Initial upload

README.md

@@ -0,0 +1,82 @@
+---
+license: other
+tags:
+- stable-diffusion
+- text-to-image
+- core-ml
+---
+
+# Stable Diffusion XL v0.9 Model Card
+
+This model was generated using [Apple’s repository](https://github.com/apple/ml-stable-diffusion) which has [ASCL](https://github.com/apple/ml-stable-diffusion/blob/main/LICENSE.md). This version contains 6-bit palettized Core ML weights for iOS 17 or macOS 14. To use weights without quantization, please visit this [model instead](https://huggingface.co/coreml-stable-diffusion-xl-v0-9-base).
+
+This model card focuses on the model associated with the Stable Diffusion XL v0.9 Base model, codebase available [here](https://github.com/Stability-AI/generative-models).
+
+SDXL v0.9 consists of a two-step pipeline for latent diffusion: 
+First, we use a base model to generate latents of the desired output size. 
+In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img") 
+to the latents generated in the first step, using the same prompt.
+
+Only the base model is included here.
+
+These weights here have been converted to Core ML for use on Apple Silicon hardware.
+
+There are 2 variants of the Core ML weights:
+
+```
+coreml-stable-diffusion-xl-v0-9-base
+└── original
+    ├── compiled              # Swift inference, "original" attention, 6-bit quantized
+    └── packages              # Python inference, "original" attention, 6-bit quantized 
+```
+
+### Model Description
+
+- **Developed by:** Stability AI
+- **Model type:** Diffusion-based text-to-image generative model
+- **License:** [SDXL 0.9 Research License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9/blob/main/LICENSE.md)
+- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses two fixed, pretrained text encoders ([OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip) and [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main)).
+- **Resources for more information:** [GitHub Repository](https://github.com/Stability-AI/generative-models) [SDXL paper on arXiv](https://arxiv.org/abs/2307.01952).
+
+### Model Sources
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/Stability-AI/generative-models
+- **Demo [optional]:** https://clipdrop.co/stable-diffusion
+
+## Uses
+
+### Direct Use
+
+The model is intended for research purposes only. Possible research areas and tasks include
+
+- Generation of artworks and use in design and other artistic processes.
+- Applications in educational or creative tools.
+- Research on generative models.
+- Safe deployment of models which have the potential to generate harmful content.
+- Probing and understanding the limitations and biases of generative models.
+
+Excluded uses are described below.
+
+### Out-of-Scope Use
+
+The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
+
+## Limitations and Bias
+
+### Limitations
+
+- The model does not achieve perfect photorealism
+- The model cannot render legible text
+- The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
+- Faces and people in general may not be generated properly.
+- The autoencoding part of the model is lossy.
+
+### Bias
+While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
+
+## Evaluation
+![comparison](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9/resolve/main/comparison.png)
+The chart above evaluates user preference for SDXL (with and without refinement) over Stable Diffusion 1.5 and 2.1. 
+The SDXL base model performs significantly better than the previous variants, and the model combined with the refinement module achieves the best overall performance.

original/compiled/TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe03850b93cf5bf8a994bb362dcd82dafbf6662ee82e27f5919836c3d241899
+size 207

original/compiled/TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a51c152cd09c8f8e7313c74922e1cf9dcd219b84c27f583fc8c2bb0255aca4
+size 983

original/compiled/TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,80 @@
+[
+  {
+    "shortDescription" : "This is a model that can be used to generate and modify images based on text prompts.It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT\/G and CLIP-ViT\/L).Please refer to https:\/\/arxiv.org\/abs\/2307.01952 for details",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The token embeddings as encoded by the Transformer model",
+        "shape" : "[]",
+        "name" : "last_hidden_state",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stabilityai\/stable-diffusion-xl-base-0.9",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9\/blob\/main\/LICENSE.md",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 2,
+      "Ios16.mul" : 36,
+      "Ios16.layerNorm" : 25,
+      "Ios16.constexprLutToDense" : 86,
+      "Transpose" : 60,
+      "Ios16.sigmoid" : 12,
+      "Ios16.linear" : 72,
+      "Ios16.add" : 37,
+      "Ios16.matmul" : 24,
+      "Ios16.softmax" : 12,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 120
+    },
+    "computePrecision" : "Mixed (Float32, Int32, Float16)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1 × 77)",
+        "shortDescription" : "The token ids that represent the input text",
+        "shape" : "[1, 77]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.1.0.dev20230718"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_0_9_text_encoder",
+    "method" : "predict"
+  }
+]

original/compiled/TextEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff22b0d1c3e7a7f508ee140cece12b85957f7aa230c224850bad79837380916
+size 139866304

original/compiled/TextEncoder2.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a20bb3d9c07198d7aa0d24673c7675c08d93832f930b9687af88ac607bc63a5
+size 207

original/compiled/TextEncoder2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a51c152cd09c8f8e7313c74922e1cf9dcd219b84c27f583fc8c2bb0255aca4
+size 983

original/compiled/TextEncoder2.mlmodelc/metadata.json

@@ -0,0 +1,83 @@
+[
+  {
+    "shortDescription" : "This is a model that can be used to generate and modify images based on text prompts.It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT\/G and CLIP-ViT\/L).Please refer to https:\/\/arxiv.org\/abs\/2307.01952 for details",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The token embeddings as encoded by the Transformer model",
+        "shape" : "[]",
+        "name" : "last_hidden_state",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stabilityai\/stable-diffusion-xl-base-0.9",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9\/blob\/main\/LICENSE.md",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 2,
+      "Ios16.mul" : 32,
+      "Ios16.layerNorm" : 65,
+      "Ios16.constexprLutToDense" : 227,
+      "Stack" : 1,
+      "Transpose" : 160,
+      "Ios16.linear" : 193,
+      "Ios16.add" : 97,
+      "Ios16.matmul" : 64,
+      "Ios16.gelu" : 32,
+      "Ios16.softmax" : 32,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 320,
+      "Ios16.reduceArgmax" : 1
+    },
+    "computePrecision" : "Mixed (Float32, Int32, Float16)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1 × 77)",
+        "shortDescription" : "The token ids that represent the input text",
+        "shape" : "[1, 77]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.1.0.dev20230718"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_0_9_text_encoder_2",
+    "method" : "predict"
+  }
+]

original/compiled/TextEncoder2.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12f95c0a669a542d8c44ca54eda8d4b88c482e31d61542f405f46057a7ea5cf
+size 600595584

original/compiled/Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a13be11bc2d489a4d4d606e39c7d8ea7f50f952ea7488469502c2ccc5d01b3c
+size 207

original/compiled/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0ac9e2cdc134f9e018182337f93bbe7950c5c44a53793cdd8eab754fd59ed4
+size 1717

original/compiled/Unet.mlmodelc/metadata.json

@@ -0,0 +1,123 @@
+[
+  {
+    "shortDescription" : "This is a model that can be used to generate and modify images based on text prompts.It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT\/G and CLIP-ViT\/L).Please refer to https:\/\/arxiv.org\/abs\/2307.01952 for details",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
+        "shape" : "[]",
+        "name" : "noise_pred",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stabilityai\/stable-diffusion-xl-base-0.9",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9\/blob\/main\/LICENSE.md",
+    "mlProgramOperationTypeHistogram" : {
+      "UpsampleNearestNeighbor" : 2,
+      "Ios16.reduceMean" : 512,
+      "Ios16.sin" : 2,
+      "Ios16.softmax" : 140,
+      "Split" : 70,
+      "Ios16.add" : 722,
+      "Concat" : 14,
+      "Ios16.realDiv" : 46,
+      "Ios16.square" : 46,
+      "ExpandDims" : 6,
+      "Ios16.sub" : 256,
+      "Ios16.cast" : 1,
+      "Ios16.conv" : 794,
+      "Ios16.constexprLutToDense" : 870,
+      "Ios16.gelu" : 70,
+      "Ios16.matmul" : 280,
+      "Ios16.batchNorm" : 46,
+      "Ios16.reshape" : 676,
+      "Ios16.rsqrt" : 210,
+      "Ios16.silu" : 38,
+      "Ios16.sqrt" : 46,
+      "Ios16.mul" : 842,
+      "Ios16.cos" : 2,
+      "SliceByIndex" : 4
+    },
+    "computePrecision" : "Mixed (Float32, Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 4 × 128 × 128)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 128, 128]",
+        "name" : "sample",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2)",
+        "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule",
+        "shape" : "[2]",
+        "name" : "timestep",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 2048 × 1 × 77)",
+        "shortDescription" : "Output embeddings from the associated text_encoder model to condition to generated image on text. A maximum of 77 tokens (~40 words) are allowed. Longer text is truncated. Shorter text does not reduce computation.",
+        "shape" : "[2, 2048, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 1280)",
+        "shortDescription" : "Additional embeddings passed to the unet based on the pooled output of the text encoders.",
+        "shape" : "[2, 1280]",
+        "name" : "text_embeds",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 6)",
+        "shortDescription" : "Additional embeddings passed to the unet based on width and height dimensions.For SDXL, default values look like [1024, 1024, 0, 0, 1024, 1024]",
+        "shape" : "[2, 6]",
+        "name" : "time_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.1.0.dev20230718",
+      "com.github.apple.ml-stable-diffusion.version" : "1.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_0_9_unet",
+    "method" : "predict"
+  }
+]

original/compiled/Unet.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e02fa888785308d476aa613ee4921a7bb52bec16090048cdf3f06cf50ad570d
+size 1927032512

original/compiled/VAEDecoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cdeab9f108fbe64f0c0d010f12dc5ec310494651180c2d49ec841e2048eadaf
+size 207

original/compiled/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:471e9de0a33b947f418b3648e490350fc09daccaf5dac260f422334ae154b8d5
+size 915

original/compiled/VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,74 @@
+[
+  {
+    "shortDescription" : "This is a model that can be used to generate and modify images based on text prompts.It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT\/G and CLIP-ViT\/L).Please refer to https:\/\/arxiv.org\/abs\/2307.01952 for details",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Generated image normalized to range [-1, 1]",
+        "shape" : "[]",
+        "name" : "image",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stabilityai\/stable-diffusion-xl-base-0.9",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float32",
+    "license" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9\/blob\/main\/LICENSE.md",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.mul" : 2,
+      "Ios16.sqrt" : 30,
+      "Ios16.sub" : 30,
+      "Transpose" : 6,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.conv" : 36,
+      "Ios16.add" : 46,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.realDiv" : 30,
+      "Ios16.reduceMean" : 60,
+      "Ios16.softmax" : 1,
+      "Ios16.batchNorm" : 29,
+      "Ios16.square" : 30,
+      "Ios16.reshape" : 65,
+      "Ios16.silu" : 29
+    },
+    "computePrecision" : "Mixed (Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 4 × 128 × 128)",
+        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
+        "shape" : "[1, 4, 128, 128]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.1.0.dev20230718"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_0_9_vae_decoder",
+    "method" : "predict"
+  }
+]

original/compiled/VAEDecoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663fd963f7a13afa32b8c415944bd3652f3c249335d02e2f57ff02bc3ac447bc
+size 197977216

original/compiled/VAEEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ca3543a6edddd2a8268d7380d9abf1a0855d5e7cb897f6dd64ae71eda21628
+size 207

original/compiled/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f3577db670a798e18e4c89c20e64af914d145df096422944051a8aa843341f
+size 919

original/compiled/VAEEncoder.mlmodelc/metadata.json

@@ -0,0 +1,75 @@
+[
+  {
+    "shortDescription" : "This is a model that can be used to generate and modify images based on text prompts.It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT\/G and CLIP-ViT\/L).Please refer to https:\/\/arxiv.org\/abs\/2307.01952 for details",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The latent embeddings from the unet model from the input image.",
+        "shape" : "[]",
+        "name" : "latent",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stabilityai\/stable-diffusion-xl-base-0.9",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9\/blob\/main\/LICENSE.md",
+    "mlProgramOperationTypeHistogram" : {
+      "Pad" : 3,
+      "Ios16.cast" : 2,
+      "Ios16.mul" : 2,
+      "Ios16.sqrt" : 22,
+      "Ios16.sub" : 22,
+      "Transpose" : 6,
+      "Ios16.conv" : 28,
+      "Ios16.add" : 34,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.realDiv" : 22,
+      "Ios16.reduceMean" : 44,
+      "Ios16.softmax" : 1,
+      "Ios16.batchNorm" : 21,
+      "Ios16.square" : 22,
+      "Ios16.reshape" : 49,
+      "Ios16.silu" : 21
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 3 × 1024 × 1024)",
+        "shortDescription" : "The input image to base the initial latents on normalized to range [-1, 1]",
+        "shape" : "[1, 3, 1024, 1024]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.1.0.dev20230718"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_0_9_vae_encoder",
+    "method" : "predict"
+  }
+]

original/compiled/VAEEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7da2b2913ea54fd16b4e333eb32c0037c9638b2d1c7d435693ed37126407b94
+size 68338112

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de0a2f2628f3acd682d396d53762257d7b252b052c7a6a5236ba55731e5deeb
+size 173086

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_text_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc50421439df3362c01855f0ac7bb8d3289e729e8e212f267df1643f240f45a
+size 139866304

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_text_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "86EF0C29-F024-403D-80C4-13DA00A72585": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "DB017C0F-5D21-4EDB-BE89-1A28032C84BD": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "DB017C0F-5D21-4EDB-BE89-1A28032C84BD"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_text_encoder_2.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef9acc716efb883ae83df7bb7c7624a38f4023f85106fb2b1a7de825c53c859
+size 452670

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_text_encoder_2.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bddeacfeade5e8f3323f4ba3011a5acf501680cccf95570c36d8c12fdea18f7
+size 600595584

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_text_encoder_2.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "02A81ACF-45B3-446A-AB57-ABDC9210E3DF": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "940ECFF5-C195-4C8D-9464-3EA7E817D4FA": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "02A81ACF-45B3-446A-AB57-ABDC9210E3DF"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43cafd123fdb5d6eb0a3d1e5c68a7696e2603f03f137c79f640d912667ef657
+size 2169848

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_unet.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bf3f8f69d7da0d505f2fe5a4d4f1f425ab52fe2f90be653fe4a7c24481b9c7
+size 1927032512

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_unet.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "40327681-9B28-4846-BC4E-5FA550B22867": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "583B349A-9131-4E73-98A8-1D2574B8A618": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "583B349A-9131-4E73-98A8-1D2574B8A618"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f56931bdb87177595409259ce621cd4201e71566387a9e9408a5792b75d15392
+size 143730

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_vae_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afcf2eea009577c84b138e34ab13c05fb5810ab2531d849c6149e8f77dbef545
+size 197977216

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_vae_decoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "AF04E042-F2F8-4009-B620-80D482DBA205": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "F0000CD6-D5F5-4F19-BA8E-53632E8F34F0": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "F0000CD6-D5F5-4F19-BA8E-53632E8F34F0"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_vae_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183df796843d151a0de22a09fe9dd0880626fa21f685de97e753c2ace3cd2ca2
+size 119655

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_vae_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d7087bf31f709986ae95569958d9f102671cf15fb41e2e2056b9c505038596
+size 68338112

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-xl-base-0.9_vae_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "66DC1E90-9AD3-4A7E-9739-A91C75EB5643": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "F2DDCE48-882D-4C78-A64E-7D7E2DDFD00B": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "66DC1E90-9AD3-4A7E-9739-A91C75EB5643"
+}