Hacker News Reader

I can afford them, I just don't need to anymore. My use cases for stock photos are websites, marketing, landing pages etc. The SOTA image models are sufficient for my use cases and my customers don't care. Infact, they are happy with the quality of AI generated stock photos and appreciate the fast turnaround and lower cost.

View on HN

Which models are SOTA as of now?

In terms of realism, Flux is leading the pack currently

I would say Flux leads the pack in COHERENCY not necessarily in terms of sheer realism. (See the Flux chin).

SDXL + LoRA easily eclipses Flux in realism, but prompting is 100% more difficult for complex scenes.

Over Midjourney?

Yeah, Midjourney tends to create sci-fi/enhanced looking humans. Flux creates photorealistic.

Interesting! What's the best way to check it out? Via API?

Reply on news.ycombinator.com