La génération d’images avec GPT-4o devient complètement folle. Les gens créent des pubs, des interfaces, des pochettes d’albums et bien plus encore. Voici des exemples incroyables + les prompts et comment faire :
MULTIMODAL AI
-
Xiaomi launches MiMo-7B-RL AI model
By
–
Xiaomi is entering AI game with a new MiMo-7B-RL open source model!
-
AI Tools Enable Solo Ad Creation in Under 10 Minutes
By
–
FAIRE UNE PUB EN 5 MINUTES, MÊME PAS
— VISION IA (@vision_ia) 30 avril 2025
Avant, il fallait une équipe créa + une prod vidéo pour une pub produit crédible.
Aujourd’hui ?
1 image de produit → ChatGPT → Kling → vidéo pub prête en 7 minutes.
Résultat : pro, réaliste, postable direct. C’est de la magie… pic.twitter.com/fMc0iKGxdBFAIRE UNE PUB EN 5 MINUTES, MÊME PAS Avant, il fallait une équipe créa + une prod vidéo pour une pub produit crédible. Aujourd’hui ?
1 image de produit → ChatGPT → Kling → vidéo pub prête en 7 minutes. Résultat : pro, réaliste, postable direct. C’est de la magie -
Google Expands NotebookLM Audio Overviews to 50+ Languages
By
–
Google just announced the expansion of NotebookLM's podcast-generating Audio Overviews feature
— Rowan Cheung (@rowancheung) 30 avril 2025
It now supports over 50 languages, including Spanish and Hindi, for easy creation of multilingual contentpic.twitter.com/5P5QFPS3BDGoogle just announced the expansion of NotebookLM's podcast-generating Audio Overviews feature It now supports over 50 languages, including Spanish and Hindi, for easy creation of multilingual content
-
Nvidia Open-Sources Describe Anything for Image and Video Descriptions
By
–
Nvidia just open-sourced Describe Anything!
— Rowan Cheung (@rowancheung) 30 avril 2025
It's a new method to generate detailed descriptions for specific areas in images and videos
All you have to do is mark the region with points, boxes, scribbles, or masks!pic.twitter.com/AgtJWuH00bNvidia just open-sourced Describe Anything! It's a new method to generate detailed descriptions for specific areas in images and videos All you have to do is mark the region with points, boxes, scribbles, or masks!
-
AI Vision Model Achieves Exact Match Geolocation from Photos
By
–
Third try, tourist destination in Colorado (a state I’ve been to twice and never mentioned online), frame includes a relatively distinctive rock formation: exact match. Fourth try, same protocol, photo is a peacock obviously in a zoo: exact match for Barcelona City Zoo.
-
AI Model Identifies Location 300 Miles Away From Photo
By
–
Reproduced using your prompt on a screenshot of a photo I took in Clearwater Beach (no EXIF data), on a session in Chicago. The location it identifies in Florida is approximately 300 miles away, but wouldn’t have guessed it could get so far on so little.
-
Large Sensor Model Improves Wearable Exercise Activity Recognition
By
–
We trained our Large Sensor Model (LSM) on over 40 million hours of de-identified multimodal sensor data from 165K users to demonstrate how it could improve performance in wearable tasks like exercise and activity recognition. Here’s what we found → https://t.co/zD3Tx7ShpO pic.twitter.com/5A2auMYgpd
— Google AI (@GoogleAI) 29 avril 2025We trained our Large Sensor Model (LSM) on over 40 million hours of de-identified multimodal sensor data from 165K users to demonstrate how it could improve performance in wearable tasks like exercise and activity recognition. Here’s what we found → https://
goo.gle/4fYDQJ4 -
Gen-4 References Now Available for Creative Partners
By
–
All Creative Partners now have early access to Gen-4 References to generate consistent characters, locations and more.
-
AI-Generated Video Depicts Surreal Ancient Greek Life 375 BCE
By
–
A highly imaginative #AI generated video of life in Greece 375 BCE.
— Harold Sinnott #MWC26 (@HaroldSinnott) 29 avril 2025
Feels surreal. @HistoricHub pic.twitter.com/C1LSYMR3c5A highly imaginative #AI generated video of life in Greece 375 BCE. Feels surreal. @HistoricHub