Pico-Banana-400k

From the paper

> The pipeline (bottom) shows how diverse OpenImages inputs are edited using Nano-Banana and quality-filtered by Gemini-2.5-Pro, with failed attempts automatically retried.

Pretty interesting. I run a fairly comprehensive image-comparison site for SOTA generative AI in text-to-image and editing. Managing it manually got pretty tiring, so a while back I put together a small program that takes a given starting prompt, a list of GenAI models, and a max number of retries which does something similar.

It generates and evaluates images using a separate multimodal AI, and then rewrites failed prompts automatically repeating up to a set limit.

It's not perfect (nine pointed star example in particular) - but often times the "recognition aspect of a multimodal model" is superior to its generative capabilities so you can run it in a sort of REPL until you get the desired outcome.

https://genai-showdown.specr.net/image-editing

The license is CC BY-NC-ND - I’m not sure who is going to be able to use it given the NC-ND part… especially given the potential uncertainty over what uses count as commercial and what counts as derivative works. OTOH, given the bulk of this dataset is AI outputs, its copyrightability is an open question.

Can it be? Has Apple FINALLY joined the party? Very ironic they are using an open dataset from Google... and Gemini for prompts by Google.

I'm happy to see something from Apple but this seems so low-tech that it could be one of my own local ComfyUI workflows.

I confess that I don't quite get the point here - is it just that they've paid the inference costs for a dataset than can be used for distillation/other research?

Looks like the dataset is distilled from Gemini nano-banana

Definitely very useful, but I’m so curious how the original datasets from these image editing models were created. I’m guessing a lot of it is synthetic data to construct scenes programmatically with layers

Maybe it is only me, but all the emojis in the readme look like AI wrote it and instantly make stop reading it ...

Any idea why they didn't use GPT-4o image generation?

[flagged]

Really cool - looking to Apple to lead the on-device AI space in short order...

Relevant from Randall Munroe https://what-if.xkcd.com/29/

> What if I took a swim in a typical spent nuclear fuel pool? Would I need to dive to actually experience a fatal amount of radiation? How long could I stay safely at the surface?

> Assuming you’re a reasonably good swimmer, you could probably survive treading water anywhere from 10 to 40 hours. At that point, you would black out from fatigue and drown. This is also true for a pool without nuclear fuel in the bottom.

Ok, but why did they call the model Micro-Penis-400k?