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。

Agents using Blender will have a massive impact on media production. I asked Astra to make a scene where people stand in a field watching a UFO - and iterated on exact timing + camera angles. Then I sent it to fal's new 3D to video model and got... show more

Justine Moore

244,367 subscribers

72,959 次观看 • 1 天前 •via X (Twitter)

艺术游戏科学技术

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

3D to Video is now live on H3 Max, the fastest video model on the market and ranked #1 for video editing. Upload a Blender previs up to 15 seconds, and H3 Max turns it into photoreal video while preserving camera movement and shot timing. Add reference images to carry specific characters and environments into the final shot.

3D to Video is now live on H3 Max, the fastest video model on the market and ranked #1 for video editing. Upload a Blender previs up to 15 seconds, and H3 Max turns it into photoreal video while preserving camera movement and shot timing. Add reference images to carry specific characters and environments into the final shot.

fal

154,019 次观看 • 3 天前

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

Tom Krcha

1,440,776 次观看 • 23 天前

I asked Astra to recreate Lewis Hamilton’s Ferrari! It went through F1 specs, regulations, videos from F1 engineers and photos of the car, then built a 3D model (w/ blender) with a full breakdown of the parts. It even made clay & wireframe versions too. Every time I think I’ve pushed this model to its limits, it surprises me.

I asked Astra to recreate Lewis Hamilton’s Ferrari! It went through F1 specs, regulations, videos from F1 engineers and photos of the car, then built a 3D model (w/ blender) with a full breakdown of the parts. It even made clay & wireframe versions too. Every time I think I’ve pushed this model to its limits, it surprises me.

Vaibhav (VB) Srivastav

100,409 次观看 • 21 天前

Another boat demo from Astra today. Asked for a sailboat in Blender, then to make it a browser experience, then to implement good water simulation and weather system. Still impressed!

Another boat demo from Astra today. Asked for a sailboat in Blender, then to make it a browser experience, then to implement good water simulation and weather system. Still impressed!

Thomas Ricouard

16,509 次观看 • 8 天前

I asked @Grok Build to make me a RISC-V chip It took a few days but it got it running Debian in emulator. Then I asked it to build a complete PCB and phone enclosure, research real parts on Alibaba and compose a bill of materials. It even made this video.

I asked @Grok Build to make me a RISC-V chip It took a few days but it got it running Debian in emulator. Then I asked it to build a complete PCB and phone enclosure, research real parts on Alibaba and compose a bill of materials. It even made this video.

Shaw Walters

12,697 次观看 • 4 个月前

Kimi K3 made this fighter jet asset for under $1. Prompt: "Use the Blender MCP tool to make me a fighter jet that I will later use in a video game. Please make it on par with a PS3-era model." 25 minutes later, it was ready in Blender. Imagine where this will be in 5 years.

Kimi K3 made this fighter jet asset for under $1. Prompt: "Use the Blender MCP tool to make me a fighter jet that I will later use in a video game. Please make it on par with a PS3-era model." 25 minutes later, it was ready in Blender. Imagine where this will be in 5 years.

Soya ⚡ AI Automation Builder

56,435 次观看 • 2 个月前

I asked GPT 6 Astra created a render of Silo in blender. It researched its own reference images and gave me this result. Created on ChatGPT work 🤯

I asked GPT 6 Astra created a render of Silo in blender. It researched its own reference images and gave me this result. Created on ChatGPT work 🤯

Pallav Agarwal

160,692 次观看 • 20 天前

I wanted a simple way to render 3D models without opening Blender. So I built this → Upload a model, tweak materials, lighting, and export video animation.

I wanted a simple way to render 3D models without opening Blender. So I built this → Upload a model, tweak materials, lighting, and export video animation.

Augis

159,819 次观看 • 6 个月前

UFO SPOTTED IN NEW YORK? Blink, and you will miss it - people claim to have seen a UFO from a passenger plane. Source: Insider Paper

UFO SPOTTED IN NEW YORK? Blink, and you will miss it - people claim to have seen a UFO from a passenger plane. Source: Insider Paper

Mario Nawfal

1,117,565 次观看 • 2 年前

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this

Eike Drescher

37,987 次观看 • 10 个月前

You can now re-shoot existing video with AI 🤯 I took this clip on people using ChatGPT for medical advice and asked @LTXStudio to re-generate a section (watch for the green bar). Input was just the initial clip + a text prompt with the new dialogue. It's shockingly seamless!

You can now re-shoot existing video with AI 🤯 I took this clip on people using ChatGPT for medical advice and asked @LTXStudio to re-generate a section (watch for the green bar). Input was just the initial clip + a text prompt with the new dialogue. It's shockingly seamless!

Justine Moore

44,346 次观看 • 9 个月前

I was negotiating to buy some shoes online and asked to see a video, then the seller sent me this

I was negotiating to buy some shoes online and asked to see a video, then the seller sent me this

We don't deserve cats 😺

1,175,893 次观看 • 10 个月前

Vibe hardware is here. I gave Astra my credit card and asked for a Teenage Engineering-style mini DJ controller. It generated a concept image, sourced parts, read Chinese datasheets, built a CAD model, ordered everything, then made a Blender animation showing how to assemble it.

Vibe hardware is here. I gave Astra my credit card and asked for a Teenage Engineering-style mini DJ controller. It generated a concept image, sourced parts, read Chinese datasheets, built a CAD model, ordered everything, then made a Blender animation showing how to assemble it.

nim

1,000,250 次观看 • 16 天前

People are earning 10,000$ by selling 3d Websites 💀 So I tried creating a 3d website using GPT-6 Astra + Hyper3D Rodin's MCP And they built this landing page with an INTERACTIVE 3D CAR in the hero. I didn't model the car. I didn't touch Blender. I didn't manually integrate the 3D asset. And this is the result 👇

People are earning 10,000$ by selling 3d Websites 💀 So I tried creating a 3d website using GPT-6 Astra + Hyper3D Rodin's MCP And they built this landing page with an INTERACTIVE 3D CAR in the hero. I didn't model the car. I didn't touch Blender. I didn't manually integrate the 3D asset. And this is the result 👇

FELIX

96,671 次观看 • 15 天前

I spent my Astra tokens trying to teach small Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???

I spent my Astra tokens trying to teach small Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???

merve

22,903 次观看 • 19 天前

I have the goal to learn hardware this year, didn't know where to start so I ask OpenAI Astra to help me build a place to learn with some components I had already and if not use 3D model of the component 🤖

I have the goal to learn hardware this year, didn't know where to start so I ask OpenAI Astra to help me build a place to learn with some components I had already and if not use 3D model of the component 🤖

Aileen Villanueva

16,474 次观看 • 14 天前

this is a big upgrade for AI video you can now drag & drop 3D characters, blocks to build 3d scene, then control the camera angle precisely for Seedance 2.0. no need to do it in Blender anymore

this is a big upgrade for AI video you can now drag & drop 3D characters, blocks to build 3d scene, then control the camera angle precisely for Seedance 2.0. no need to do it in Blender anymore

el.cine

48,078 次观看 • 2 个月前

* MASSIVE INVINCIBLE SPOILERS * Dude this is hilarious, imagine being a show-only watching a clip and then it just autoplays to this video like that LMAO

* MASSIVE INVINCIBLE SPOILERS * Dude this is hilarious, imagine being a show-only watching a clip and then it just autoplays to this video like that LMAO

Gokuto 🍱 - COMMISSIONS OPEN

456,400 次观看 • 5 个月前