/
Navigation
C
Chronicles
Browse all articles
C
E
Explore
Semantic exploration
E
R
Research
Entity momentum
R
N
Nexus
Correlations & relationships
N
~
Story Arc
Topic evolution
S
↻
Drift Map
Semantic trajectory animation
D
P
Posts
Analysis & commentary
P
Browse
@
Entities
Companies, people, products, technologies
◇
Domains
Browse by publication source
☉
Handles
Browse by social media handle
Detection
?
Concept Search
Semantic similarity search
!
High Impact Stories
Top coverage by position
+
Sentiment Analysis
Positive/negative coverage
*
Anomaly Detection
Unusual coverage patterns
Analysis
vs
Rivalry Report
Compare two entities head-to-head
/\
Semantic Pivots
Narrative discontinuities
!!
Crisis Response
Event recovery patterns
Connected
Nav: C E R N
Search: /
Command: ⌘K
Embeddings: large
VOICE ARCHIVE

@fofrai

@fofrai
13 posts
2026-02-27
Nano Banana 2 🍌 is here. It's my new favorite model. Outputs are naturally more vibrant, constrasty and interesting compared with Nano Banana Pro. Side-by-side comparisons in the thread. Use with “gemini-3.1-flash-image-preview” in the API, or in @GeminiApp. [image]
2026-02-27 View on X
The Keyword

Google rolls out Nano Banana 2, aka Gemini 3.1 Flash Image, with faster image generation, advanced world knowledge, and precision text rendering and translation

Our latest image generation model offers advanced world knowledge, production-ready specs, subject consistency and more, all at Flash speed.

View original
2026-02-26
Nano Banana 2 🍌 is here. It's my new favorite model. Outputs are naturally more vibrant, constrasty and interesting compared with Nano Banana Pro. Side-by-side comparisons in the thread. Use with “gemini-3.1-flash-image-preview” in the API, or in @GeminiApp. [image]
2026-02-26 View on X
The Keyword

Google rolls out Nano Banana 2, aka Gemini 3.1 Flash Image, with faster image generation, advanced world knowledge, and precision text rendering and translation

Our latest image generation model offers advanced world knowledge, production-ready specs, subject consistency and more, all at Flash speed.

View original
2025-11-21
It's also pretty good at orientation. > The text “nano banana pro” written in every orientation, include a mirror [image]
2025-11-21 View on X
9to5Google

Google launches Gemini 3 Pro Image, aka Nano Banana Pro, with more control, improved text rendering, and enhanced world knowledge, for free in the Gemini app

except when it gaslit me Ryan Whitwam / Ars Technica : Google's new Nano Banana Pro uses Gemini 3 power to generate more realistic AI images Robert Hart / The Verge : Google's new ...

View original
The consistency and depth of understanding in Nano Banana Pro is good enough to turn it into a little video model. > Sprite sheet of [thing], 3x3 grid, white background, sequence, frame by frame animation, square aspect ratio. Follow the structure of the attached reference image [image]
2025-11-21 View on X
9to5Google

Google launches Gemini 3 Pro Image, aka Nano Banana Pro, with more control, improved text rendering, and enhanced world knowledge, for free in the Gemini app

except when it gaslit me Ryan Whitwam / Ars Technica : Google's new Nano Banana Pro uses Gemini 3 power to generate more realistic AI images Robert Hart / The Verge : Google's new ...

View original
To say Nano Banana Pro is good at text is an understatement. Here's the Gemini 3 blog post, as a glossy magazine article. > Put this whole text, verbatim, into a photo of a glossy magazine article on a desk, with photos, beautiful typography design, pull quotes and brave [image]
2025-11-21 View on X
9to5Google

Google launches Gemini 3 Pro Image, aka Nano Banana Pro, with more control, improved text rendering, and enhanced world knowledge, for free in the Gemini app

except when it gaslit me Ryan Whitwam / Ars Technica : Google's new Nano Banana Pro uses Gemini 3 power to generate more realistic AI images Robert Hart / The Verge : Google's new ...

View original
> Make it lego Nano Banana Pro generates recognisable lego pieces. It's a small detail, but it shows the depth of understanding. [image]
2025-11-21 View on X
9to5Google

Google launches Gemini 3 Pro Image, aka Nano Banana Pro, with more control, improved text rendering, and enhanced world knowledge, for free in the Gemini app

except when it gaslit me Ryan Whitwam / Ars Technica : Google's new Nano Banana Pro uses Gemini 3 power to generate more realistic AI images Robert Hart / The Verge : Google's new ...

View original
2025-11-20
> Make it lego Nano Banana Pro generates recognisable lego pieces. It's a small detail, but it shows the depth of understanding. [image]
2025-11-20 View on X
9to5Google

Google launches Gemini 3 Pro Image, aka Nano Banana Pro, with more control, improved text rendering, and enhanced world knowledge, for free in the Gemini app

Google is following Tuesday's launch of Gemini 3 Pro with Nano Banana Pro.  The image generation and editing model …

View original
The consistency and depth of understanding in Nano Banana Pro is good enough to turn it into a little video model. > Sprite sheet of [thing], 3x3 grid, white background, sequence, frame by frame animation, square aspect ratio. Follow the structure of the attached reference image [image]
2025-11-20 View on X
9to5Google

Google launches Gemini 3 Pro Image, aka Nano Banana Pro, with more control, improved text rendering, and enhanced world knowledge, for free in the Gemini app

Google is following Tuesday's launch of Gemini 3 Pro with Nano Banana Pro.  The image generation and editing model …

View original
To say Nano Banana Pro is good at text is an understatement. Here's the Gemini 3 blog post, as a glossy magazine article. > Put this whole text, verbatim, into a photo of a glossy magazine article on a desk, with photos, beautiful typography design, pull quotes and brave [image]
2025-11-20 View on X
9to5Google

Google launches Gemini 3 Pro Image, aka Nano Banana Pro, with more control, improved text rendering, and enhanced world knowledge, for free in the Gemini app

Google is following Tuesday's launch of Gemini 3 Pro with Nano Banana Pro.  The image generation and editing model …

View original
2025-08-20
> Make a fashion magazine cover with a woman posing in a red dress, the title of the magazine is Qwen Image Edit, no other text [image]
2025-08-20 View on X
VentureBeat

Alibaba releases Qwen-Image-Edit, the image editing version of Qwen-Image, supporting modifying Chinese and English text while preserving font, size, and style

Carl Franzen / VentureBeat :

View original
Wow. This is has historically been a really hard one for image editing models to get right. > Add a photo of a woman standing in front of “Qwen” text but behind “Image Edit” text, in a stylish design [image]
2025-08-20 View on X
VentureBeat

Alibaba releases Qwen-Image-Edit, the image editing version of Qwen-Image, supporting modifying Chinese and English text while preserving font, size, and style

Carl Franzen / VentureBeat :

View original
2025-05-21
My first Veo 3 gen > a video with dialogue of two muffins while baking in an over, the first muffin says “I can't believe this Veo 3 thing can do dialogue now!”, the second muffin says “AAAAH, a talking muffin!” [video]
2025-05-21 View on X
CNBC

Google announces new video and image generation models Veo 3 and Imagen 4, new AI filmmaking tool Flow, and expanded access to music generation model Lyria 2

Google on Tuesday announced Veo 3, an AI video generator that can also create and incorporate audio.

View original
2024-06-13
SD3 medium weights have landed https://huggingface.co/... With Comfy workflows. Update your ComfyUI first! [image]
2024-06-13 View on X
VentureBeat

Stability AI releases Stable Diffusion 3 Medium, intended to be a smaller yet capable model on consumer GPUs, with 2B parameters, compared to SD3 Large's 8B

View original