Alibaba is open-sourcing Wan2.1-VACE tonight (local time)! Judging by the teaser poster, it’s an all-in-one model for video creation and editing. Big news incoming!
MULTIMODAL AI
-
ByteDance DanceGRPO advances vision generation; Qwen3 tech report released
By
–
May 14 – Today’s Highlights (May 14) ByteDance applies GRPO to vision generation for the first time. The new DanceGRPO method enables faster convergence and higher visual fidelity. The code will be released. https://
arxiv.org/abs/2505.07818 Qwen3’s full tech report is out. -
Hugging Face Releases Comprehensive Vision-Language Models Guide
By
–
Hugging Face just dropped a comprehensive blog post on Vision-Language Models (VLMs) — covering architecture, training, benchmarks, and useful resources. A must-read if you're navigating the multimodal frontier! https://
huggingface.co/blog/vlms-2025 -
AI Designs Structurally Sound LEGO Models
By
–
New Lego-building #AI creates models that actually stand up in real life
-
Face-to-Many Animation with PixVerse Lip Sync and AI Voice
By
–
I haven't experimented much with voices and lip sync before.
— fofr (@fofrAI) 13 mai 2025
This is 0_1 put through face-to-many to make her ps2-like, then animated with PixVerse, lip synced with Tavus's Hummingbird and audio from Minimax speech-01-hd, and then captions added using an autocaption model. pic.twitter.com/ZVyj5RbHr1I haven't experimented much with voices and lip sync before. This is 0_1 put through face-to-many to make her ps2-like, then animated with PixVerse, lip synced with Tavus's Hummingbird and audio from Minimax speech-01-hd, and then captions added using an autocaption model.
-
PixVerse v4 Enables Frame Transitions for AI Video
By
–
You can do start and end frame transitions with PixVerse v4 on Replicate now.https://t.co/ZVyRigkcKc
— fofr (@fofrAI) 13 mai 2025
Here's an Arnie transformation pic.twitter.com/GTKCE3r10pYou can do start and end frame transitions with PixVerse v4 on Replicate now. https://
replicate.com/pixverse/pixve
rse-v4
… Here's an Arnie transformation -
Do We Hear Known Voices Reading Familiar Text?
By
–
When you read something written by someone you know, do you hear their voice reading the words?
-
Microsoft AI Hiring Data Engineers for Multimodal Datasets
By
–
If you’re a good data engineer, or an engineer who loves looking at data creating datasets for games, video, images, audio, text … please send me a message here or on LinkedIn. We still have plenty of data jobs at @MicrosoftAI – but hurry 😅 https://t.co/F5vrE3EbiJ
— Nando de Freitas (@NandoDF) 13 mai 2025If you’re a good data engineer, or an engineer who loves looking at data creating datasets for games, video, images, audio, text … please send me a message here or on LinkedIn. We still have plenty of data jobs at @MicrosoftAI – but hurry
-
Open-Source AI Image Editor ‘IceEdit’ Runs Locally and for Free
By
–
Une IA open source qui modifie les images mieux que Gemini ou GPT-4o ?
— VISION IA (@vision_ia) 13 mai 2025
IceEdit transforme n’importe quelle photo avec un simple prompt. Suppression d’objets, changement de style, d’éclairage, d’expressions… en 10 secondes.
Le plus fou ? Ça tourne en local. Gratuitement.… pic.twitter.com/WR2E5jObqLAn open-source AI that edits images better than Gemini or GPT-4o? IceEdit transforms any photo with a simple prompt. Object removal, style changes, lighting, expressions… in 10 seconds. The craziest part? It runs locally. For free. Explanations:
-
GPT-Image-1 Achieves 17% Market Share Two Weeks After API Launch
By
–
Image generation is becoming increasingly competitive as quality and adherence improve. OpenAI's GPT-Image-1 rapidly grew to 17% of usage in the two weeks after its API launch, mirroring the viral success in the ChatGPT app in March. (3/5)