This week, we’re sharing the moodboard that guided the look and feel of our latest Stable 4D 2.0 release. We began by developing a visual style we call Gallery Gloss, inspired by soft plastics, collectible toy design, and characters posed in clear display cases. We formed
MULTIMODAL AI
-
AI Video Generation: Indistinguishable Reality in 2025
By
–
Que me estéis preguntando si este vídeo es real o está generado con IA es la mejor prueba de lo fuerte que va la IA en 2025. En ambos casos la respuesta es impresionante.
— Carlos Santana (@DotCSV) 26 mai 2025
PD: Es real… ¿o no? 😏 https://t.co/YBwaIq4cOlQue me estéis preguntando si este vídeo es real o está generado con IA es la mejor prueba de lo fuerte que va la IA en 2025. En ambos casos la respuesta es impresionante. PD: Es real… ¿o no?
-
Imagen 4 Masters Retro Family Photo Style Generation
By
–
Imagen 4 can do the "old family photos" style pretty well: > aggressively mediocre, scanned vacation photo in northern Spain mountains, 1984, giant sculpture of the alien god embedded into mountain, family photo
-
Apple Plans AI Smart Glasses Launch for 2026
By
–
APPLE PRÉPARE DES LUNETTES À IA POUR 2026 La prochaine grande révolution d’Apple ? Des lunettes intelligentes. Avec de l’IA, des caméras, des micros, des haut-parleurs — en gros, si Siri et votre iPhone avaient un bébé… qui vous colle au visage. Leur lancement est prévu pour
-
WonderPlay: AI-Powered 3D Scene Generation from Images
By
–
WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
Paper: https://
arxiv.org/pdf/2505.18151
v1.pdf
…
Project Page：
https://
kyleleey.github.io/WonderPlay/
Code：
https://
github.com/kyleleey/Wonde
rPlay
… （coming soon) -
WonderPlay Transforms Static Images Into Dynamic 3D Scenes
By
–
WonderPlay is a new framework that turns a single image into a dynamic 3D scene, combining physics simulation with video generation. Unlike past works stuck with rigid or simple elastic motions, WonderPlay supports everything from cloth to snow, liquids to smoke —all… pic.twitter.com/9juDq4nG2E
— 机器之心 JIQIZHIXIN (@jiqizhixin) 26 mai 2025WonderPlay is a new framework that turns a single image into a dynamic 3D scene, combining physics simulation with video generation. Unlike past works stuck with rigid or simple elastic motions, WonderPlay supports everything from cloth to snow, liquids to smoke —all
-
How to turn selfies into custom LEGO mini-figures with ChatGPT
By
–
People are using ChatGPT to turn any selfie into a custom LEGO mini-figure for free. Here's how you can do it for free:
-
Crystal Ball Prompt for ChatGPT Image Generation Scenes
By
–
Très beau prompt pour chatgpt : Prompt :
Une boule de cristal [TYPE] posée sur une corniche en pierre, reflétant une image inversée de [INSÉRER UN MONUMENT OU UNE SCÈNE], tandis que le véritable [INSÉRER MONUMENT OU SCÈNE] apparaît en arrière-plan avec un léger flou.
La boule de -
Gemma 3n E4B: Lightweight Multimodal AI Model
By
–
And ofc, there is a recently added Gemma 3n E4B. A SOTA, lightweight, open-source multimodal AI model, designed for efficient execution on low-resource devices.
-
Veo 3 Struggles with Split-Screen Foley Artist Prompt
By
–
This was a prompt idea from @steveruizok, but I don't think it's one that Veo 3 can get right, this was the closest:
— fofr (@fofrAI) 25 mai 2025
> a video is split 50/50, on the left is a scene, on the right is a foley artist producing the sound effects for that scene pic.twitter.com/Sx4kTFbePwThis was a prompt idea from @steveruizok
, but I don't think it's one that Veo 3 can get right, this was the closest: > a video is split 50/50, on the left is a scene, on the right is a foley artist producing the sound effects for that scene