正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Learn to model visors with crisp reflections. 👀 In episode 3, shift gears from subdivision surface modelling and model the visor using weighted bevels and shrinkwraps. Meaning we can worry less about topology and still achieve clean results. #Blender3D #BlenderModeling

Joshua Graham

3,095 subscribers

31,159 次观看 • 1 年前 •via X (Twitter)

#Blender3D #BlenderModeling

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

🚨Modelling Challenge🚨 How would you model a sphere with a bunch of circular cutouts? Main thing is that it needs to subdivide nicely and have clean shading. Share your results and method in the comments. 👇 #Blender3D #BlenderModeling #HardSurfaceModeling #B3D

🚨Modelling Challenge🚨 How would you model a sphere with a bunch of circular cutouts? Main thing is that it needs to subdivide nicely and have clean shading. Share your results and method in the comments. 👇 #Blender3D #BlenderModeling #HardSurfaceModeling #B3D

Joshua Graham

51,397 次观看 • 1 年前

🚨Modelling Challenge🚨 How would you approach this trapezium with 5 circular cutouts and 4 connecting lines? Only rule is that it has to subdivide nicely with crisp edges. Share your results and method in the comments. 👇 #Blender3D #BlenderModeling

🚨Modelling Challenge🚨 How would you approach this trapezium with 5 circular cutouts and 4 connecting lines? Only rule is that it has to subdivide nicely with crisp edges. Share your results and method in the comments. 👇 #Blender3D #BlenderModeling

Joshua Graham

47,281 次观看 • 1 年前

LINE BOIL IN VRCHAT?? Finally got to put ironmouse🇵🇷😈💖 's Chibi Decora model I made into VRChat, lineboil and all :3 I still have some clean-up to do, make the outlines a little more weighted, but the base model is done and I'm so happy with it :D #ironmouseart

LINE BOIL IN VRCHAT?? Finally got to put ironmouse🇵🇷😈💖 's Chibi Decora model I made into VRChat, lineboil and all :3 I still have some clean-up to do, make the outlines a little more weighted, but the base model is done and I'm so happy with it :D #ironmouseart

Blue | Dollmaker | Find me on Bluer Skies

18,867 次观看 • 7 个月前

With Gen-4.5 you can achieve an unprecedented level of cinematic realism while still achieving novel creative concepts. The model is exceptionally good at generating objects that move with realistic weight, momentum and force. Even when suspended in zero gravity. Gen-4.5 early access is now gradually rolling out and will be available soon to all plans. Learn more about the model and what's to come at the link below.

With Gen-4.5 you can achieve an unprecedented level of cinematic realism while still achieving novel creative concepts. The model is exceptionally good at generating objects that move with realistic weight, momentum and force. Even when suspended in zero gravity. Gen-4.5 early access is now gradually rolling out and will be available soon to all plans. Learn more about the model and what's to come at the link below.

Runway

37,198 次观看 • 9 个月前

Arena AutoEval uses tens of millions of historical Arena battles from humans, to train a reward model that can estimate human preferences at scale, and deliver evaluation results at frontier speed. Unlike LLM-as-judge methods, AutoEval remains a live benchmark: it is derived from existing real-world battles, with the reward model scoring from human prompts and model responses. Arena ML Engineers, Haoran Guo and Wayne Zhang, discuss AutoEval below. Watch the full video to learn more about AutoEval’s methodology and model lab use cases in the post below.

Arena AutoEval uses tens of millions of historical Arena battles from humans, to train a reward model that can estimate human preferences at scale, and deliver evaluation results at frontier speed. Unlike LLM-as-judge methods, AutoEval remains a live benchmark: it is derived from existing real-world battles, with the reward model scoring from human prompts and model responses. Arena ML Engineers, Haoran Guo and Wayne Zhang, discuss AutoEval below. Watch the full video to learn more about AutoEval’s methodology and model lab use cases in the post below.

Arena.ai

34,516 次观看 • 1 个月前

We spoke to JL Mussi about his career as a 3D artist and what inspired him to create courses for the 3D community. Learn what you can achieve with the Blender Hard Surface Blueprint course:

We spoke to JL Mussi about his career as a 3D artist and what inspired him to create courses for the 3D community. Learn what you can achieve with the Blender Hard Surface Blueprint course:

80 LEVEL

20,887 次观看 • 2 个月前

Dumelang. I recently traveled to Rwanda and to India and I want to share my reflections with you about what they are doing right and what we can learn from these two nations to fix South Africa. I expound in the video below;

Dumelang. I recently traveled to Rwanda and to India and I want to share my reflections with you about what they are doing right and what we can learn from these two nations to fix South Africa. I expound in the video below;

Mmusi Maimane MP

16,079 次观看 • 7 个月前

Super excited about HydraFusion in GitHub Copilot, and what it shows about the shift from model selection to model orchestration. By bringing together multiple models to plan, build, critique, and complete coding tasks, it can deliver outcomes at up to 67% lower cost. It’s a great example of the value of a heterogeneous model ecosystem, and how we’re continuing to advance the cost-to-outcome frontier.

Super excited about HydraFusion in GitHub Copilot, and what it shows about the shift from model selection to model orchestration. By bringing together multiple models to plan, build, critique, and complete coding tasks, it can deliver outcomes at up to 67% lower cost. It’s a great example of the value of a heterogeneous model ecosystem, and how we’re continuing to advance the cost-to-outcome frontier.

Satya Nadella

321,917 次观看 • 13 天前

LETS GOO! Generate full songs (4 min) with vocals in less than 10 seconds - open weights model! 🔥 It's crazy how much you can achieve from open models as of today! - going right for Suno and likes! VAE + Base model combined is < 2.5GB Open weights on the hub and a space to play around with it! 🤯

LETS GOO! Generate full songs (4 min) with vocals in less than 10 seconds - open weights model! 🔥 It's crazy how much you can achieve from open models as of today! - going right for Suno and likes! VAE + Base model combined is < 2.5GB Open weights on the hub and a space to play around with it! 🤯

Vaibhav (VB) Srivastav

64,204 次观看 • 1 年前

A short snippet from the Unleashing DePIN #050 episode with Dom Carosa (Co-Founder Hivello.com) representing #hivello and talking about what it is we want to achieve 🌎👀

A short snippet from the Unleashing DePIN #050 episode with Dom Carosa (Co-Founder Hivello.com) representing #hivello and talking about what it is we want to achieve 🌎👀

Hivello Official

11,966 次观看 • 1 年前

Are we going to say bye bye to Blender in the future? We’re still REALLY early in AI 3D modeling, yet AI can already generate surprisingly clean 3D topology from a single image. It’s far from perfect, but the direction is pretty insane. And this is probably just the beginning, isn't it? 👀

Are we going to say bye bye to Blender in the future? We’re still REALLY early in AI 3D modeling, yet AI can already generate surprisingly clean 3D topology from a single image. It’s far from perfect, but the direction is pretty insane. And this is probably just the beginning, isn't it? 👀

The Bugged Dev

52,573 次观看 • 1 个月前

Introducing Veo 2, our new, state-of-the-art video model (with better understanding of real-world physics & movement, up to 4K resolution). You can join the waitlist on VideoFX. Our new and improved Imagen 3 model also achieves SOTA results, and is coming today to 100+ countries in ImageFX.

Introducing Veo 2, our new, state-of-the-art video model (with better understanding of real-world physics & movement, up to 4K resolution). You can join the waitlist on VideoFX. Our new and improved Imagen 3 model also achieves SOTA results, and is coming today to 100+ countries in ImageFX.

Sundar Pichai

4,573,933 次观看 • 1 年前

Generative 3D has been stuck in a representational compromise. When you serialize spatial data to fit standard architectures, you force a unidirectional causal bias. It fundamentally breaks the symmetry of 3D geometry and limits how the model understands global context. With Tripo P1.0, we stepped back to fix the representation. Instead of flattening 3D into sequences, P1.0 operates entirely within a native spatial probability space. It reasons about the entire structure at once. That’s why the topology actually makes sense. We aren't running a post-process remesher to clean up artifacts. When you directly model the structured surface manifold, clean edge flows and structural coherence naturally emerge from the noise. This is what happens when the architecture finally respects the medium. And we are doing it in 2 seconds.

Generative 3D has been stuck in a representational compromise. When you serialize spatial data to fit standard architectures, you force a unidirectional causal bias. It fundamentally breaks the symmetry of 3D geometry and limits how the model understands global context. With Tripo P1.0, we stepped back to fix the representation. Instead of flattening 3D into sequences, P1.0 operates entirely within a native spatial probability space. It reasons about the entire structure at once. That’s why the topology actually makes sense. We aren't running a post-process remesher to clean up artifacts. When you directly model the structured surface manifold, clean edge flows and structural coherence naturally emerge from the noise. This is what happens when the architecture finally respects the medium. And we are doing it in 2 seconds.

Yanpei Cao

65,685 次观看 • 6 个月前

Introducing Gemini 3 ✨ It’s the best model in the world for multimodal understanding, and our most powerful agentic + vibe coding model yet. Gemini 3 can bring any idea to life, quickly grasping context and intent so you can get what you need with less prompting. Find Gemini 3 Pro rolling out today in the Google Gemini and AI Mode in Search. For developers, build with it now in Google AI Studio and Vertex AI. Excited for you to try it!

Introducing Gemini 3 ✨ It’s the best model in the world for multimodal understanding, and our most powerful agentic + vibe coding model yet. Gemini 3 can bring any idea to life, quickly grasping context and intent so you can get what you need with less prompting. Find Gemini 3 Pro rolling out today in the Google Gemini and AI Mode in Search. For developers, build with it now in Google AI Studio and Vertex AI. Excited for you to try it!

Sundar Pichai

2,954,091 次观看 • 10 个月前

With all of the procedural sims stuff which is awesome - we forget about good ol' Modelling tips and tricks! Here is one of my favorite procedural modelling tricks to add wrinkles/elasticity for procedural organic flow to really anything.. simply using 2 simple tools in conjunciton with each other: Spline Deformer and Smooth Deformer (geometry with good topology yields nice loops to extract with the edge to spline command🤘) Note: Set Smooth deformer to relax and initialize BEFORE deformations take place Maxon

With all of the procedural sims stuff which is awesome - we forget about good ol' Modelling tips and tricks! Here is one of my favorite procedural modelling tricks to add wrinkles/elasticity for procedural organic flow to really anything.. simply using 2 simple tools in conjunciton with each other: Spline Deformer and Smooth Deformer (geometry with good topology yields nice loops to extract with the edge to spline command🤘) Note: Set Smooth deformer to relax and initialize BEFORE deformations take place Maxon

Spenser Dickerson

29,831 次观看 • 2 年前

#121 - Aamito In this episode, we have a deep and insightful conversation with Ugandan actress and fashion model, Aamito Stacie Lagum, about her perspective on success, life, and seeing the world in a non-monochrome way. Aamito shares her personal experiences and beliefs on embracing the complexity and diversity of the world, and the importance of promoting inclusivity and understanding among people from different backgrounds. Her inspiring insights and reflections provide a valuable reminder to celebrate and value the richness of human diversity in all its forms. Subscribe to enjoy.

#121 - Aamito In this episode, we have a deep and insightful conversation with Ugandan actress and fashion model, Aamito Stacie Lagum, about her perspective on success, life, and seeing the world in a non-monochrome way. Aamito shares her personal experiences and beliefs on embracing the complexity and diversity of the world, and the importance of promoting inclusivity and understanding among people from different backgrounds. Her inspiring insights and reflections provide a valuable reminder to celebrate and value the richness of human diversity in all its forms. Subscribe to enjoy.

BigConvosPod

15,416 次观看 • 3 年前

Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive. Instead, Joseph Amigo and Rooholla Khorrambakht propose to break the problem down: into a large-scale world model that can generate forward trajectories, and a lightweight, low-dimensional latent-space model which can approximate local dynamics of a problem, without needing to back-propagate through a heavy global model. What this means: you can do reinforcement learning in this coupled local-global world model, and learn contact rich skills for a robot. To learn more, watch Episode #101 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan!

Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive. Instead, Joseph Amigo and Rooholla Khorrambakht propose to break the problem down: into a large-scale world model that can generate forward trajectories, and a lightweight, low-dimensional latent-space model which can approximate local dynamics of a problem, without needing to back-propagate through a heavy global model. What this means: you can do reinforcement learning in this coupled local-global world model, and learn contact rich skills for a robot. To learn more, watch Episode #101 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan!

RoboPapers

16,641 次观看 • 14 天前

I joined Anthropic last week! It’s obvious to me that we’re bottlenecked not by model capabilities, but by creativity and understanding. I’ll be building demos and prototypes that highlight new capabilities and share what we learn about building using these models at Anthropic. Excited to build with the best team and the best models.

I joined Anthropic last week! It’s obvious to me that we’re bottlenecked not by model capabilities, but by creativity and understanding. I’ll be building demos and prototypes that highlight new capabilities and share what we learn about building using these models at Anthropic. Excited to build with the best team and the best models.

Thariq

165,495 次观看 • 1 年前