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。

We gave GLM-5.3-Flash a Blender scene and 12 hours later it built this.

Lou

21,995 subscribers

201,154 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

34 条评论

Loktar 🇺🇸 的头像

Loktar 🇺🇸1 个月前

I'm not surprised you guys hit the 3d HARD in training for sure. GLM 5.3 Flash is definitely miles ahead other models in any 3d generation.

Meshak 的头像

Meshak1 个月前

can you break down how u did this ?

0x505badc0de 的头像

0x505badc0de1 个月前

Well, what exactly did it do? Camera movement? Render queuing? Because that's not clear from the post.

Lukas Bug 的头像

Lukas Bug1 个月前

Please give us a small writeup on how u did this. Would love to utilize GLM 5.3 Flash for something like this

Han Xiao 的头像

Han Xiao1 个月前

would be really nice to share some tricks for long-horizon tasks like this. like the prompt the harness the gotchas etc.

Ryan Sael 的头像

Ryan Sael1 个月前

It's really good at 3d

Ivan Fioravanti ᯅ 的头像

Ivan Fioravanti ᯅ1 个月前

This is incredible! Love it!

Elliot Arledge 的头像

Elliot Arledge1 个月前

wow

Superpositionbigbang 的头像

Superpositionbigbang1 个月前

Try intergrating seedance 2.5 with the model

Matt Furnari 的头像

Matt Furnari1 个月前

I don't believe you. I couldn't even get it to reliably return Json formatting.

HKay 的头像

HKay1 个月前

How much did this cost?

Mike Gannotti 的头像

Mike Gannotti1 个月前

Wow!!!!! such a good model! Have it running right now locally on my 2 @NVIDIAAI DGX Sparks and it is AWESOME!

Justin 的头像

Justin1 个月前

Insane. Let him cook now. Tell him To make Toy Story 6

Marcel Spatz 的头像

Marcel Spatz1 个月前

Would be great to understand what it actually did, havent had any good results with any model using blender so far

Fax 的头像

Fax1 个月前

How? Good blender MCP output is a massive bottleneck, everything comes out like a potato 😂

Hanchen Li 的头像

Hanchen Li1 个月前

This is crazy

Victoria Neiman 的头像

Victoria Neiman1 个月前

hey! we tested glm 5.3 in three scenes, which it created on its own. the results for a really low price are insane

cached 的头像

cached1 个月前

i've tried blender with many frontier agents and tbh they're not that good compared to other things. i think part of it is because it just runs python scripts and its unimaginably impractical to ''code'' your way to sculpting models. need better way of interaction with blender

Black Eyed Hat Man 的头像

Black Eyed Hat Man1 个月前

Impressive without the people or furry animals, could see how it's useful for scenes 👌

Levanto Labs 的头像

Levanto Labs1 个月前

Explain.

Gon N 的头像

Gon N1 个月前

Please share the prompt Lou

George Raven 的头像

George Raven1 个月前

No human in the loop?

yu qiu 的头像

yu qiu1 个月前

wowo！It would be wonderful if you could share how he managed to do it.

sneha 的头像

sneha1 个月前

how did you do it?

lazysloth 的头像

lazysloth1 个月前

5.3-flash is god tier, super fast iteration and the vlm feels amazing to use, you no longer need to delegate to that crappy mcp which is like using a dog(mcp) to guide a blind human(glm.5.3).

Rick A.F. 的头像

Rick A.F.1 个月前

@_ryu15_ Dang looks like real life tbh

Taylor Ogan 的头像

Taylor Ogan1 个月前

Looking forward to experiencing the cocktail bar!

Alexander 的头像

Alexander1 个月前

What harness had you used?

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

12 hours for this, impressive patience

Coinupbtc 🪙 的头像

Coinupbtc 🪙1 个月前

@TechMDAI No way?

DaBin.Binah 的头像

DaBin.Binah1 个月前

具体用什么工具、分步步骤拆解的流程能讲一下吗？

J A Z I I 的头像

J A Z I I1 个月前

You guys cooked

A.K.A CS 的头像

A.K.A CS1 个月前

@TechMDAI The is is looking so good? How did you achieve this?

Shivang 的头像

Shivang1 个月前

Can you share the prompt

相关视频

We use GLM-5.3-Flash build a dream kitchen. A 3D world built in Blender. This is not a generated video.

We use GLM-5.3-Flash build a dream kitchen. A 3D world built in Blender. This is not a generated video.

Lou

1,010,361 次观看 • 1 个月前

We are all sitting in a room watching GLM-5.3-Flash write Blender script for automotive museum.

We are all sitting in a room watching GLM-5.3-Flash write Blender script for automotive museum.

Lou

44,446 次观看 • 1 个月前

Five frontier models. One simple prompt. No retries. No blender. Just a simple frontend web design. Fable 5.1 vs. GPT-6 Astra vs. DeepSeek v4.1 Flash vs. GLM 5.3 Flash vs. Qwen3.8 Flash Next Which model built the best looking luxury watch landing page? IMO Fable 5.1 and GLM 5.3 Flash look the best. LIVE DEMO:

Five frontier models. One simple prompt. No retries. No blender. Just a simple frontend web design. Fable 5.1 vs. GPT-6 Astra vs. DeepSeek v4.1 Flash vs. GLM 5.3 Flash vs. Qwen3.8 Flash Next Which model built the best looking luxury watch landing page? IMO Fable 5.1 and GLM 5.3 Flash look the best. LIVE DEMO:

Mia

16,546 次观看 • 28 天前

4 AI models trying to draw their self-portraits. GLM-5.3-Flash, GLM-5.3, Kimi K3, and Claude Opus 5. GLM-5.3-Flash came out looking the most handsome 🤓

4 AI models trying to draw their self-portraits. GLM-5.3-Flash, GLM-5.3, Kimi K3, and Claude Opus 5. GLM-5.3-Flash came out looking the most handsome 🤓

TypingMind

77,196 次观看 • 1 个月前

Build & Train a GLM-5.3-Flash Model From Scratch I built a 25.7M-parameter educational model inspired by GLM-5.3-Flash, then tested its architecture, pretraining, and executable-reward reinforcement learning end to end. Repository: YouTube: Become AI researcher in 90 days:

Build & Train a GLM-5.3-Flash Model From Scratch I built a 25.7M-parameter educational model inspired by GLM-5.3-Flash, then tested its architecture, pretraining, and executable-reward reinforcement learning end to end. Repository: YouTube: Become AI researcher in 90 days:

Vuk Rosić 武克

14,590 次观看 • 1 个月前

GLM-5.3 made this after 4+ hours!

GLM-5.3 made this after 4+ hours!

Da7em

161,443 次观看 • 2 个月前

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in

atomic.chat

32,515 次观看 • 1 个月前

GLM-5.3-Flash streaming at 32 tok/s on a single Spark via Tensorfold ⚡️ i will share the recipe later today

GLM-5.3-Flash streaming at 32 tok/s on a single Spark via Tensorfold ⚡️ i will share the recipe later today

filipe

15,167 次观看 • 11 天前

Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepSeek-V4.1 Flash: 615 tok/s 1/7

Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepSeek-V4.1 Flash: 615 tok/s 1/7

RunAnywhere

64,384 次观看 • 22 天前

GLM 5.3 free on Kira AI, 100M tokens + 50M check-in 😳 GLM 5.3 + Flash + Qwen 3.8 Flash free. 1M context, no card. → → sign up → grab key → plug in Third-party proxy, don't send secrets. Go grab it.

GLM 5.3 free on Kira AI, 100M tokens + 50M check-in 😳 GLM 5.3 + Flash + Qwen 3.8 Flash free. 1M context, no card. → → sign up → grab key → plug in Third-party proxy, don't send secrets. Go grab it.

Punch AI

17,124 次观看 • 1 个月前

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.

Harrison Kinsley

54,330 次观看 • 23 天前

Ox Alpha is actually GLM-5.3-Flash, and it’s one of my favorite models ever released.

Ox Alpha is actually GLM-5.3-Flash, and it’s one of my favorite models ever released.

Theo - t3.gg

138,782 次观看 • 1 个月前

Built a villa scene in Blender with Fable 5.1 and GPT-6 Astra This is what it built

Built a villa scene in Blender with Fable 5.1 and GPT-6 Astra This is what it built

Karan

2,889,133 次观看 • 1 个月前

Here's Qwen3.8-Flash with the same prompt. It looks good, but it didn't do any firm grain, and misses many of the cool effects GLM 5.3 Flash added. Live demo:

Here's Qwen3.8-Flash with the same prompt. It looks good, but it didn't do any firm grain, and misses many of the cool effects GLM 5.3 Flash added. Live demo:

Mia

12,890 次观看 • 1 个月前

Gave Opus 5.5 donald's prompt, Midjourney, and a moodboard 12 hours later, woke up to this:

Gave Opus 5.5 donald's prompt, Midjourney, and a moodboard 12 hours later, woke up to this:

anabology

20,014,765 次观看 • 18 天前

glm 5.3 flash is 7.5x cheaper, but 3.4x slower than gemini 3.7 flash Z.ai glm 5.3 flash – shipped aug 26, $0.07/$0.25 per 1m Google DeepMind gemini 3.7 flash – shipped aug 13, $0.38/$1.88 per 1m we put the two models on one job: write one html file that draws an animated 3d scene in the browser. no images, no downloads, and it has to look the same on every load. the setup: three scenes – a glass aquarium in a lit room, the solar system, a night city under a thunderstorm. identical brief word for word, reasoning effort high, 64k output cap. the numbers below are not the whole run. they cover the three scenes we kept – the best one per task from each model, the ones in the video. - total generation time for the three scenes #1 gemini 3.7 flash – 10m 36s #2 glm 5.3 flash – 36m 30s - tokens spent on those three scenes #1 glm 5.3 flash – 110k #2 gemini 3.7 flash – 111k - cost of those three scenes #1 glm 5.3 flash – $0.027 #2 gemini 3.7 flash – $0.202 observations: • glm's first 10 attempts: 7 blank pages. it kept inventing short random helpers and forgetting to define one of them. the fix was one line in the brief: use exactly one random helper, named rand(), and don't invent shorthands next to it. next 12 attempts: 11 alive, 0 crashes. • glm spends 66% of its output on reasoning, gemini 57%. that is the whole speed gap. • gemini's storm came back as a black rectangle in 4 of 6 runs. glm's best storm has a branching bolt, lit rain and wet asphalt – for $0.01. conclusion: same three scenes, same token spend – glm 5.3 flash billed $0.027 and took 36m 30s, gemini 3.7 flash billed $0.202 and took 10m 36s. glm wins gemini on price and made the best storm of the whole run follow thehype. for 24/7 ai news, analysis and breakdowns

glm 5.3 flash is 7.5x cheaper, but 3.4x slower than gemini 3.7 flash Z.ai glm 5.3 flash – shipped aug 26, $0.07/$0.25 per 1m Google DeepMind gemini 3.7 flash – shipped aug 13, $0.38/$1.88 per 1m we put the two models on one job: write one html file that draws an animated 3d scene in the browser. no images, no downloads, and it has to look the same on every load. the setup: three scenes – a glass aquarium in a lit room, the solar system, a night city under a thunderstorm. identical brief word for word, reasoning effort high, 64k output cap. the numbers below are not the whole run. they cover the three scenes we kept – the best one per task from each model, the ones in the video. - total generation time for the three scenes #1 gemini 3.7 flash – 10m 36s #2 glm 5.3 flash – 36m 30s - tokens spent on those three scenes #1 glm 5.3 flash – 110k #2 gemini 3.7 flash – 111k - cost of those three scenes #1 glm 5.3 flash – $0.027 #2 gemini 3.7 flash – $0.202 observations: • glm's first 10 attempts: 7 blank pages. it kept inventing short random helpers and forgetting to define one of them. the fix was one line in the brief: use exactly one random helper, named rand(), and don't invent shorthands next to it. next 12 attempts: 11 alive, 0 crashes. • glm spends 66% of its output on reasoning, gemini 57%. that is the whole speed gap. • gemini's storm came back as a black rectangle in 4 of 6 runs. glm's best storm has a branching bolt, lit rain and wet asphalt – for $0.01. conclusion: same three scenes, same token spend – glm 5.3 flash billed $0.027 and took 36m 30s, gemini 3.7 flash billed $0.202 and took 10m 36s. glm wins gemini on price and made the best storm of the whole run follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

16,041 次观看 • 1 个月前

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient

Iam_

110,563 次观看 • 1 个月前

Space Bunny performs TERRIBLE in physics 💀 we tested Space Bunny against GLM 5.3 in a task with a single focus scenes: an explosion in a desert, a tornado, a balloon pop, a water drop fall, and the Newton’s cradle here’s what we got: - the Newton’s cradle is where GLM 5.3 totally cooked Space Bunny - water drop and tornado were the worst, neither of the models handled it price: Space Bunny: free GLM 5.3: $0.40 try it with

Space Bunny performs TERRIBLE in physics 💀 we tested Space Bunny against GLM 5.3 in a task with a single focus scenes: an explosion in a desert, a tornado, a balloon pop, a water drop fall, and the Newton’s cradle here’s what we got: - the Newton’s cradle is where GLM 5.3 totally cooked Space Bunny - water drop and tornado were the worst, neither of the models handled it price: Space Bunny: free GLM 5.3: $0.40 try it with

AI/ML API

27,304 次观看 • 20 天前

I told you Local AI will be competitive. 12 / 15 sessions running on my machine rn are local, DS4.1-Flash and GLM-5.3-Flash are better than anything else out there. So fast, don't complain, no rate limits. Why we gotta live like plebs?

I told you Local AI will be competitive. 12 / 15 sessions running on my machine rn are local, DS4.1-Flash and GLM-5.3-Flash are better than anything else out there. So fast, don't complain, no rate limits. Why we gotta live like plebs?

0xSero

65,627 次观看 • 27 天前

GLM 5.3 Flash on 2x DGX Sparks Look at the tok/s at the top :) This is prose. Releasing soon

GLM 5.3 Flash on 2x DGX Sparks Look at the tok/s at the top :) This is prose. Releasing soon

Mia

16,605 次观看 • 1 个月前