ChatGPT has really good understanding of cheeseburgers and photography
MULTIMODAL AI
-
New 4o Image Model Applications Showcased Video
By
–
Just made a video with all the ways I could think of that people are using the new 4o Image model. Shared many many of your posts as well. Tons of people from this thread got shoutouts. 🙂
-
Using ChatGPT for Damaged Image Reconstruction
By
–
2/ A new use of ChatGPT’s image prompt powers is emerging: Lost Photo/Document Reconstruction You upload a damaged image. The AI revives it—with period-accurate style.
-
Retro Diffusion Core: Professional Pixel Art Image Generation Model
By
–
Now available: Retro Diffusion Core! This specialized image model creates professional-grade pixel art across across 15 style presets, including anime, game assets, and even animation frames. (1/3)
-
Vision AI at Edge for Security and Surveillance Applications
By
–
We’re live at #ISCWest2025!
Stop by Booth #33051 @ Venetian Expo to see vision AI at the edge in action. Demos Kits Real-time analytics Axelera AI team ready to chat
Let’s talk AI for security, surveillance & more. https://
eu1.hubs.ly/H0h-xjW0 -
Animated Short Film Generated Entirely with Gen-4
By
–
The Retrieval. An animated short generated entirely with Gen-4. pic.twitter.com/URWWJh4jTY
— Runway (@runwayml) 2 avril 2025The Retrieval. An animated short generated entirely with Gen-4.
-
Tinder Launches AI-Powered Speech Game for Flirting Practice
By
–
Tinder dropped "The Game Game," a speech-to-speech experience to help people practice flirting skills Users talk to OpenAI-powered personas, which offer immediate feedback on charm, engagement, and social awareness Only limited to 5 sessions daily!
-
Meta’s MoCha generates movie-grade character animations from speech text
By
–
Meta just announced MoCha, an AI model that produces movie-grade talking/singing character animations from speech and text
— Rowan Cheung (@rowancheung) 2 avril 2025
It even enables multi-character conversations with turn-based dialogue generationpic.twitter.com/roKR16uxI5Meta just announced MoCha, an AI model that produces movie-grade talking/singing character animations from speech and text It even enables multi-character conversations with turn-based dialogue generation
-
Agent S2: Compositional Generalist-Specialist Framework for Computer Use
By
–
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents Agashe et al.: https://
arxiv.org/abs/2504.00906 #ArtificialIntelligence #DeepLearning #MachineLearning