gemimg

That result for rendering HTML to an image (the Counter Info one) is pretty impressive. https://github.com/minimaxir/gemimg/blob/main/docs/files/cou... to this: https://x.com/minimaxir/status/1991580127587921971 - see also https://minimaxir.com/2025/11/nano-banana-prompts/#image-pro...

I...worked on the detailed Nano Banana prompt engineering analysis for months (https://news.ycombinator.com/item?id=45917875)...and...Google just...Google released a new version. Nano Banana Pro should work with my gemimg package (https://github.com/minimaxir/gemimg) without pushing a new version by passing: g = GemImg(model="gemini-3-pro-image-preview") I'll add the new output resolutions and other features ASAP. However, looking at the pricing (https://ai.google.dev/gemini-api/docs/pricing#standard_1), I'm definitely not changing the default model to Pro as $0.13 per 1k/2k output will make it a tougher sell. EDIT: Something interesting in the docs: https://ai.google.dev/gemini-api/docs/image-generation#think... > The model generates up to two interim images to test composition and logic. The last image within Thinking is also the f

I like the Python library that accompanies this: https://github.com/minimaxir/gemimg I added a CLI to it (using Gemini CLI) and submitted a PR, you can run that like so: GEMINI_API_KEY="..." \ uv run --with https://github.com/minimaxir/gemimg/archive/d6b9d5bbefa1e2ffc3b09086bc0a3ad70ca4ef… \ python -m gemimg "a racoon holding a hand written sign that says I love trash" Result in this comment: https://github.com/minimaxir/gemimg/pull/7#issuecomment-3529...

Everyone is sleeping on Gemini 2.5 Flash Image / Nano Banana. As shown in the OP, it's substantially more powerful than most other models while at the same price-per-image, and due to its text encoder it can handle significantly larger and more nuanced prompts to get exactly what you want. I open-sourced a Python package for generating from it with examples (https://github.com/minimaxir/gemimg) and am currently working on a blog post with even more representative examples. Google also allows generations for free with aspect ratio control in AI Studio: https://aistudio.google.com/prompts/new_chat That said, I am surprised Seedream 4.0 beat it in these tests.

I recently released a Python package for easily generating images with Nano Banana: https://github.com/minimaxir/gemimg Through that testing, there is one prompt engineering trend that was consistent but controversial: both a) LLM-style prompt engineering with with Markdown-formated lists and b) old-school AI image style quality syntatic sugar such as award-winning and DSLR camera are both extremely effective with Gemini 2.5 Flash Image, due to its text encoder and larger training dataset which can now more accurately discriminate which specific image traits are present in an award-winning image and what traits aren't. I've tried generations both with and without those tricks and the tricks definitely have an impact. Google's developer documentation encourages the latter. However, taking advantage of the 32k context window (compared to 51

Google's Gemini API is a little more difficult to work with, so I wrote a lightweight wrapper around it to make it easier to generate/edit images programmatically with Nano Banana/Gemini 2.5 Flash Image. I also included a number of Notebook examples and some observations on how the model works.