Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: Cinematic title card showing ‘IMAGES’ in bold white sans-serif text centered over a nighttime pastoral field under a vast starry sky, with a subtle rectangular constellation of brighter stars forming a frame shape in the distant background, deep navy sky with silver stars, moonlit grass in muted gold, widescreen composition, film poster aesthetic.
Had early access to nano banana pro, and, in addition to other gains, I found that with some prompting, it can do many of the things previous image models found impossible: glasses of wine filled to the brim, horses riding astronauts, et. https://x.com/emollick/status/1991527285267275854
I asked it to create a personalized weekly workout plan, and then posters that I can print on the wall to remind me what exercises to do each day. Tuesday looks more intense because I asked for “”more testosterone”” :D. (sorry I’ll stop posting more nano banana pro stuff now) https://x.com/karpathy/status/1992711182537707990
I think my “otters on a plane using WiFi” may be a saturated benchmark now that nano banana pro can do this. https://x.com/emollick/status/1991709695414006073
Learning how TPU’s work this weekend from Nano Banana Pro 🤯 https://x.com/OfficialLoganK/status/1992385461671862676
The new Nano Banana Pro makes all of Tennyson’s Ulysses into a comic on the first try when given the poem broken into four pieces. Eight months have passed since the quoted example. https://x.com/emollick/status/1992671393490878782
Using nano banana pro to explain the similarities and differences between photogrammetry and 3d gaussian splatting https://x.com/bilawalsidhu/status/1991659453524156656
Create an illustrated explainer, detailing the physics of the fluid dynamics that are caught in this image and what happens next. https://x.com/JeffDean/status/1991528053504405736
FLUX Playground – Black Forest Labs https://playground.bfl.ai/image/generate
FLUX.2: Frontier Visual Intelligence | Black Forest Labs https://bfl.ai/blog/flux-2
Overview – Black Forest Labs https://docs.bfl.ai/flux_2/flux2_overview
Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture”” TL;DR: Full Studio pipeline for 4D volumetric capture (GS); HD Scene capture + Face capture https://x.com/Almorgand/status/1993730815818154258
Turned my real world 360 images into 3d scenes with World Labs. You can use the built-in editing tools to stitch them together into large-scale 3d worlds – then use them as virtual set for your AI videos, games and VR experiences. The holodeck is much closer than you think. https://x.com/bilawalsidhu/status/1992703722473038259
Black Forest Labs – Frontier AI Lab https://bfl.ai/research/representation-comparison
Forget the Turing Test, AI now passes the Stroop test. (I’ll help, @grok whats the Stroop test and bow does it apply)”” / X https://x.com/emollick/status/1992687687304716750
RynnVLA-002 A Unified Vision-Language-Action and World Model https://x.com/_akhaliq/status/1992973969784213854
𝚁𝚢𝚗𝚗𝚅𝙻𝙰-𝟎𝟎𝟐 RynnVLA-002: a unified action world model that evolves RynnVLA-001 from “VLA and generative priors” into a fully joint Chameleon-based action-world framework, merging VLA policy and world model in one autoregressive transformer with shared token space for https://x.com/gm8xx8/status/1992910628172800412
We’re launching a new frontier physics eval on Artificial Analysis where no model achieves greater than 9%: CritPt (Complex Research using Integrated Thinking – Physics Test) Developed by 60+ researchers from 30+ institutions across the world including the Argonne National https://x.com/ArtificialAnlys/status/1991913465968222555
3d visual positioning experiment — look at the alignment between the 3d mesh and the live camera view. Truly feels magical — like x-ray vision. Workflow: 1. Scanned a street in 15 mins w/ xgrids 2. Localized against that scan at night, in real-time, while sitting in a car The https://x.com/bilawalsidhu/status/1993444825463701958
We’re now rolling out interactive images to the @GeminiApp for more visual and dynamic learning. It’s designed to help you visually explore complex academic concepts, turning studying from passive viewing into active exploration. Learn more → https://x.com/Google/status/1993453369965351284
. @NanoBanana show me what you think Gemini 3 looks like”” / X https://x.com/OfficialLoganK/status/1991963591617159222
A conversation with @koraykv (Google DeepMind CTO and Google’s Chief AI Architect) about how we are approaching building AGI, the Gemini 3 launch, Nano Banana Pro, and a year of rapid AI progress. https://x.com/OfficialLoganK/status/1993150466071703760
A conversation with @sundarpichai about Gemini 3, Nano Banana Pro, and Google’s full stack AI strategy playing out over the last 10 years https://x.com/OfficialLoganK/status/1993464111397781906
A curated collection of the best Nano Banana prompts, image generation styles, and resources for advanced AI visual experiments. https://x.com/_philschmid/status/1993650772240941106
Gemini Nano Banana Pro can solve exam questions *in* the exam page image. With doodles, diagrams, all that. ChatGPT thinks these solutions are all correct except Se_2P_2 should be “”diselenium diphosphide”” and a spelling mistake (should be “”thiocyanic acid”” not “”thoicyanic””) :O https://x.com/karpathy/status/1992655330002817095
Google back-to-back with the one-two punch! Nano Banana Pro lived up to the hype. Thanks to Google for the early access. Stay tuned for my full video review. https://x.com/bilawalsidhu/status/1991533844319859089
How to Create an Effective Prompt for Nano Banana Pro https://www.radicalcuriosity.xyz/p/how-to-create-an-effective-prompt
ICYMI: Last week we started rolling out our all-new state-of-the-art image generation and editing model, Nano Banana Pro. See how it’s taking visuals to the next level 🧵”” / X https://x.com/GeminiApp/status/1993363771121967452
Introducing Nano Banana Pro 🍌 aka Gemini 3 Pro Image, our new SOTA image generation and editing model. It is all the things you loved about @NanoBanana, but with some wild new improvements. It is available right now for developers in the Gemini API and in the Gemini App!”” / X https://x.com/OfficialLoganK/status/1991539339357216917
Is this the Google PM behind the name Nano Banana — any guesses on what’s dropping soon? :)”” / X https://x.com/bilawalsidhu/status/1991388938339250477
Nano Banana Pro can help you visualize any idea, from representing data as infographics, to turning handwritten notes into diagrams. https://x.com/Google/status/1993087643224064371
Nano Banana Pro demos, showcases, and vibes, live from Mountain view 🍌 https://x.com/OfficialLoganK/status/1991581564237725969
Nano Banana Pro is a really good cartographer. Used it to turn low res satellite imagery into a detailed hand drawn map and vector HD map. Pretty wild how well it segments everything and even recovers paths/roads hidden under tree cover. Looks way more detailed than the https://x.com/bilawalsidhu/status/1991635734546284703
Nano banana Pro: “i need a flowchart for how to toast bread, make it as wacky and over the top and complicated as possible.” Not absolutely perfect, but I can’t believe how much there is a coherent through-line, how clear the text is, and also parts of it are actually funny? https://x.com/emollick/status/1991549167773376978
Nano Banana Pro: raw intelligence with tool use – Quesma Blog https://quesma.com/blog/nano-banana-pro-intelligence-with-tools/
Nano Banana-pilled, Nano Banana-shilled for Spaceship Engineering — Angadh Nanjangud https://angadh.com/inkhaven-23
Non-natural image gen and editing are difficult tasks. We tested the state of the art at the time — including Nano Banana 1.0 & GPT-image — all performed quite poorly on StructBench. Nano Banana 2 (NB2) just dropped, and its improvements strongly validate a direction we studied https://x.com/RisingSayak/status/1993662000103371136
Now that Gemini 3 beats human geoguessers, I have a new challenge for locations, the nano banana pro prompt “Magic card various things in this scene.” https://x.com/emollick/status/1991943113481609724
Now you can edit and reimagine any photo right in Google Messages with Remix. 🍌 Remix, rolling out this month, uses our Nano Banana Gemini image model to help you do everything from redesigning rooms to turning puppies into action figures. Just long-press a photo in your chat to https://x.com/Google/status/1993371869634818049
Pretty cool. Ariel Noyman at MIT Media Lab adapted my Nano Banana Pro prompts to map “”urban informality”” — complex settlements that are notoriously difficult to map manually. “”What used to take hours (days) of manual work can now be distilled into minutes, with results that are https://x.com/bilawalsidhu/status/1991924158339658192
PSA: our team is online 24/7 helping customers scale with Gemini 3 Pro and Nano Banana Pro, please let us know what you need (including higher API rate limits)! My email is Lkilpatrick@google.com”” / X https://x.com/OfficialLoganK/status/1992049541617463620
Ruining great art with the nano banana pro command “Make this much more cheerful with as few changes as possible” https://x.com/emollick/status/1991701248630985161
The real implication from nano banana pro is its the first AI imagen to cross from toy/artist use to useful to all. A non-experienced user can get a good PowerPoint slide explanation, illustration for a document, or infographic with a first prompt or a round or two of feedback.”” / X https://x.com/emollick/status/1991554762828050745
When you lay out lots of items in a precise arrangement for a photo, it’s called knolling. You can make accurate and detailed pictures like these using Nano Banana Pro. Prompt: A knolling for Google DeepMind https://x.com/NanoBanana/status/1993311207714177251
Google’s new Nano Banana Pro (Gemini 3 Pro Image) model is the new #1 Image Generation and Image Editing model in the Artificial Analysis Image Arena! Google’s Nano Banana Pro improves performance over Nano Banana but will not be a replacement for all users given its premium https://x.com/ArtificialAnlys/status/1993032471274024970
Birth of a Painting: Differentiable Brushstroke Reconstruction”” TL;DR: differentiable stroke reconstruction framework that unifies painting, stylized texturing, and smudging to faithfully reproduce the human painting-smudging loop. (1/2) https://x.com/Almorgand/status/1991542123120980102
pages from a home decor magazine from a world where adding giant googly eyes to anything is considered the height of fashion”” https://x.com/emollick/status/1993570245781733575
This was repeatable for me (though I asked for an illuminated manuscript as an answer). Surprising! Still can’t do a maze though. https://x.com/emollick/status/1992712854005580259
black-forest-labs/FLUX.2-dev · Hugging Face https://huggingface.co/black-forest-labs/FLUX.2-dev
🎨 Introducing FLUX.2 from Black Forest Labs, a production-grade image generation model with multi-reference consistency and brand-exact color matching. AI natives can now use FLUX.2 on Together AI and benefit from reliable inference for production-scale visual content creation. https://x.com/togethercompute/status/1993464539871060400
black-forest-labs/flux2: Official inference repo for FLUX.2 models https://github.com/black-forest-labs/flux2
Check out @bfl_ml’s deep dive on the rate-distortion-modelability trade-off in diffusion latent space design. I previously discussed this in my blog post on latents. Here’s amazing practical demonstration, taken directly from the development of FLUX.2! https://x.com/sedielem/status/1993392284180865312
Diffusers welcomes FLUX-2 https://huggingface.co/blog/flux-2
fal/FLUX.2-Tiny-AutoEncoder · Hugging Face https://huggingface.co/fal/FLUX.2-Tiny-AutoEncoder
Flux.1-dev has been the second most liked model on Hugging Face just after Deepseek R1 so super excited to see the release of Flux.2-dev by @bfl_ml today! Download the weights or try the model (thanks to @fal) on @huggingface: https://x.com/huggingface/status/1993416469531836527
FLUX.2 image generation just dropped in Synthesia. 💥 From infographics to realistic images to wild abstract art — it’s all one text prompt away. Available now on all plans. https://x.com/synthesiaIO/status/1993364380629475655
FLUX.2 is available on Replicate. Multi-reference editing, complex typography, stunning detail up to 4MP. Available in 3 variants: FLUX.2 [pro] (original FLUX.2): https://x.com/replicate/status/1993345980784427029
FLUX.2 is here – our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weights. Into the new. https://x.com/bfl_ml/status/1993345470945804563
FLUX.2 is out, and AI Toolkit has day zero support for both text to image and editing.”” / X https://x.com/ostrisai/status/1993348832944697581
FLUX.2 is out! 🚨 FLUX.2-dev bing state-of-the-art to open weight, with a chonky 32B parameter model, however, it can run on low-end cards with quantization and the new remote text encoder Read more on the 🧨 diffusers welcomes FLUX-2 blog https://x.com/multimodalart/status/1993349396482998691
FLUX.2 just landed in LTX. We’re proud to be official launch partners with @bfl_ml FLUX.2 is built for production with speed, precision, and photorealism. Here’s what makes it different 🧵 https://x.com/LTXStudio/status/1993354049367031956
FLUX.2 Pro image model is now available on Vercel AI Gateway – Vercel https://vercel.com/changelog/flux-2-pro-image-model-is-now-available-on-vercel-ai-gateway
FLUX.2 Pro is now available on Vercel AI Gateway. • Text-to-image model designed for richer visualization and photo-quality detail generation • Set model to 𝚋𝚏𝚕/𝚏𝚕𝚞𝚡-𝟸-𝚙𝚛𝚘 https://x.com/vercel_dev/status/1993348429653930260
How to Train a FLUX.2 LoRA with AI Toolkit. In this tutorial I show you how to train a style LoRA for FLUX.2 that can be used in both text to image and image editing tasks. AI Toolkit has day 0 support for training @bfl_ml FLUX.2 LoRAs. Links in 🧵 https://x.com/ostrisai/status/1993360008218825185
Introducing Unlimited FLUX.2 Pro Multiple reference characters, sharper realism, smarter controls, and higher resolution More info below 👇 https://x.com/freepik/status/1993346586446119032
Prompting Guide – FLUX.2 – Black Forest Labs https://docs.bfl.ai/guides/prompting_guide_flux2
We have just open sourced the ‘Tiny Autoencoder’ for FLUX.2 [dev] that lets us stream intermediary outputs when generating images. This means you won’t have to deal with pesky progress bars anymore. https://x.com/fal/status/1993669462550323652
Vibe coded this JARVIS inspired HUD with laser eyes and repulsor hands in 20 mins w/ Gemini 3 Pro using MediaPipe and ThreeJS. Augmented reality filters were always cool – but vibe coding makes them so much more accessible than complex AR authoring tools of the past. https://x.com/bilawalsidhu/status/1993025326520451475
🤯 Z-Image-Turbo: Open-source extremely fast 6B Single-Stream Diffusion model that runs on a single GPU, delivers photorealistic + text-accurate images. ⬇️ Now available on Hugging Face (gen time = < 3 sec) https://x.com/victormustar/status/1993794840514162814
Remember all the line of works mega-focused on using activations of imagenet-pretrained model to converge better on imagenet? Remember when I told you there is no way thats going to scale beyond imagenet / other domains? Im glad BFL shared this result with the world https://x.com/cloneofsimo/status/1993371224140054873
This model is called Z-image, Apache2.0 licensed. 6B size, Coming soon.🫡 https://x.com/bdsqlsz/status/1993545608179990544
Leave a Reply