正在加载视频...

视频加载失败

返回首页

Blender tutorials are about to age very badly. In this demo, Kimi K3 gets two character references and a plain-English request. Minutes later, it builds the first version inside Blender. The user asks for a better horn, Kimi edits the same scene, and the character starts moving. This is...

irinatoxi's profile picture

Rina

2,476 subscribers

19,092 次观看 • 2 个月前 •via X (Twitter)

LIVE

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

This is much worse for 3D artists than another AI image generator. Claude takes one architectural reference, connects directly to Blender, and starts rebuilding it as an actual editable scene. It blocks out the buildings, matches the camera, adds materials, vegetation, lighting, and then renders the result. The interesting part is not the first generation. Claude inspects its own render, notices the composition and lighting are wrong, then goes back into Blender and keeps changing the scene. The final result is still rough. The materials look basic, the geometry needs cleanup, and an experienced artist would make it far better. But AI is no longer producing a flat image and pretending it understands 3D. It is operating the software, judging its own work, and iterating inside the real project. The “AI cannot do their actual work” argument is getting harder to defend.
1:43

This is much worse for 3D artists than another AI image generator. Claude takes one architectural reference, connects directly to Blender, and starts rebuilding it as an actual editable scene. It blocks out the buildings, matches the camera, adds materials, vegetation, lighting, and then renders the result. The interesting part is not the first generation. Claude inspects its own render, notices the composition and lighting are wrong, then goes back into Blender and keeps changing the scene. The final result is still rough. The materials look basic, the geometry needs cleanup, and an experienced artist would make it far better. But AI is no longer producing a flat image and pretending it understands 3D. It is operating the software, judging its own work, and iterating inside the real project. The “AI cannot do their actual work” argument is getting harder to defend.

Rina

34,431 次观看 • 2 个月前

DeepSeek V4.1 Flash vs Kimi K3 This is not one-shot from DeepSeek btw. The first result was boxy and not realistic, so I iterated with a $6 cap. Kimi did this in one shot, costing $6.95. Not as good as Kimi K3, but it did better than the other Flash models I’ve tried.
0:25

DeepSeek V4.1 Flash vs Kimi K3 This is not one-shot from DeepSeek btw. The first result was boxy and not realistic, so I iterated with a $6 cap. Kimi did this in one shot, costing $6.95. Not as good as Kimi K3, but it did better than the other Flash models I’ve tried.

Bhavy☄️

34,313 次观看 • 23 天前

First tool of its kind a fully agent powered Blender, built straight into Flick. Blender takes months to learn. This takes minutes. Describe your scene, and 3D Stage blocks it out, animates it, and lets you direct the camera Blender quality results, completely free to start. No 3D skills, no separate software anyone can do this. Then it goes straight into AI Video Canvas to finish the shot. Flick
0:33

First tool of its kind a fully agent powered Blender, built straight into Flick. Blender takes months to learn. This takes minutes. Describe your scene, and 3D Stage blocks it out, animates it, and lets you direct the camera Blender quality results, completely free to start. No 3D skills, no separate software anyone can do this. Then it goes straight into AI Video Canvas to finish the shot. Flick

Salt

11,190 次观看 • 2 个月前

THIS STARTUP FORKED BLENDER AND REBUILT IT AROUND AI AGENTS. it's called Mixar. you open a 3D scene and can: → tell an agent what to change directly inside the scene → generate 3D assets from references → retopologize, texture and clean assets → run multiple agents across different scenes → use 400+ AI models from one place they forked Blender itself and are turning it into an agentic 3D platform.
0:30

THIS STARTUP FORKED BLENDER AND REBUILT IT AROUND AI AGENTS. it's called Mixar. you open a 3D scene and can: → tell an agent what to change directly inside the scene → generate 3D assets from references → retopologize, texture and clean assets → run multiple agents across different scenes → use 400+ AI models from one place they forked Blender itself and are turning it into an agentic 3D platform.

matt

71,430 次观看 • 1 天前

SOMEONE JUST DROPPED A FREE AI PLUGIN THAT LIVES INSIDE BLENDER it's called Blender Buddy and it's basically your personal AI helper for 3D work. what it does: > ask it anything about Blender and it answers > tell it to do something and it actually does it inside your scene > it can SEE your viewport, so it knows what you're working on > it can search the web when it needs to look something up > runs locally on your computer (no accounts, no logins, no monthly fees) why this matters: > every other AI Blender addon costs money or needs an API key > this one is completely free AND works offline > 400+ people downloaded it in the first 11 hours if you use Blender, just go grab it. it's free. link in replies 👇
1:59

SOMEONE JUST DROPPED A FREE AI PLUGIN THAT LIVES INSIDE BLENDER it's called Blender Buddy and it's basically your personal AI helper for 3D work. what it does: > ask it anything about Blender and it answers > tell it to do something and it actually does it inside your scene > it can SEE your viewport, so it knows what you're working on > it can search the web when it needs to look something up > runs locally on your computer (no accounts, no logins, no monthly fees) why this matters: > every other AI Blender addon costs money or needs an API key > this one is completely free AND works offline > 400+ people downloaded it in the first 11 hours if you use Blender, just go grab it. it's free. link in replies 👇

Creators Toolbox

362,783 次观看 • 5 个月前

Grok 4.5 just turned Blender into a conversation. Instead of manually importing assets, fixing rigs, placing armies, adjusting cameras, and debugging objects that face the wrong direction, the user simply tells Grok what to change. It builds a medieval battlefield from existing 3D assets, adds horses, knights, a castle, siege machines, trees, animation paths, cameras, and even spatial audio. The impressive part is not that it gets everything right. It absolutely does not. Models spawn upside down, characters face the wrong way, and the scene needs constant correction. But Grok keeps editing the actual Blender project instead of generating another fake 3D image and hoping nobody notices. It is replacing a suspicious amount of the boring work they had to do before the skilled part even started.
2:49

Grok 4.5 just turned Blender into a conversation. Instead of manually importing assets, fixing rigs, placing armies, adjusting cameras, and debugging objects that face the wrong direction, the user simply tells Grok what to change. It builds a medieval battlefield from existing 3D assets, adds horses, knights, a castle, siege machines, trees, animation paths, cameras, and even spatial audio. The impressive part is not that it gets everything right. It absolutely does not. Models spawn upside down, characters face the wrong way, and the scene needs constant correction. But Grok keeps editing the actual Blender project instead of generating another fake 3D image and hoping nobody notices. It is replacing a suspicious amount of the boring work they had to do before the skilled part even started.

Rina

1,091,506 次观看 • 2 个月前

Everyone keeps talking about how good Kimi K3 is. So I gave it one of my favorite frontend tests: one prompt + one reference image. The task: rebuild a 3D globe dashboard. 🌎 The result was almost too good. It did not just build a working page. The texture, lighting, spacing, depth, glass panels, and overall layout were all remarkably close to the reference. Some parts felt nearly pixel-perfect. My honest first impression: for this kind of frontend work, Kimi K3 might be slightly better than Fable 5. All at Sonnet prices.
0:31

Everyone keeps talking about how good Kimi K3 is. So I gave it one of my favorite frontend tests: one prompt + one reference image. The task: rebuild a 3D globe dashboard. 🌎 The result was almost too good. It did not just build a working page. The texture, lighting, spacing, depth, glass panels, and overall layout were all remarkably close to the reference. Some parts felt nearly pixel-perfect. My honest first impression: for this kind of frontend work, Kimi K3 might be slightly better than Fable 5. All at Sonnet prices.

Kai

405,113 次观看 • 2 个月前

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? 👀
0:23

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

53,324 次观看 • 1 个月前

vibe coding metahuman with threejs and codex: first demo I mean it's still a long way to go, but i'm quite surprised myself, turned out way better than i expected and the character isn't too far from AAA? all textures generated by gpt image 2, the facial expressions and target locking were fully written by codex in code, no pre baked animations. So this took about 4 evenings, of which 3 were wasted by clicking through endless blender menus, extruding faces to retopo the model generated with tripo Honestly, a proper AI integrated into blender would've compressed it probably down to a day Very sad to see blender turning away from the future! I have to use it for modeling for now, but will eventually drop it the second an AI boosted modeling software comes out (for free)
0:31

vibe coding metahuman with threejs and codex: first demo I mean it's still a long way to go, but i'm quite surprised myself, turned out way better than i expected and the character isn't too far from AAA? all textures generated by gpt image 2, the facial expressions and target locking were fully written by codex in code, no pre baked animations. So this took about 4 evenings, of which 3 were wasted by clicking through endless blender menus, extruding faces to retopo the model generated with tripo Honestly, a proper AI integrated into blender would've compressed it probably down to a day Very sad to see blender turning away from the future! I have to use it for modeling for now, but will eventually drop it the second an AI boosted modeling software comes out (for free)

robot 2.0

11,065 次观看 • 5 个月前

ChatGPT 6 Astra who? 😭 Fable 5.1 is mogging.. in blender - u just asked it to make 1km x 1km WOW-like fantasy world in blender - basically, just gave it the theme: two opposing fantastical forces - Fable took care of terrains, buildings, trees, points of interest, assets, and layout of the scene - used Blender MCP + Blender skills - Even plugged into local comfyUI setup for texture generation - Then it created the aerial views + 30-60 second flythrough - all from a single prompt.. -This took about 20-25 minutes / 400k tokens :D What is really amazing is how far prompt + tool/MCP + engineering has come now you’re not just asking the AI to make an image anymore.. You’re just asking it to just access the tools and telling it: "hey bro build this game..." And it does... If that’s what a one shot test looks like, game developers are cooked...
0:37

ChatGPT 6 Astra who? 😭 Fable 5.1 is mogging.. in blender - u just asked it to make 1km x 1km WOW-like fantasy world in blender - basically, just gave it the theme: two opposing fantastical forces - Fable took care of terrains, buildings, trees, points of interest, assets, and layout of the scene - used Blender MCP + Blender skills - Even plugged into local comfyUI setup for texture generation - Then it created the aerial views + 30-60 second flythrough - all from a single prompt.. -This took about 20-25 minutes / 400k tokens :D What is really amazing is how far prompt + tool/MCP + engineering has come now you’re not just asking the AI to make an image anymore.. You’re just asking it to just access the tools and telling it: "hey bro build this game..." And it does... If that’s what a one shot test looks like, game developers are cooked...

Priy

51,025 次观看 • 28 天前

This AI video is a Masterpiece 🤯 Took an experiment further than planned: feeding one concept shot into GPT-6 Astra, generating the base geometry in Blender, and pushing the final render through Flova. Made it with FlovaAI
0:25

This AI video is a Masterpiece 🤯 Took an experiment further than planned: feeding one concept shot into GPT-6 Astra, generating the base geometry in Blender, and pushing the final render through Flova. Made it with FlovaAI

William AI

606,819 次观看 • 23 天前

🚨 STOP learning Blender !! Learning Blender in 2026..... Is officially obsolete. MiniMax Design can now automate Blender to create ANY 3d SCENE !! I just gave it a PROMPT.... And MiniMax Design used GPT-6 Astra to handle everything like: 1️⃣ Opening Blender 2️⃣ Generating the 3D elements 3️⃣ Fixing lighting 4️⃣ Camera Tracking Data etc.... It built the entire scene inside Blender. Finally, I used MiniMax H3 Max to add colors to the 3d SCENE !! Then I just rendered the 3d scene !! Best part? Using GPT-6 Astra through MiniMax Design is way more affordable than running it directly.
0:48

🚨 STOP learning Blender !! Learning Blender in 2026..... Is officially obsolete. MiniMax Design can now automate Blender to create ANY 3d SCENE !! I just gave it a PROMPT.... And MiniMax Design used GPT-6 Astra to handle everything like: 1️⃣ Opening Blender 2️⃣ Generating the 3D elements 3️⃣ Fixing lighting 4️⃣ Camera Tracking Data etc.... It built the entire scene inside Blender. Finally, I used MiniMax H3 Max to add colors to the 3d SCENE !! Then I just rendered the 3d scene !! Best part? Using GPT-6 Astra through MiniMax Design is way more affordable than running it directly.

Darshal Jaitwar

86,087 次观看 • 18 天前

This is running in a browser tab. No engine. No install. No download. Six spells, real-time particle simulation, refracting ice geometry, and a live VFX editor on the right side where every parameter is tunable while the scene runs. A studio VFX artist builds this in weeks. It is genuinely the hardest discipline in 3D - nothing about particle work is intuitive. The thing that changed is not that AI got better at art. It is that Astra writes geometry and shaders as CODE instead of as files. A game made of .fbx files is a game an AI can only rearrange. A game made of code is a game an AI can edit. That is why the good demos this week are all three.js and Blender-scripted, and why they run at 60fps in a tab. Dude built a full game this way and it came out under 2 MB before audio. Every rock, tree and character - procedural code, not assets. The cost consequence is the part almost nobody understood: → let the model CLICK in Blender: burns your weekly cap in two minutes → let the model WRITE Blender Python: ~100x cheaper One builder shipped a complete 3D roguelike level - day/night cycle, weather, modeling, texturing, enemies - for 3% of his quota. That is the entire reason why. Scripts, not clicks. It's the single rule that decides your bill. Full breakdown + the 7-day guide in the article below ↓
0:28

This is running in a browser tab. No engine. No install. No download. Six spells, real-time particle simulation, refracting ice geometry, and a live VFX editor on the right side where every parameter is tunable while the scene runs. A studio VFX artist builds this in weeks. It is genuinely the hardest discipline in 3D - nothing about particle work is intuitive. The thing that changed is not that AI got better at art. It is that Astra writes geometry and shaders as CODE instead of as files. A game made of .fbx files is a game an AI can only rearrange. A game made of code is a game an AI can edit. That is why the good demos this week are all three.js and Blender-scripted, and why they run at 60fps in a tab. Dude built a full game this way and it came out under 2 MB before audio. Every rock, tree and character - procedural code, not assets. The cost consequence is the part almost nobody understood: → let the model CLICK in Blender: burns your weekly cap in two minutes → let the model WRITE Blender Python: ~100x cheaper One builder shipped a complete 3D roguelike level - day/night cycle, weather, modeling, texturing, enemies - for 3% of his quota. That is the entire reason why. Scripts, not clicks. It's the single rule that decides your bill. Full breakdown + the 7-day guide in the article below ↓

Aleiah

41,744 次观看 • 27 天前

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 ↓
0:58

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 • 2 个月前

GPT-5.6 Sol Ultra was given a full set of character references and asked to rebuild the character in Blender, rig it, create three animations, export a real GLB, and build a complete Three.js showcase around it. The entire pipeline was completed in 2 hours and 11 minutes. The final model still loses some of the original proportions, costume structure, and material fidelity, but going from reference images to a rigged, animated 3D character running in the browser is already a very strong result. Cc: Givros
0:27

GPT-5.6 Sol Ultra was given a full set of character references and asked to rebuild the character in Blender, rig it, create three animations, export a real GLB, and build a complete Three.js showcase around it. The entire pipeline was completed in 2 hours and 11 minutes. The final model still loses some of the original proportions, costume structure, and material fidelity, but going from reference images to a rigged, animated 3D character running in the browser is already a very strong result. Cc: Givros

Token Gremlin

37,583 次观看 • 2 个月前

Mechanical CAD might be one of the first jobs MCP quietly wrecks. This guy connects an AI agent to Autodesk Fusion, gives it the dimensions for a snap-fit brick, and basically stops modeling. The agent builds the actual CAD part, adds the studs, hollows the underside, calculates the wall thickness and center support, then modifies the real Fusion model when asked. Then it checks the geometry and rounds the exposed edges. This is not text-to-3D. This is AI operating Autodesk Fusion like a junior CAD engineer. If this gets reliable, memorizing every tool in Fusion starts looking a lot less valuable than knowing what the part actually needs to do.
0:46

Mechanical CAD might be one of the first jobs MCP quietly wrecks. This guy connects an AI agent to Autodesk Fusion, gives it the dimensions for a snap-fit brick, and basically stops modeling. The agent builds the actual CAD part, adds the studs, hollows the underside, calculates the wall thickness and center support, then modifies the real Fusion model when asked. Then it checks the geometry and rounds the exposed edges. This is not text-to-3D. This is AI operating Autodesk Fusion like a junior CAD engineer. If this gets reliable, memorizing every tool in Fusion starts looking a lot less valuable than knowing what the part actually needs to do.

Rina

14,531 次观看 • 1 个月前

Claude Fable 5 vs Kimi K3 — same 3D build, 3.3x cheaper. someone prototyped a 3D stadium seat-view picker with Fable 5 — preview exactly what you'll see from your seat before buying a ticket. I rebuilt the same thing with Kimi K3 in two hours, at 3.3x lower cost. no more static seat maps. pick a seat, see the actual view in 3D, then buy. works for cinemas, concerts, cricket grounds, Wimbledon — any venue. K3 dropped this week: 2.8 trillion parameters, open weights July 27. 3D is the future, and it just got a lot cheaper to build. Live Fable 5: Live Kimi K3: Code: full Kimi K3 breakdown below.
0:47

Claude Fable 5 vs Kimi K3 — same 3D build, 3.3x cheaper. someone prototyped a 3D stadium seat-view picker with Fable 5 — preview exactly what you'll see from your seat before buying a ticket. I rebuilt the same thing with Kimi K3 in two hours, at 3.3x lower cost. no more static seat maps. pick a seat, see the actual view in 3D, then buy. works for cinemas, concerts, cricket grounds, Wimbledon — any venue. K3 dropped this week: 2.8 trillion parameters, open weights July 27. 3D is the future, and it just got a lot cheaper to build. Live Fable 5: Live Kimi K3: Code: full Kimi K3 breakdown below.

Kirill

207,314 次观看 • 2 个月前

How about one image straight to an editable UE5 or Blender scene? Lumera just dropped paper - Engine-Native Editable 3D World Reconstruction with Objects & Lighting. You give it an image. It figures out what's in the scene, rebuilds every object as a separate mesh, then recreates the lighting as actual engine lights you can move and tweak. Even pulls an HDR environment out of the shot. The lighting part is the big deal here. Every other image-to-3D approach bakes it in. Lumera keeps it a parameter, like the scene was built in the engine from the start. Code and weights marked as "Soon". Paper -
1:51

How about one image straight to an editable UE5 or Blender scene? Lumera just dropped paper - Engine-Native Editable 3D World Reconstruction with Objects & Lighting. You give it an image. It figures out what's in the scene, rebuilds every object as a separate mesh, then recreates the lighting as actual engine lights you can move and tweak. Even pulls an HDR environment out of the shot. The lighting part is the big deal here. Every other image-to-3D approach bakes it in. Lumera keeps it a parameter, like the scene was built in the engine from the start. Code and weights marked as "Soon". Paper -

Stefan 3D AI

47,223 次观看 • 1 个月前

There’s a pattern with agent demos. You see the setup, then the result. The messy middle is usually missing. Nex-N2.5 Pro caught my attention because it leaves that part in. You can watch it read the screen, act, see what changed, and adjust. That’s where the 397B multimodal build comes in. Take a look at the Blender task below. Instead of just generating some code and calling it a day, it actually works through the whole thing. here’s what I noticed: It started by creating the scene, then checked the result instead of assuming everything went right. Something looked off? It went back in, changed the setup, rendered again and checked the new result. That little loop is what stood out to me. Because real computer work rarely goes: prompt → perfect result. There’s usually a lot of: “this doesn’t look right, let me fix that.” Seeing an AI handle that part inside Blender is probably the most interesting thing about this demo. You can try Nex-N2.5 Pro for free on OpenRouter.
1:15

There’s a pattern with agent demos. You see the setup, then the result. The messy middle is usually missing. Nex-N2.5 Pro caught my attention because it leaves that part in. You can watch it read the screen, act, see what changed, and adjust. That’s where the 397B multimodal build comes in. Take a look at the Blender task below. Instead of just generating some code and calling it a day, it actually works through the whole thing. here’s what I noticed: It started by creating the scene, then checked the result instead of assuming everything went right. Something looked off? It went back in, changed the setup, rendered again and checked the new result. That little loop is what stood out to me. Because real computer work rarely goes: prompt → perfect result. There’s usually a lot of: “this doesn’t look right, let me fix that.” Seeing an AI handle that part inside Blender is probably the most interesting thing about this demo. You can try Nex-N2.5 Pro for free on OpenRouter.

SayoClips

165,376 次观看 • 23 天前