正在加载视频...

视频加载失败

返回首页

Quick experiment with Sora (text 2 video) -> Gaussian Splat -> WebAR 🚀. Can't wait to generate more! #8thwall #threejs #sora

stspanho's profile picture

Stijn Spanhove

4,222 subscribers

38,110 次观看 • 2 年前 •via X (Twitter)

#8thwall#threejs#sora
LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

Stijn Spanhove 的头像
Stijn Spanhove2 年前

Transformed the Sora video from @OpenAI with @LumaLabsAI to a Gaussian Splat

Stijn Spanhove 的头像
Stijn Spanhove2 年前

Did a fast cutout with Super Splat (@playcanvas). Visualised it in WebAR with @the8thwall and @threejs

Manuel Sainsily 的头像
Manuel Sainsily2 年前

Really cool! I also had fun bringing the splat in Unity. Not enough time today for AR but I’m happy someone else did it :D

Stijn Spanhove 的头像
Stijn Spanhove2 年前

Oh nice one! 🙌

I▲N CURTIS 的头像
I▲N CURTIS2 年前

👀👀

David Hamilton 的头像
David Hamilton2 年前

Wow. Awesome! Now how to convert to various game platforms (e.g. minecraft) for integration?

Jib Jabber 的头像
Jib Jabber2 年前

We be playing Counter Strike on VisionPro soon

Gab Bowie 的头像
Gab Bowie2 年前

It might be helpful if you could adjust the Sora prompt to enable the video to supply more data as input for the 3D generation by Luma.

Stijn Spanhove 的头像
Stijn Spanhove2 年前

Yes exactly, looking forward to experiment with it

相关视频

🧑‍🍳 Experiment with a multimodal LLM in WebAR. The AI identifies ingredients, sets up bounding boxes, and prepares them for AR. I'm also using open-source models to generate recipes and corresponding images. #threejs #8thwall #generativeai
0:51

🧑‍🍳 Experiment with a multimodal LLM in WebAR. The AI identifies ingredients, sets up bounding boxes, and prepares them for AR. I'm also using open-source models to generate recipes and corresponding images. #threejs #8thwall #generativeai

Stijn Spanhove

61,019 次观看 • 2 年前

My Very First Sora 2 Short Film 🤯 100% Text to Video This is FROSTBITE Created with Sora 2 Pro Edited and Directed by Me
2:58

My Very First Sora 2 Short Film 🤯 100% Text to Video This is FROSTBITE Created with Sora 2 Pro Edited and Directed by Me

Dave Clark

277,863 次观看 • 11 个月前

An experiment with 𝘃𝗶𝗿𝘁𝘂𝗮𝗹 𝘁𝗿𝘆-𝗼𝗻 in WebAR 👇 👕 The GenAI-model seamlessly maps pictures onto my 3D-body in AR, all running smoothly on the web. Cool to see the results 👀 #generativeai #threejs #8thwall
2:11

An experiment with 𝘃𝗶𝗿𝘁𝘂𝗮𝗹 𝘁𝗿𝘆-𝗼𝗻 in WebAR 👇 👕 The GenAI-model seamlessly maps pictures onto my 3D-body in AR, all running smoothly on the web. Cool to see the results 👀 #generativeai #threejs #8thwall

Stijn Spanhove

42,097 次观看 • 2 年前

~cowboyz~ made with sora text to video experimental gen ai
2:10

~cowboyz~ made with sora text to video experimental gen ai

Dave Clark

12,041 次观看 • 1 年前

SORA 2 AND SORA 2 PRO ARE LIVE! The next-gen video model has landed on ImagineArt — bringing hyper-realistic visuals, natural physics, and cinematic SFX to life. 💎 1 Month FREE on Creator Plan 💰 Generate a Sora 2 video & Win $11,000 in the SORA 2 Challenge! #ImagineArt #Sora2
0:27

SORA 2 AND SORA 2 PRO ARE LIVE! The next-gen video model has landed on ImagineArt — bringing hyper-realistic visuals, natural physics, and cinematic SFX to life. 💎 1 Month FREE on Creator Plan 💰 Generate a Sora 2 video & Win $11,000 in the SORA 2 Challenge! #ImagineArt #Sora2

ImagineArt

512,966 次观看 • 11 个月前

I ran a quick test: I used the exact same prompt to generate videos with Seedance 2.0 and Sora 2, just to see how they differ. Sora 2 automatically adds music, which instantly makes the video feel polished. But Seedance 2.0 handles shot breakdown and pacing better, it feels more like a professionally edited sequence.
0:30

I ran a quick test: I used the exact same prompt to generate videos with Seedance 2.0 and Sora 2, just to see how they differ. Sora 2 automatically adds music, which instantly makes the video feel polished. But Seedance 2.0 handles shot breakdown and pacing better, it feels more like a professionally edited sequence.

underwood

13,972 次观看 • 7 个月前

only video you need to see what OpenAI released today at DevDay 2025! > apps sdk → build native apps inside ChatGPT > agentkit → openai’s version of n8n > chatkit, evals > more powerful codex > new models in the API → sora 2, gpt-5-pro
1:21

only video you need to see what OpenAI released today at DevDay 2025! > apps sdk → build native apps inside ChatGPT > agentkit → openai’s version of n8n > chatkit, evals > more powerful codex > new models in the API → sora 2, gpt-5-pro

Tushar Mehta

13,762 次观看 • 11 个月前

this whole video was made with AI and it only took me 15 minutes to make here were the tools used: > sora 2 pro > kling 2.6/2.5 > veo 3.1 >nano banana > elevenlabs >topaz upscale >capcut it's never been this easy to make realistic AI videos
0:32

this whole video was made with AI and it only took me 15 minutes to make here were the tools used: > sora 2 pro > kling 2.6/2.5 > veo 3.1 >nano banana > elevenlabs >topaz upscale >capcut it's never been this easy to make realistic AI videos

Miko

27,358 次观看 • 7 个月前

more example videos of OpenAI #sora text to video. The girl in the train is just crazy #openaisora #OpenAI
1:31

more example videos of OpenAI #sora text to video. The girl in the train is just crazy #openaisora #OpenAI

JSFILMZ

104,759 次观看 • 2 年前

Quick After Effects Tutorial - Dripping Text Animation - Add CC Smear on a text layer -> Position the smear on each letter and animate the "REACH" from 0 to 1.000. - New Adjustment Layer -> Add Gaussian Blur at 35 - Add Levels -> Select Alpha -> Set the arrows in the middle.
1:40

Quick After Effects Tutorial - Dripping Text Animation - Add CC Smear on a text layer -> Position the smear on each letter and animate the "REACH" from 0 to 1.000. - New Adjustment Layer -> Add Gaussian Blur at 35 - Add Levels -> Select Alpha -> Set the arrows in the middle.

Cash Design

176,114 次观看 • 3 年前

Introducing Mint MCP - It turns your coding agent into a 3D engine! ✅ Create Threejs apps and games ✅ Generate 3D models ✅ Rig and animate models ✅ Generate Gaussian Splat worlds ✅ Generate PBR materials ✅ Generate themed Asset packs ✅ Generate audio / sfx ✅ Retopologize 3D models ✅ Convert 3D models to any popular format All the scenes in this demo were created with 5.6 + Mint Mcp + Mint Threejs Skills (links below)
0:38

Introducing Mint MCP - It turns your coding agent into a 3D engine! ✅ Create Threejs apps and games ✅ Generate 3D models ✅ Rig and animate models ✅ Generate Gaussian Splat worlds ✅ Generate PBR materials ✅ Generate themed Asset packs ✅ Generate audio / sfx ✅ Retopologize 3D models ✅ Convert 3D models to any popular format All the scenes in this demo were created with 5.6 + Mint Mcp + Mint Threejs Skills (links below)

tamrat

60,192 次观看 • 2 个月前

The new Sora 2 video app is wild. Just asked it to generate “the most 80's thing ever” and the output was uncanny.
1:17

The new Sora 2 video app is wild. Just asked it to generate “the most 80's thing ever” and the output was uncanny.

Nate Lorenzen

445,987 次观看 • 11 个月前

Higgsfield Mod for Minecraft is live. > prompt any building or city, even the Statue of Liberty > create paintings with text-to-image > snap a view and restyle it with image-to-image > make videos from a prompt with text-to-video. > animate in-game photos with image-to-video
0:34

Higgsfield Mod for Minecraft is live. > prompt any building or city, even the Statue of Liberty > create paintings with text-to-image > snap a view and restyle it with image-to-image > make videos from a prompt with text-to-video. > animate in-game photos with image-to-video

Higgsfield AI 🧩

463,434 次观看 • 3 个月前

The OpenAI Sora 2 Agent just dropped on ASI:One, and it opens an entirely new world of creative workflows. ⚡ You can now go from idea → script → video → thumbnail, all inside chat. Sora 2 handles the video generation step: turning natural prompts into cinematic clips in seconds. Experiment. Chain it with other agents. Build your own media pipeline. Live now on Link to agent: Watch 👇
1:22

The OpenAI Sora 2 Agent just dropped on ASI:One, and it opens an entirely new world of creative workflows. ⚡ You can now go from idea → script → video → thumbnail, all inside chat. Sora 2 handles the video generation step: turning natural prompts into cinematic clips in seconds. Experiment. Chain it with other agents. Build your own media pipeline. Live now on Link to agent: Watch 👇

Fetch.ai

19,963 次观看 • 11 个月前

Sora 2 has its capabilities, but it still struggles with making fast movements. However, I’m terrified of what Sora 3 will be able to do. I extended my previous video to a full 2 minute anime intro. It shows clear weaknesses and its strengths.
2:20

Sora 2 has its capabilities, but it still struggles with making fast movements. However, I’m terrified of what Sora 3 will be able to do. I extended my previous video to a full 2 minute anime intro. It shows clear weaknesses and its strengths.

LUͦʷCͦk

2,026,467 次观看 • 11 个月前