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.
“Stable Cascade is exceptionally easy to train and finetune on consumer hardware thanks to its three-stage approach.”
Awesome. People were worried Stability will focus on enterprise AI after SDXL and completely forget making consumer AI, but this is definitely not the case.
This model is being released under a non-commercial license that permits non-commercial use only.
Awesome. People were worried Stability will focus on enterprise AI after SDXL and completely forget making consumer AI, but this is definitely not the case.
God bless.
They’ve said in the past that this only applies to incorporating the models into a service, not the outputs from models.