Nano banana pro is okay-ish. Struggles with facial identity when given a single image but great for celeb faces.
MULTIMODAL AI
-
SAM 3 Unifies Detection and Tracking in Vision Models
By
–
SAM 3 tackles a challenging problem in vision: unifying a model architecture for detection and tracking. Christoph, a researcher on SAM 3, shares how the team made it possible.
— AI at Meta (@AIatMeta) 20 novembre 2025
🔗 Read the SAM 3 research paper: https://t.co/6b7VkmKr9k pic.twitter.com/U5br0vGehoSAM 3 tackles a challenging problem in vision: unifying a model architecture for detection and tracking. Christoph, a researcher on SAM 3, shares how the team made it possible. Read the SAM 3 research paper: https://
go.meta.me/6411f7 -
Nano Banana Pro: Google’s Image Generation Model on Replicate
By
–
Meet Nano Banana Pro, on Replicate Google's SOTA image generation and editing model. It has better world knowledge, text rendering, and precision controls. Plus 4K outputs.
-
Nano Banana Pro: Gemini 3-based AI generates accurate life infographics
By
–
Nano banana pro (built on Gemini 3) is out! I asked it to generate an infographic of my life and it did so wildly accurately! Mind blowing! Huge congrats to @m__dehghani and the team!
-
Papers With Code SOTA Returns with Gemini 3 AI Research
By
–
Papers With Code SOTA is back 🚀
— alphaXiv (@askalphaxiv) 20 novembre 2025
We used Gemini 3 to process millions of charts and tables across arXiv + the web to surface state-of-the-art AI research in reasoning, computer-use, OCR, and more
Track the best-performing methods and see which benchmarks are getting adopted pic.twitter.com/9yKJXL35K7Papers With Code SOTA is back We used Gemini 3 to process millions of charts and tables across arXiv + the web to surface state-of-the-art AI research in reasoning, computer-use, OCR, and more Track the best-performing methods and see which benchmarks are getting adopted
-
Gemini Now Verifies SynthID Watermarks on AI-Generated Images
By
–
You can also now check for SynthID watermarking directly in the @GeminiApp and verify if an image was made by our models – just upload the image and ask Gemini. Being able to verify what you’re seeing is critical for building AI responsibly. pic.twitter.com/Oj3SeARhKm
— Demis Hassabis (@demishassabis) 20 novembre 2025You can also now check for SynthID watermarking directly in the @GeminiApp and verify if an image was made by our models – just upload the image and ask Gemini. Being able to verify what you’re seeing is critical for building AI responsibly.
-
Nano Banana Pro Launches Studio-Quality Image Generation Model
By
–
Rolling out today we are launching Nano Banana Pro, the world’s best image model built to move beyond casual creation and into a new era of studio-quality, functional design. Nano Banana Pro enables a new level of precision and creative control, transforming the way you bring
-
AI Inbox revolutionizes email management with natural language and voice
By
–
First up: AI Inbox just dropped and it's insane.
— God of Prompt (@godofprompt) 20 novembre 2025
Manage your entire email with natural language through text OR voice.
Drowning in 500 unread emails? AI Inbox auto-summarizes, drafts replies, and even converts emails into slides.
Watch this 👇 pic.twitter.com/RV1QQn89qGFirst up: AI Inbox just dropped and it's insane. Manage your entire email with natural language through text OR voice. Drowning in 500 unread emails? AI Inbox auto-summarizes, drafts replies, and even converts emails into slides. Watch this
-
Visual Data Generator: Prompt for Viral Chart
By
–
—
10. The "Visual Data" Generator Grok 4.1 is multimodal (can understand and generate image ideas). Prompt: "I want to post a viral chart or visualization about [INSERT TOPIC]. Look at the data on this topic. If you were to create a simple, hand-drawn style chart on a napkin
— -
Google Releases Gemini 3 Pro Image Preview Free
By
–
https://
zenmux.ai/google/gemini-
3-pro-image-preview-free
…