The fact that you have the possibility of running Flux locally might be enough of an argument to sway the balance for some cases. For example, if you've already set up a workflow and Google jacks up the price, or changes the API, you have no choice but to go along. If BFL does the same, you at least have the option of running locally.

Those cases imply commercial workflows that are prohibited with the open-weights model without purchasing a license.

I am curious to see how the Apache 2.0 distilled variant performs but it's still unlikely that the economics will favor it unless you have a specific niche use case: the engineering effort needed to scale up image inference for these large models isn't zero cost.