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。

Vibecoding ➡️ Vibesculpting (in 3D) I generated a 3D model of a Spitfire-looking plane in Blender, using Claude 3.7 + Blender MCP (link below 👇), piece by piece... using natural language only. Seeing this alongside Google's new image edition demo, I think we're ahead of a true seismic shift... show more

Emm | scenario.com

55,358 subscribers

95,572 次观看 • 1 年前 •via X (Twitter)

教育科学技术艺术

Anya Rossi• Live Now

Private livecam show

12 条评论

Emm 🔜 GDC 2025 的头像

Emm 🔜 GDC 20251 年前

Start to finish..

Emm 🔜 GDC 2025 的头像

Emm 🔜 GDC 20251 年前

I used by @sidahuj - try it out below.

Digital Currency 的头像

Digital Currency2 年前

From 3D modeling to VR/AR development, our MSc in Metaverse program equips you with the technical skills to excel in the rapidly evolving digital world. Don't miss out—enroll today! #UNIC #MScMetaverse

George Crudo 的头像

George Crudo1 年前

why is "Claude" manually clicking drop down menus and manipulating object with the gizmo when the rest of the time its sending scripting commands to Blender? 🤔

Emm 🔜 GDC 2025 的头像

Emm 🔜 GDC 20251 年前

Glad you're paying attention, George! 😂 Bc Claude doesn't know - yet - how to properly position four propeller blades together in Blender. Same thing with the cockpit, the cowling and the vertical tail - clicking was faster than prompting. I also wanted it to be perfect 48 hours after the MCP was released, but I don't worry too much - in no time it will take over Blender just like Cursor is taking over VSCode.

Rishi Ajith 的头像

Rishi Ajith1 年前

It looks like 💩 tbh. A person could have made it faster and better than whatever this is.

Edgy raven 的头像

Edgy raven1 年前

honestly, with so much texting around, you might as well learn the techniques. I use Blender, it's not exactly rocket science.

Emm 🔜 GDC 2025 的头像

Emm 🔜 GDC 20251 年前

The text is from the model (Claude) not me 🫣

XCecil 的头像

XCecil1 年前

I’ve been avoiding Claud because it feels like there’s too much advertising which means it must not be free.

Transfigured Human D (parody) 的头像

Transfigured Human D (parody)1 年前

Waste of time, it looks like ass and the model looks like ass

Myonisto 🟧 ᛤ 的头像

Myonisto 🟧 ᛤ1 年前

This looks awesome, do you know how i can use cursor instead of claude

Emm 🔜 GDC 2025 的头像

Emm 🔜 GDC 20251 年前

Check out @VisionaryxAI is doing it. It might work better tbh.

相关视频

"Blender MCP" vs. "Generative 3D" – The Showdown ⚔️ Side-by-side comparison of two generated buildings: ⬅️ The 1st one (left) was created using Blender MCP (powered by Claude 3.7). ➡️ The 2nd one (right) was generated with a generative 3D model (direct 2D-to-3D). Check out the differences below 👇

"Blender MCP" vs. "Generative 3D" – The Showdown ⚔️ Side-by-side comparison of two generated buildings: ⬅️ The 1st one (left) was created using Blender MCP (powered by Claude 3.7). ➡️ The 2nd one (right) was generated with a generative 3D model (direct 2D-to-3D). Check out the differences below 👇

Emm | scenario.com

265,859 次观看 • 1 年前

This might actually change everything 🫨 (no, for real). The 3D lighthouse you see was created in Blender using Claude 3.7, guided by my text prompts, and the reference image on the right - more below 👇 Manual adjustments were minimal - just basic repositioning/resizing of some elements (stretching lengths or widening diameters). Everything else - the primitives, shapes, colors, materials, lighting etc - was generated by the LLM itself. And this is only on day 1! Claude 3.7 wasn't even specifically designed for this. Imagine what a specialized LLM could achieve - one that better understands prompts & visual references or that could follow an artist’s manual guidance (“vibesculpting”) This is on Blender so far, but it feels clear that a similar process will apply to ALL creative software (3D, 2D, video…) and eventually… any software.

This might actually change everything 🫨 (no, for real). The 3D lighthouse you see was created in Blender using Claude 3.7, guided by my text prompts, and the reference image on the right - more below 👇 Manual adjustments were minimal - just basic repositioning/resizing of some elements (stretching lengths or widening diameters). Everything else - the primitives, shapes, colors, materials, lighting etc - was generated by the LLM itself. And this is only on day 1! Claude 3.7 wasn't even specifically designed for this. Imagine what a specialized LLM could achieve - one that better understands prompts & visual references or that could follow an artist’s manual guidance (“vibesculpting”) This is on Blender so far, but it feels clear that a similar process will apply to ALL creative software (3D, 2D, video…) and eventually… any software.

Emm | scenario.com

192,765 次观看 • 1 年前

Here's a look behind the scenes of how I used a 3d model, generated from an image, as a "driver" for ai animation. In the near future we'll see more 3d tools that support these types of workflows, with much more emphasis on enhancing user input instead of just letting the ai do everything. I used the 3d model to generate keyframes that I then animated in Luma Dream. By using a 3d model with a diffusion "layer" done with Krea, I got quite high quality frames with a relatively high consistency as well since the AI didn't have to "hallucinate" that much. I upscaled and detailed the frames using Magnific. Using semi-detailed 3d models as drivers for gen ai is very powerful, and it allows us to use models that are sculpted in a more free-flowing type of workflow that doesn't rely so much on high surface detailing or very time-consuming finish, but instead relies more on gestural 3d sculpting. #art #ai

Here's a look behind the scenes of how I used a 3d model, generated from an image, as a "driver" for ai animation. In the near future we'll see more 3d tools that support these types of workflows, with much more emphasis on enhancing user input instead of just letting the ai do everything. I used the 3d model to generate keyframes that I then animated in Luma Dream. By using a 3d model with a diffusion "layer" done with Krea, I got quite high quality frames with a relatively high consistency as well since the AI didn't have to "hallucinate" that much. I upscaled and detailed the frames using Magnific. Using semi-detailed 3d models as drivers for gen ai is very powerful, and it allows us to use models that are sculpted in a more free-flowing type of workflow that doesn't rely so much on high surface detailing or very time-consuming finish, but instead relies more on gestural 3d sculpting. #art #ai

Martin Nebelong

48,259 次观看 • 2 年前

Found my lost childhood game — and rebuilt it in 3D with Fable 5 + Godot. AirXonix — one of the first games I ever played. My sister and I wore it out on a single PC. Nostalgia hit hard. So I gave Claude Fable 5 the full toolbox: Godot MCP + Blender MCP + APIs for textures, 3D models, SFX, even the music. The whole pipeline in one chat. Honestly? More fun than I've had in months. And the game came out genuinely good. Full build:

Found my lost childhood game — and rebuilt it in 3D with Fable 5 + Godot. AirXonix — one of the first games I ever played. My sister and I wore it out on a single PC. Nostalgia hit hard. So I gave Claude Fable 5 the full toolbox: Godot MCP + Blender MCP + APIs for textures, 3D models, SFX, even the music. The whole pipeline in one chat. Honestly? More fun than I've had in months. And the game came out genuinely good. Full build:

Stefan 3D AI

14,443 次观看 • 14 天前

Alright—it's hard to ignore the new tool in the designer's toolkit. I added a new page on my website with my perspective on using AI-generated images in branding, along with some examples of client and personal work where I have done that. link below 👇

Alright—it's hard to ignore the new tool in the designer's toolkit. I added a new page on my website with my perspective on using AI-generated images in branding, along with some examples of client and personal work where I have done that. link below 👇

charlota

60,995 次观看 • 2 年前

"why didn't you tweet yesterday bro?" idk bro claude can now control adobe, blender, autodesk fusion, ableton, affinity, splice, sketchup and resolume. 9 creative tools at once and natural language interface across all of them. > blender: debug an entire scene, batch apply changes across every object, build custom scripts, and add new tools directly into blender's interface > autodesk fusion: create and modify 3d models through conversation > adobe creative cloud: 50+ tools across photoshop, premiere, firefly, and express through one connector > ableton: you don’t need to learn via forums anymore… just ask via natural language to access all knowledge from docs > canva’s affinity: batch image changes, layer renaming, file export, and custom features generated inside the app > splice: search their royalty free sample catalog from inside claude > sketchup and resolume: 3d modeling via conversation and live visual control yes, Claude for CAD exists now. and so does claude for ableton… and so does claude for the entire adobe stack. and the bigger move barely anyone’s noticed: anthropic also joined the blender development fund as a patron. meaning likely more open infra for us the connector itself is built on MCP, which means it works for other AI models too. "that's why I haven't tweeted bro" I had some things to comprehend

"why didn't you tweet yesterday bro?" idk bro claude can now control adobe, blender, autodesk fusion, ableton, affinity, splice, sketchup and resolume. 9 creative tools at once and natural language interface across all of them. > blender: debug an entire scene, batch apply changes across every object, build custom scripts, and add new tools directly into blender's interface > autodesk fusion: create and modify 3d models through conversation > adobe creative cloud: 50+ tools across photoshop, premiere, firefly, and express through one connector > ableton: you don’t need to learn via forums anymore… just ask via natural language to access all knowledge from docs > canva’s affinity: batch image changes, layer renaming, file export, and custom features generated inside the app > splice: search their royalty free sample catalog from inside claude > sketchup and resolume: 3d modeling via conversation and live visual control yes, Claude for CAD exists now. and so does claude for ableton… and so does claude for the entire adobe stack. and the bigger move barely anyone’s noticed: anthropic also joined the blender development fund as a patron. meaning likely more open infra for us the connector itself is built on MCP, which means it works for other AI models too. "that's why I haven't tweeted bro" I had some things to comprehend

klöss

62,257 次观看 • 3 个月前

Hard surface model test: 3D model of an unfinished overland build. Got really nice images again from Grok. Also realised an ‘unfinished’ vehicle might not be the best idea lol. Anyways, I was well surprised with the results. I don’t trust rotating a generated wheel yet 😁, so I made the wheels in Blender. Very similar workflow as the mech character: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing + upscaling. Blender final preparation. Unreal Engine / UEFN shaders. Next time i'd work a bit longer on the normals.

Hard surface model test: 3D model of an unfinished overland build. Got really nice images again from Grok. Also realised an ‘unfinished’ vehicle might not be the best idea lol. Anyways, I was well surprised with the results. I don’t trust rotating a generated wheel yet 😁, so I made the wheels in Blender. Very similar workflow as the mech character: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing + upscaling. Blender final preparation. Unreal Engine / UEFN shaders. Next time i'd work a bit longer on the normals.

Jerome | InsaneUnreal

167,148 次观看 • 6 个月前

Yes, I did feed an AI with my own artwork to generate 3 AI videos, and posted on FB. However, accusing me of using AI to make fan art is a serious accusation. I have the entire creative process of every single piece I made in the past 2 years recorded, like this one.

Yes, I did feed an AI with my own artwork to generate 3 AI videos, and posted on FB. However, accusing me of using AI to make fan art is a serious accusation. I have the entire creative process of every single piece I made in the past 2 years recorded, like this one.

Makotron

56,011 次观看 • 1 年前

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 次观看 • 3 年前

Go from a single image to an entire film, ad or piece of content using our new Story Panels Featured Workflow. This Workflow allows you to build a catalogue of shots with consistent characters, locations and style all in a few simple steps. Comment "Mammoth" for the in-depth tutorial and link to featured Workflow.

Go from a single image to an entire film, ad or piece of content using our new Story Panels Featured Workflow. This Workflow allows you to build a catalogue of shots with consistent characters, locations and style all in a few simple steps. Comment "Mammoth" for the in-depth tutorial and link to featured Workflow.

Runway

25,529 次观看 • 5 个月前

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Martin Nebelong

280,033 次观看 • 1 年前

New clean 3D AI workflow Control Rig physics in UEFN! Been exploring some more hybrid AI workflows lately, and for 3D assets splitting the model into parts is kinda essential. This video shows my first test using AssetHub, one of the cleanest ways i've used to keep the whole generation process organized. It auto-detected the pose in my main image and broke it down into parts, then generated images for each. From there I can just iterate on each piece separately and generate the 3D models in one workflow. AssetHub is still in closed beta atm, so let me know if you want to try it out. Main reference image came from Grok Imagine. All the part images and high poly meshes were done in AssetHub, selected Tripo 3.1 as the main model. After that I ran it through Hunyuan 3D for retopo + unwrap. Final assembly in Blender. Baked normals from high to low poly. End result: under 60K tris, 3 materials, 2K textures. Also Control Rig physics in Unreal Engine are insane. It finally validates in UEFN too, so of course I had to test it out.

New clean 3D AI workflow Control Rig physics in UEFN! Been exploring some more hybrid AI workflows lately, and for 3D assets splitting the model into parts is kinda essential. This video shows my first test using AssetHub, one of the cleanest ways i've used to keep the whole generation process organized. It auto-detected the pose in my main image and broke it down into parts, then generated images for each. From there I can just iterate on each piece separately and generate the 3D models in one workflow. AssetHub is still in closed beta atm, so let me know if you want to try it out. Main reference image came from Grok Imagine. All the part images and high poly meshes were done in AssetHub, selected Tripo 3.1 as the main model. After that I ran it through Hunyuan 3D for retopo + unwrap. Final assembly in Blender. Baked normals from high to low poly. End result: under 60K tris, 3 materials, 2K textures. Also Control Rig physics in Unreal Engine are insane. It finally validates in UEFN too, so of course I had to test it out.

Jerome | InsaneUnreal

82,367 次观看 • 3 个月前

I'm not a 3d modeler. I barely know how to open blender let alone do anything functional in it. But with the siddharth ahuja blender MCP and Claude I was able to vibe code an entire environment for my upcoming grow a garden game in Portals Claude used the MCP to assemble and arrange every single asset in this space (i literally don't even know how to import an asset into blender lol) within the spawn of a few hours and with access to a folder of low poly assets. When I had it start doing its own modeling, it even matched the style of the environment to keep things consistent If you are building UGC games and you don't know anything about modeling or design like me, you gotta try it out...

I'm not a 3d modeler. I barely know how to open blender let alone do anything functional in it. But with the siddharth ahuja blender MCP and Claude I was able to vibe code an entire environment for my upcoming grow a garden game in Portals Claude used the MCP to assemble and arrange every single asset in this space (i literally don't even know how to import an asset into blender lol) within the spawn of a few hours and with access to a folder of low poly assets. When I had it start doing its own modeling, it even matched the style of the environment to keep things consistent If you are building UGC games and you don't know anything about modeling or design like me, you gotta try it out...

Hugh MFER (PORTALS Guy)

180,406 次观看 • 6 个月前

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

AK

305,663 次观看 • 3 年前

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.

Santiago

44,783 次观看 • 1 年前

This is what directing an AI creative studio looks like. I gave my orchestration system a reference image and had it deploy three different interpretations across three machines running Blender simultaneously, all visible from a single dashboard. When one direction looks promising, I branch from it. The system copies the files to the other machines and keeps exploring from that new starting point. Branch, direct, branch again. Each split opens up a new creative path while I give notes in real-time. The number of creative directions I can explore simultaneously is only limited by how many computers I have.

This is what directing an AI creative studio looks like. I gave my orchestration system a reference image and had it deploy three different interpretations across three machines running Blender simultaneously, all visible from a single dashboard. When one direction looks promising, I branch from it. The system copies the files to the other machines and keeps exploring from that new starting point. Branch, direct, branch again. Each split opens up a new creative path while I give notes in real-time. The number of creative directions I can explore simultaneously is only limited by how many computers I have.

Spencer Sterling

85,319 次观看 • 5 个月前

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

Amira Zairi

186,621 次观看 • 3 个月前

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓

slash1s

150,102 次观看 • 11 天前