I'm back!

Interestingly, these are all new posters just for the bundle, albeit made out of existing assets. But cool and interesting they’d bother making semi unique posters for the bundles

The round 1 of World Puzzle Championship is starting in a few minutes* My incredibly optimistic goal is top20. *Actually tweeting this after the round so I already know that I had a terrible start 🥲

nano-strawberry incoming!!! 🍓

nano bananaでスタイル参照できた 参照したいスタイルの複数人画像と、キャラ画像を入れて、右端のキャラと入れ替えてくださいと言えば、こんな感じで似たスタイルにして入れ替えてくれる 絵柄によっては難しい場合があって、その時はキャラ画像にノイズとぼかしを加えるとうまくいく

Nano Bananaすごいな。適当に指示してもそれっぽいマンガを書いてくれる・・・ つまりちゃんと指示をすれば・・・

完全にNano Bananaのコツを掴んだ

My account @ChetasLua was suspended without any reason or explanation. I’ve appealed multiple times but received no reply. I requested a manual review, I’ve never promoted anything, spammed, or used derogatory language. Please restore my account. @nikitabier @airbreeze @AqueelMiq @_Andrew_Bean

nano banana experiment: > make this a how to draw example, with 4 progressive changes showing the development of the minimal sketch (no text)

nano banana experiment: > caption this image and wrap it around her portrait, the words follow the contour of her portrait Not bad, this is closer than I expected. Text rendering on unusual text orientation still problematic.

Once you learn how multi-shot prompting works, you can generate a mini-cartoon like this on the very first attempt - using only 1 image 👏👏

From the beginning, Flow has been a tool built by artists, for artists. In that spirit, we have some news: 1) Welcome @HenryDaubrez as our first filmmaker in residence who will work directly with our team to shape the future of Flow. 2) We're launching Flow Sessions, a pilot program that will provide mentorship and education for filmmakers on how they can best use Flow to bring their stories to life. Learn more: blog.google/technology/googl…

Today, my son said he wanted a cartoon about a "cat in a museum" so we made this 10-second cartoon using @0xFramer Cartoon Hero method. Feels like a Scooby-Doo episode opening.

I’ll be very busy for the next few weeks. To those who wanted a more detailed workflow tutorial for my 37-page nano-banana-assisted sample comic, I’m sorry I couldn’t put it together today. If I ever make it, it will be after these busy weeks.

From concept all the way through editing, around 12 hours over a few evenings.

I'm excited to share episode 1 of my latest animated short! "Steve Against the World" 😼 Meet Steve the cat. He’s refined. He’s judgmental. He uses a toilet. Inspired by the Cartoon Hero course by @0xFramer. Thanks to @HeyGen_Official for the amazing lip-sync model (Avatar IV). Learn how I made this short: 👇

From photo to figurine style in just one prompt. People are having fun turning their photos into images of custom miniature figures, thanks to nano-banana in Gemini. Try a pic of yourself, a cool nature shot, a family photo, or a shot of your pup. Here’s how to make your own 🧵

Gemini 2.5 Flash Image (Nano Banana) best practices 🍌🍌🍌 - Be hyper-specific: The more detail you provide, the more control you have. Instead of "fantasy armor," describe it "ornate elven plate armor, etched with silver leaf patterns, with a high collar and pauldrons shaped like falcon wings." - Fix character consistency drifts: If you notice a character's features begin to drift after many iterative edits, you can restart a new conversation with a detailed description to retain consistency. - Provide context and intent: Explain the *purpose* of the image. For example, "Create a logo for a high-end, minimalist skincare brand" will yield better results than just "Create a logo." - Iterate and refine: Don't expect a perfect image on the first try. Use the conversational nature of the model to make small changes. Follow up with prompts like, "That's great, but can you make the lighting a bit warmer?" or "Keep everything the same, but change the character's expression to be more serious." - Use "semantic negative prompts": Instead of saying "no cars," describe the desired scene positively, "an empty, deserted street with no signs of traffic." - Aspect ratios: When editing, Gemini 2.5 Flash Image generally preserves the input image's aspect ratio. If you upload multiple images with different aspect ratios, the model will adopt the aspect ratio of the *last* image provided. - Control the camera: Use photographic and cinematic language to control the composition. Terms like `wide-angle shot`, `macro shot`, `low-angle perspective`, `85mm portrait lens`, and `Dutch angle` give you precise control over the final image.

🍌 nano-banana just did something insane. On the very first try, Samurai Joker landed exactly in the sketch pose I attached 😱 Dynamic, cinematic, perfect. But here’s the truth: that layered, chaotic kimono only exists in my head… and even AI struggles to decode a mind as messy as mine 😅 So it improvised... dropped the top layers to make the pose crystal clear. Honestly? Kinda genius. Pose = flawless. Outfit = wild reinterpretation. And that’s the magic: control + surprise, the combo that keeps me hooked. 🚨 Full prompt below — go play with it ⤵️

gpt-image-1-high-fidelity just went live on the LMArena.