Today marks the launch of Stable Cascade in its research preview. This innovative text to image model introduces an interesting three-stage approach, setting new benchmarks for quality, flexibility, fine-tuning, and efficiency with a focus on further eliminating hardware barriers.
  • Zarxrax@lemmy.worldEnglish
    5·
    11 months ago

    Looks interesting, but also somewhat complicated. Now generation has to run through 3 models? I thought it was bad enough having a separate refiner model for sdxl.

  • Pennomi@lemmy.worldEnglish
    4·
    11 months ago

    Oh wow, I was just looking for updates on this yesterday and suddenly this pops up! Very exciting!