeah!

G. @ The Neuron profil fotoğrafı

G. @ The Neuron5 ay önce

lets gooooooo

Meta-Gnome profil fotoğrafı

Meta-Gnome5 ay önce

DOPE!

pboykexh 🦸(❖,❖) profil fotoğrafı

pboykexh 🦸(❖,❖)5 ay önce

Moonlake’s 3D Agent is a massive win for creators! Turning one image into a complex, editable scene with hundreds of objects is exactly how I’m scaling Kiisha’s Lunar Escape so fast. This is the future of 3D builds! 🔥 #MoonlakeAI You see it below 👇

retto profil fotoğrafı

retto5 ay önce

2026, the year of the agents

Lee Penkman profil fotoğrafı

Lee Penkman5 ay önce

wow

AI News Hungama profil fotoğrafı

AI News Hungama5 ay önce

Interesting.

ChineseTechBro profil fotoğrafı

ChineseTechBro5 ay önce

looking great! i saw codex do exactly the same thing. crazy how powerful LLMs have become!

ZeRo Xu profil fotoğrafı

ZeRo Xu5 ay önce

a huge breakthrough

AI Mastery Guide profil fotoğrafı

AI Mastery Guide5 ay önce

Single image in. Large-scale editable 3D scene with hundreds of articulated assets out. The technical art pipeline just changed significantly.

Dennis, Founder @Tixu 🎟️ | profil fotoğrafı

Dennis, Founder @Tixu 🎟️ |5 ay önce

This is super interesting. We’re working on capturing real human work in kitchens and factories — egocentric video, objects, tasks, workflows. A tool like this could turn scanned real workstations into interactive worlds for training and evaluating Physical AI.

techmo profil fotoğrafı

techmo5 ay önce

Can it do low poly quake 2 style models???

JMoon profil fotoğrafı

JMoon5 ay önce

the technical artist framing is the useful abstraction. agents that expose creative-domain primitives rather than raw code outputs lower the skill floor for serious use. the constraint is whether the output quality is consistent enough to trust in a production pipeline.

Alice The Ai Expert profil fotoğrafı

Alice The Ai Expert3 ay önce

One image. Whole worlds built.

Mondomedia 賢 Grokstar profil fotoğrafı

Mondomedia 賢 Grokstar5 ay önce

How can I access?

DreamxTheory profil fotoğrafı

DreamxTheory5 ay önce

How or where can I get this?

RAZA | AI EXPLORER profil fotoğrafı

RAZA | AI EXPLORER2 ay önce

Turning a single image into 3D editable scenes is incredible.

Danil Pashkevich profil fotoğrafı

Danil Pashkevich5 ay önce

And my agent can take a photo and turn it into a 3D object - and print it.

Professor Pixel profil fotoğrafı

Professor Pixel5 ay önce

Can this be used to do scenic design? It would need to understand measurements precisely and be able to read a ground plan.

Time is Light profil fotoğrafı

Time is Light5 ay önce

.

Bessi profil fotoğrafı

Bessi5 ay önce

@Jayaram_Reddy10 Another automated artist layoff generator.

AqibAi profil fotoğrafı

AqibAi5 ay önce

Single image → fully editable 3D scene is a wild leap. Not just generating assets, but reconstructing structure, articulation, and relationships between objects—then iterating on it like a technical artist. This feels like the bridge from “AI visuals” to actual production-ready worlds. Curious how it handles complex scenes and physics 👀

Coocoo profil fotoğrafı

Coocoo5 ay önce

@teortaxesTex IIRC you tried to recreate Major Tanya's room last year with Nano Banana 1 or an earlier imagegen model, I hope this is a big step up from back then.

Benzer Videolar

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!

Siyuan Huang

12,819 görüntüleme • 1 yıl önce

Introducing Agent 2.0 Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets. Agent is being built to become the most capable autonomous agent for real-world work.

Introducing Agent 2.0 Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets. Agent is being built to become the most capable autonomous agent for real-world work.

Runway

954,788 görüntüleme • 3 ay önce

Introducing Gizmo, a simulation-authoring agent that turns text and reference images into structured, editable 3D scenes for robotics workflows. We're opening the public beta today.

Introducing Gizmo, a simulation-authoring agent that turns text and reference images into structured, editable 3D scenes for robotics workflows. We're opening the public beta today.

Shrey Kothari

50,829 görüntüleme • 2 ay önce

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Google DeepMind

1,443,142 görüntüleme • 1 yıl önce

Introducing Agent Skills. Build an ad campaign, create a commercial, localize your ads and more with a simple command. Type /, choose a Skill and Agent gets to work. Scale your marketing. On command. Get started at the link below.

Introducing Agent Skills. Build an ad campaign, create a commercial, localize your ads and more with a simple command. Type /, choose a Skill and Agent gets to work. Scale your marketing. On command. Get started at the link below.

Runway

24,431 görüntüleme • 3 ay önce

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

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

el.cine

103,430 görüntüleme • 4 ay önce

introducing HermitClaw - a 24/7 Agent that lives (and can only access) a single folder on your desktop HermitClaw follows its own research curiosities, surfs the web, writes code - and will play with any file you drop in its folder all code and details below!

introducing HermitClaw - a 24/7 Agent that lives (and can only access) a single folder on your desktop HermitClaw follows its own research curiosities, surfs the web, writes code - and will play with any file you drop in its folder all code and details below!

Brendan Hogan

187,776 görüntüleme • 8 ay önce

Agentic Real2Sim is an interesting take on world modeling. Instead of learning physics directly from videos, it lets a Vision-Language Agent reconstruct a physics simulator from a single real-world video. The result is an editable, executable world model that can be queried, simulated, and improved.

Agentic Real2Sim is an interesting take on world modeling. Instead of learning physics directly from videos, it lets a Vision-Language Agent reconstruct a physics simulator from a single real-world video. The result is an editable, executable world model that can be queried, simulated, and improved.

Robots Digest 🤖

12,075 görüntüleme • 2 ay önce

New course: Build AI agents that generate images and videos -- an under-explored frontier. A key to performance is having the agent evaluate its own output, and iterate to improve quality. This short course is built together with Google Cloud Tech and taught by Katie Nguyen and Wafae Bakkali. You'll learn three evaluation techniques and combine them in an agent: image-text similarity scoring to check the output matches the prompt, an LLM judge that scores against custom criteria like brand consistency, and structured rubrics that break a prompt into verifiable yes/no questions like "is the subject in the frame?" and "does the camera motion match?" Skills you'll gain: - Learn image and video prompt engineering - Build an image agent that turns brand guidelines into UI mockups - Build a video agent that plans multi-scene explainers and animates reference frames with synchronized audio Join and build agents that create images and video!

Andrew Ng

142,383 görüntüleme • 4 ay önce

✨ Introducing 3 new ways to build with real-world imagery and AI → From the fine details of a city street to a bird's eye view of the planet, at Cloud Next we revealed new ways that businesses can use our Street View, aerial and satellite imagery, and tap into our comprehensive view of the physical world including: 🏙️ Use Maps Imagery Grounding in Gemini Enterprise Agent Platform to generate location-specific assets at scale, anchored in real-world Street View imagery 🌍 Unlock a new perspective with Aerial and Satellite Insights, part of Earth AI, in BigQuery and Agent Platform to quickly extract detailed info about our changing planet 🛰️ Build custom apps with Aerial and Satellite models in Model Garden from Earth AI that easily identify specific objects or scenes Read the blog at the link above and sign up for early access.

✨ Introducing 3 new ways to build with real-world imagery and AI → From the fine details of a city street to a bird's eye view of the planet, at Cloud Next we revealed new ways that businesses can use our Street View, aerial and satellite imagery, and tap into our comprehensive view of the physical world including: 🏙️ Use Maps Imagery Grounding in Gemini Enterprise Agent Platform to generate location-specific assets at scale, anchored in real-world Street View imagery 🌍 Unlock a new perspective with Aerial and Satellite Insights, part of Earth AI, in BigQuery and Agent Platform to quickly extract detailed info about our changing planet 🛰️ Build custom apps with Aerial and Satellite models in Model Garden from Earth AI that easily identify specific objects or scenes Read the blog at the link above and sign up for early access.

Google Maps Platform

12,355 görüntüleme • 5 ay önce

This first-person shooter was built from a single prompt, using 404-generated 3D assets. On the latest Novelty Search, 404 explains how SN17 is moving from Titan, its open image-to-3D model built with miners, toward 3D assets generated as code that AI agents can edit and use directly in games. That work is part of a broader direction for 404: building world models where AI agents can learn and act. Hosted by const Full episode in the first comment

This first-person shooter was built from a single prompt, using 404-generated 3D assets. On the latest Novelty Search, 404 explains how SN17 is moving from Titan, its open image-to-3D model built with miners, toward 3D assets generated as code that AI agents can edit and use directly in games. That work is part of a broader direction for 404: building world models where AI agents can learn and act. Hosted by const Full episode in the first comment

Openτensor Foundaτion

19,046 görüntüleme • 1 ay önce

Our model can now learn from its own experience with RL! Our new π*0.6 model can more than double throughput over a base model trained without RL, and can perform real-world tasks: making espresso drinks, folding diverse laundry, and assembling boxes. More in the thread below.

Our model can now learn from its own experience with RL! Our new π*0.6 model can more than double throughput over a base model trained without RL, and can perform real-world tasks: making espresso drinks, folding diverse laundry, and assembling boxes. More in the thread below.

Physical Intelligence

712,033 görüntüleme • 11 ay önce

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

LangChain

26,513 görüntüleme • 8 ay önce

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Palantir

83,765 görüntüleme • 3 ay önce

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,466 görüntüleme • 8 ay önce

The next front door to commerce may be an AI agent. Today, we're introducing Mastercard Agent Connect and expanding Agent Suite for Merchants to help businesses build, connect, and scale AI-powered shopping experiences. Learn more about how we're powering the future of commerce with partners across the ecosystem:

The next front door to commerce may be an AI agent. Today, we're introducing Mastercard Agent Connect and expanding Agent Suite for Merchants to help businesses build, connect, and scale AI-powered shopping experiences. Learn more about how we're powering the future of commerce with partners across the ecosystem:

Mastercard

25,501 görüntüleme • 1 ay önce

Today’s Agent Spotlight: A browser-native agent that acts on the web using ASI:One. ⚡ Built using Notte, this Nike agent doesn’t merely scrape - it clicks, scrolls, and navigates like a real user. Not limited to Nike.com. With Agentverse and Notte, you can build agents for any site. Try now: Link to agent:

Today’s Agent Spotlight: A browser-native agent that acts on the web using ASI:One. ⚡ Built using Notte, this Nike agent doesn’t merely scrape - it clicks, scrolls, and navigates like a real user. Not limited to Nike.com. With Agentverse and Notte, you can build agents for any site. Try now: Link to agent:

Fetch.ai

49,482 görüntüleme • 1 yıl önce

What if we can simulate an *interactive 3D world*, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

What if we can simulate an interactive 3D world, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

Wenlong Huang

278,964 görüntüleme • 9 ay önce