Well, from what I remember, there was going to be version 6.9 based on SDXL, but it didn’t happen. Using AuraFlow as a base seemed like the best option at the time, since there was no real alternative like Flux Schnell or Qwen then.
Putting issues with development and deployment aside, the current PonyV7 version seems like a fundamentally broken model hampered by the initial decisions and the lack of proper documentation. Focusing on the natural language prompting instead of tags made the model a chore to use, requiring a ridiculously long and flowery prompt to get any useful results. Using style clusters instead of artist tags looked like an interesting idea, but it turned out to be an utter mess, considering no documentation on these clusters and them clearly not working as intended.
The end result is a model that is slow, inconsistent, difficult to use and creates outputs that are SDXL-level at best and SD 1.5 level most of the time. I don’t see any reason to use it over the current Noob-based, or even PonyV6-based models, which are better in pretty much every single way.
