Core ML Stable Diffusion
Updated • 7 • 19Note SDXL base model with mixed-bit palettization, achieving 4.5-bit quantization (average). See the blog post for details: https://huggingface.co/blog/stable-diffusion-xl-coreml
apple/coreml-stable-diffusion-xl-base
Text-to-Image • Updated • 29 • 67Note SDXL base model.
apple/coreml-stable-diffusion-2-1-base
Text-to-Image • Updated • 9 • 44Note Stable Diffusion 2.1, exported to Core ML in various configurations suitable for macOS, iOS using Swift or Python inference.
pcuenq/coreml-stable-diffusion-2-1-base
Text-to-Image • Updated • 13 • 3Note ^ zip archives of above model for use in https://github.com/huggingface/swift-coreml-diffusers
apple/coreml-stable-diffusion-2-1-base-palettized
Text-to-Image • Updated • 878 • 17Note ^ 6-bit palettized version of Stable Diffusion 2.1. Includes zip archives for use in apps.
apple/coreml-stable-diffusion-2-base
Text-to-Image • Updated • 79Note Stable Diffusion 2.0, exported to Core ML in various configurations suitable for macOS, iOS using Swift or Python inference.
pcuenq/coreml-stable-diffusion-2-base
Updated • 1Note ^ zip archives of above model for use in https://github.com/huggingface/swift-coreml-diffusers
apple/coreml-stable-diffusion-2-base-palettized
Text-to-Image • Updated • 7 • 3Note ^ 6-bit palettized version of Stable Diffusion 2.0. Includes zip archives for use in apps.
apple/coreml-stable-diffusion-v1-5
Text-to-Image • Updated • 31 • 57Note Stable Diffusion 1.5 published by RunwayML and converted to Core ML in various configurations suitable for macOS or iOS.
pcuenq/coreml-stable-diffusion-v1-5
Updated • 3Note ^ zip archives of above model for use in https://github.com/huggingface/swift-coreml-diffusers
apple/coreml-stable-diffusion-v1-5-palettized
Text-to-Image • Updated • 6 • 5Note ^ 6-bit palettized version of Stable Diffusion 1.5. Includes zip archives for use in apps.
apple/coreml-stable-diffusion-v1-4
Text-to-Image • Updated • 81 • 29pcuenq/coreml-stable-diffusion-1-4
Updatedapple/coreml-stable-diffusion-1-4-palettized
Text-to-Image • Updated • 1 • 4SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Paper • 2307.01952 • Published • 82High-Resolution Image Synthesis with Latent Diffusion Models
Paper • 2112.10752 • Published • 12