0.1.0: SD-XL 1.0 with permissive license

Release

• Releasing two new open models with a permissive CreativeML Open RAIL++-M license (see Inference for file hashes):
  • SDXL-base-1.0: An improved version over SDXL-base-0.9.
  • SDXL-refiner-1.0: An improved version over SDXL-refiner-0.9.
• Sharing the technical report on SDXL is now available here

Contributions

• #17: Setup packaging with hatch
• #59: Freeze requirements for .pt13, .pt2 environments, add black formatter & automatic build tests
• #57, #66: Add automatic inference tests with pytest, add codeowner
• #69: Improve inference code
• #68, #67, #70, #71: Update README, Licenses, model names & hashes

Stability Generative Models

• Release SD-XL 0.9-base and SD-XL 0.9-refiner models
• Release new sgm codebase
• Remove extensive subclassing
• Handle all types of conditioning inputs (vectors, sequences and spatial conditionings, and all combinations thereof) in a single class GeneralConditioner
• Separate guiders and samplers independent of the model
• Adopt the "denoiser framework" for both training and inference
• Discrete times models are special case of continuous time models
• Make independent following features: weighting of the diffusion loss function, preconditioning of the network, and sampling of noise levels during training
• Clean up Autoencoding models