Has anyone experimented with an ensemble + synthesizer approach for reliability? I'm thinking: make n identical requests to get diverse outputs, then use a separate LLM call to synthesize/reconcile the distinct results…
That's true and that's indeed the reason why we built imageprompt.io. And for sure we will continue actively improving our selection process and updating our collection to showcase only top-tier Midjourney-generated…
Has anyone experimented with an ensemble + synthesizer approach for reliability? I'm thinking: make n identical requests to get diverse outputs, then use a separate LLM call to synthesize/reconcile the distinct results…
That's true and that's indeed the reason why we built imageprompt.io. And for sure we will continue actively improving our selection process and updating our collection to showcase only top-tier Midjourney-generated…