Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

GPT Image 2.0 + Generated Normal Maps = Dynamic Lighting and Shadows for UI. 🤯 The workflow for building high-fidelity skeuomorphic UI concepts with AI + Three.js just got a lot easier. Interactive experience, sound fx, and normals all generated with Omma AI (tool by Spline). 3D iPhone by...

gaborpribek's profile picture

Gábor Pribék

2,084 subscribers

12,290 görüntüleme • 1 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

I used the GPT Image 2 "360 equirectangular [subject: cats]" trick and turned them into 360 immersive videos! Videos and interactive 3D experience using Three.js generated with Omma AI (tool by Spline ) Planning to share the workflow and experience on Omma community, lmk if you are interested!
0:14

I used the GPT Image 2 "360 equirectangular [subject: cats]" trick and turned them into 360 immersive videos! Videos and interactive 3D experience using Three.js generated with Omma AI (tool by Spline ) Planning to share the workflow and experience on Omma community, lmk if you are interested!

Gábor Pribék

23,493 görüntüleme • 1 ay önce

Vibe-coded a "Ponku" sticker experience to mirror how Apple is blending iPhone hardware with Korea Emojis. 🌈📱 3D iPhone by Ranguel on Sketchfab. Built with AI in Omma by Spline. Lmk in the comments if you would like to grab a copy of the experience!
0:11

Vibe-coded a "Ponku" sticker experience to mirror how Apple is blending iPhone hardware with Korea Emojis. 🌈📱 3D iPhone by Ranguel on Sketchfab. Built with AI in Omma by Spline. Lmk in the comments if you would like to grab a copy of the experience!

Gábor Pribék

17,196 görüntüleme • 2 ay önce

What if anatomy explorers felt alive? This 3D dog, including the skeleton, organs and rig, was generated with ai and reacts to the cursor in real time with head tracking and tail movement. - Used GPT Images 2 for consistency - Omma AI for 3D generation and code using Three.js Lmk if you’d like to try it!
0:14

What if anatomy explorers felt alive? This 3D dog, including the skeleton, organs and rig, was generated with ai and reacts to the cursor in real time with head tracking and tail movement. - Used GPT Images 2 for consistency - Omma AI for 3D generation and code using Three.js Lmk if you’d like to try it!

Gábor Pribék

203,261 görüntüleme • 1 ay önce

1. Generate UI with gpt-image-2 2. Generate a normal map from the image 3. Dynamic lighting for UI components - raised elements actually cast shadows and get lit naturally.
0:13

1. Generate UI with gpt-image-2 2. Generate a normal map from the image 3. Dynamic lighting for UI components - raised elements actually cast shadows and get lit naturally.

Jacob Miller

57,009 görüntüleme • 1 ay önce

Played around with generating the internal anatomy of a creature (skeletons and organs). I used GPT Images 2 to keep the creature anatomy consistent, while the code, interactions and 3D models were generated with Omma and uses Three.js.
0:10

Played around with generating the internal anatomy of a creature (skeletons and organs). I used GPT Images 2 to keep the creature anatomy consistent, while the code, interactions and 3D models were generated with Omma and uses Three.js.

Gábor Pribék

75,478 görüntüleme • 1 ay önce

Now you can use the Gemini app to see if a video was generated with Google AI. We’re building on our powerful content verification tool to help you more easily identify AI-generated content. You can upload an image or video and Gemini will check for the SynthID watermark to see if it was edited or created with Google AI.
0:18

Now you can use the Gemini app to see if a video was generated with Google AI. We’re building on our powerful content verification tool to help you more easily identify AI-generated content. You can upload an image or video and Gemini will check for the SynthID watermark to see if it was edited or created with Google AI.

Google Gemini

66,432 görüntüleme • 6 ay önce

This is SOTA for AI generated 3D objects. It's come a long way. - Generated with Hunyuan3d-2 Image-to-3D.
0:12

This is SOTA for AI generated 3D objects. It's come a long way. - Generated with Hunyuan3d-2 Image-to-3D.

cocktail peanut

63,704 görüntüleme • 1 yıl önce

Just built a 3D Strava/Apple Health fitness visualizer in Omma (by Spline) that turns .gpx files into 3D terrain with live metrics. Drag, drop, and watch your run come to life in real-time. Lmk if you want to remix and test with your own data!
0:14

Just built a 3D Strava/Apple Health fitness visualizer in Omma (by Spline) that turns .gpx files into 3D terrain with live metrics. Drag, drop, and watch your run come to life in real-time. Lmk if you want to remix and test with your own data!

Gábor Pribék

19,854 görüntüleme • 2 ay önce

GPT Image 2 + Seedance 2.0 - Prompt Share Created on Martini Art AI Workflow: Create a character with Midjourney. Turn that character to stylized 3d with GPT Image 2. Create a storyboard with that character sheet. Create the final video using both character sheet and storyboard references.
0:15

GPT Image 2 + Seedance 2.0 - Prompt Share Created on Martini Art AI Workflow: Create a character with Midjourney. Turn that character to stylized 3d with GPT Image 2. Create a storyboard with that character sheet. Create the final video using both character sheet and storyboard references.

Kōda

31,303 görüntüleme • 18 gün önce

From a passing glance to holding hands forever 🌸❤️ Generated this with GPT image 2 + Seedance 2.0 on BudgetPixel AI
0:15

From a passing glance to holding hands forever 🌸❤️ Generated this with GPT image 2 + Seedance 2.0 on BudgetPixel AI

Ai Arainz

18,985 görüntüleme • 1 ay önce

We just added a Sora UI Kit to MagicPath. MagicPath is the only design platform where you can do this today: create high-fidelity, interactive components with AI, in your own style, on an infinite canvas. No other tool even comes close.
0:18

We just added a Sora UI Kit to MagicPath. MagicPath is the only design platform where you can do this today: create high-fidelity, interactive components with AI, in your own style, on an infinite canvas. No other tool even comes close.

Pietro Schirano

21,366 görüntüleme • 8 ay önce

With the launch of Nano Banana Pro, we're also rolling out the ability for Gemini users to check whether an image was generated with or edited by Google AI using SynthID, our digital watermarking technology. Now you can upload any image into the Gemini app and ask "Is this AI-generated?" Gemini then scans the image for the imperceptible SynthID watermarks that are embedded into all Google AI-generated images - including those by Nano Banana Pro! Learn more about Google’s efforts to increase AI transparency:
0:16

With the launch of Nano Banana Pro, we're also rolling out the ability for Gemini users to check whether an image was generated with or edited by Google AI using SynthID, our digital watermarking technology. Now you can upload any image into the Gemini app and ask "Is this AI-generated?" Gemini then scans the image for the imperceptible SynthID watermarks that are embedded into all Google AI-generated images - including those by Nano Banana Pro! Learn more about Google’s efforts to increase AI transparency:

Google Gemini

190,382 görüntüleme • 6 ay önce

The most insane underground dance battle of the year 🕺 I generated this with GPT Image 2 + Seedance 2.0 on Genflow AI
0:14

The most insane underground dance battle of the year 🕺 I generated this with GPT Image 2 + Seedance 2.0 on Genflow AI

Ai Arainz

16,424 görüntüleme • 11 gün önce

HTML enters 3D! Or vice versa? With the new HTML in Canvas by WICG, we can finally put native DOM elements directly into WebGL/WebGPU scenes. It is experimental for now, but the possibilities for 3D interfaces and special effects are huge. This demo was built using Three.js and Omma AI (tool by Spline ) It’s a fun new way to explore what the web can do! Are you interested in seeing the demo?
0:10

HTML enters 3D! Or vice versa? With the new HTML in Canvas by WICG, we can finally put native DOM elements directly into WebGL/WebGPU scenes. It is experimental for now, but the possibilities for 3D interfaces and special effects are huge. This demo was built using Three.js and Omma AI (tool by Spline ) It’s a fun new way to explore what the web can do! Are you interested in seeing the demo?

Gábor Pribék

175,387 görüntüleme • 1 ay önce

Created with Seedance 2.0 + GPT Image 2 on Pollo AI Paying just $0.11 for Seedance 2.0 generations still feels impossible. Pollo AI Ultra honestly changed the economics of AI content. Workflow 👇🏻
0:14

Created with Seedance 2.0 + GPT Image 2 on Pollo AI Paying just $0.11 for Seedance 2.0 generations still feels impossible. Pollo AI Ultra honestly changed the economics of AI content. Workflow 👇🏻

Calira

22,074 görüntüleme • 1 ay önce

So, I heard you like equirectangular 360° images generated with GPT Image 2.0. Let's build a grid out of them and run it through best video model Seedance 2.0. Prompts in the replies. Feel free to take them and tweak as you like. GPT Image 2.0 × Seedance 2.0 on Higgsfield
0:15

So, I heard you like equirectangular 360° images generated with GPT Image 2.0. Let's build a grid out of them and run it through best video model Seedance 2.0. Prompts in the replies. Feel free to take them and tweak as you like. GPT Image 2.0 × Seedance 2.0 on Higgsfield

Kōda

12,357 görüntüleme • 1 ay önce

GPT-5.3-Codex + Image-to-3D Skill Just generated a cute avatar for Sam Altman
0:17

GPT-5.3-Codex + Image-to-3D Skill Just generated a cute avatar for Sam Altman

Hyper3D by Deemos

80,329 görüntüleme • 4 ay önce

More coming soon ! I manage to integrate for the first time volumetric 3D video made with Kartel.ai inside the AI world generated in gaussian splatting by World Labs !! I coded all in three.js! And it's possible to integrate elements on the fly ;) And so you can imagine soon what we will produce with that en AI : consistency of character and environment, relighting etc...
0:14

More coming soon ! I manage to integrate for the first time volumetric 3D video made with Kartel.ai inside the AI world generated in gaussian splatting by World Labs !! I coded all in three.js! And it's possible to integrate elements on the fly ;) And so you can imagine soon what we will produce with that en AI : consistency of character and environment, relighting etc...

Lovis Odin

33,984 görüntüleme • 1 yıl önce

GPT Image 2.0 + Seedance 2.0 is a powerful combo for game scene creation. Generate the character UI, loading screen, HUD, and cinematic gameplay look with GPT Image 2.0, then use Seedance 2.0 to turn it into a smooth one-shot game demo video.
0:15

GPT Image 2.0 + Seedance 2.0 is a powerful combo for game scene creation. Generate the character UI, loading screen, HUD, and cinematic gameplay look with GPT Image 2.0, then use Seedance 2.0 to turn it into a smooth one-shot game demo video.

BudgetPixel AI

730,287 görüntüleme • 1 ay önce

GPT Image 2 + Seedance 2.0 I could've pushed it further but didn't want to burn more credits. If anyone wants to explore it, you can check the prompts. GPT Image 2 Prompts Homepage UI: Create a 16:9 Netflix homepage UI with logo "KODAFLIX" shaped like the Netflix logo., featuring a main hero film with its title and still generated from the uploaded reference. Ensure all displayed movies and shows are completely original fictional titles with no real or existing IP used. Use "K" icon instead of "N". Login UI: Create a 16:9 Netflix login UI with the logo "KODAFLIX" shaped like the Netflix logo. Show 4 user profiles: Kōda, Alex, Fer, and Kids. Use uploaded references as profile pictures. Intro UI: Create a 16:9 cinematic Netflix-style logo intro, a bold red ribbon letter "K" forming from darkness. Seedance 2.0 Prompt in the replies.
0:15

GPT Image 2 + Seedance 2.0 I could've pushed it further but didn't want to burn more credits. If anyone wants to explore it, you can check the prompts. GPT Image 2 Prompts Homepage UI: Create a 16:9 Netflix homepage UI with logo "KODAFLIX" shaped like the Netflix logo., featuring a main hero film with its title and still generated from the uploaded reference. Ensure all displayed movies and shows are completely original fictional titles with no real or existing IP used. Use "K" icon instead of "N". Login UI: Create a 16:9 Netflix login UI with the logo "KODAFLIX" shaped like the Netflix logo. Show 4 user profiles: Kōda, Alex, Fer, and Kids. Use uploaded references as profile pictures. Intro UI: Create a 16:9 cinematic Netflix-style logo intro, a bold red ribbon letter "K" forming from darkness. Seedance 2.0 Prompt in the replies.

Kōda

21,157 görüntüleme • 1 ay önce