I think you can guess that part. I doubt a current LLM can create a valid PNG, even if it’s just a 1x1px one that has been created before. This is partially because PNGs have a checksum and the LLM has definitely not seen enough PNGs in base64 to figure out the algorithm, and is not optimized to calculate checksums. Also, it gets penalized for repetition, which occurs a lot in image headers.
AFAIK, the smallest valid image you see mentioned on the web is a 35-byte transparent pixel GIF, and the smallest PNG is a black pixel with 67 bytes:
did it give you the images in base64 from an llm, or from an image generation model ?
I think you can guess that part. I doubt a current LLM can create a valid PNG, even if it’s just a 1x1px one that has been created before. This is partially because PNGs have a checksum and the LLM has definitely not seen enough PNGs in base64 to figure out the algorithm, and is not optimized to calculate checksums. Also, it gets penalized for repetition, which occurs a lot in image headers.
AFAIK, the smallest valid image you see mentioned on the web is a 35-byte transparent pixel GIF, and the smallest PNG is a black pixel with 67 bytes:
Testing rendering:
, 
, another 67-byte PNG but 8 px wide: 
, or 1 gray pixel: 
, or a green one: 
The article + the generator
Why did it take a whole minute to scroll passed this on my Connect app?
No idea, it only has 1350 bytes now after the edit, and no crazy formatting
I think it was one first and then the other