No elephants: Breakthroughs in image generation

Re:No elephants: Breakthroughs in image generation by throwaway2037 on Wednesday April 09, 2025 @03:40AM (#43629769)

    > four versions to choose to build and iterate on

How does this work? How do you ask a model to produce four different variations? Or do they have four different models run the same inference?

[ Parent | on HN ]

Re:No elephants: Breakthroughs in image generation by dmurray on Wednesday April 09, 2025 @07:21AM (#43630932)

There's some noise in the process, so you won't get the same results if you ask the same model the same prompt 4 times. Most of the services that do this just ask the same model 4 times with a different random seed, as far as I can tell.

[ Parent | on HN ]

Re:No elephants: Breakthroughs in image generation by HelloMcFly on Wednesday April 09, 2025 @07:45AM (#43631060)

You don't ask to run four models, it's just that every single prompt you give it will return four models. You can then choose to have one of them iterated on, or upscaled.

If you're still not sure let me know and I'll show a screenshot.

[ Parent | on HN ]