initial commit

README.md

@@ -0,0 +1,9 @@
+# Core ML Stable Diffusion Model (SD 2.1, 640x384)
+
+This repository contains pre-converted Core ML models of Stable Diffusion v2
+for use on Apple silicon devices. I changed the resolution to make it handy for
+generating widescreen images.
+
+- Original model: [Stable Diffusion v2-1](https://huggingface.co/stabilityai/stable-diffusion-2-1)
+- Image resolution: 640x384
+- Tested on ml-stable-diffusion v1.1.0

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d64a68253098643e42009d1a0d88d9173a8f904122cb6420e510d0602a62c0
+size 207

original/compiled/TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcc9ab5db34eb18ff509fc2412f605eea0887d1f6703fee3d5b8be5757d4264
+size 839

original/compiled/TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,85 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 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-2-1-base",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-1-base",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 23,
+      "Ios16.layerNorm" : 47,
+      "Ios16.sub" : 1,
+      "BandPart" : 1,
+      "Stack" : 1,
+      "Transpose" : 115,
+      "Ios16.linear" : 138,
+      "Ios16.add" : 70,
+      "Ios16.matmul" : 46,
+      "Ios16.gelu" : 23,
+      "Ios16.softmax" : 23,
+      "ExpandDims" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.gatherNd" : 1,
+      "Ios16.reshape" : 230,
+      "Ios16.reduceArgmax" : 1
+    },
+    "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 × 77)",
+        "shortDescription" : "The token ids that represent the input text",
+        "shape" : "[1, 77]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "6.3.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_text_encoder",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011f1d70fc59a4b2159595ffe0b9af6819c78553c79238d3e5da98a922f7b404
+size 680811520

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5846fc4dd630634b348775b23c2505256e929b277f0219ee58c1be78ab0fd0bd
+size 207

original/compiled/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f3ba5dc59186bc9ec95c02094f91c6624307c2d66dc0806917c5e35db5420d
+size 1221

original/compiled/Unet.mlmodelc/metadata.json

@@ -0,0 +1,101 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 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-2-1-base",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-1-base",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.reduceMean" : 218,
+      "Ios16.sin" : 1,
+      "Ios16.softmax" : 32,
+      "Split" : 16,
+      "Ios16.add" : 265,
+      "Concat" : 14,
+      "Ios16.realDiv" : 61,
+      "Ios16.square" : 61,
+      "ExpandDims" : 3,
+      "Ios16.sub" : 109,
+      "Ios16.cast" : 1,
+      "Ios16.conv" : 282,
+      "Ios16.gelu" : 16,
+      "Ios16.matmul" : 64,
+      "Ios16.reshape" : 282,
+      "Ios16.batchNorm" : 61,
+      "Ios16.rsqrt" : 48,
+      "Ios16.silu" : 47,
+      "Ios16.sqrt" : 61,
+      "SliceByIndex" : 2,
+      "Ios16.mul" : 193,
+      "Ios16.cos" : 1
+    },
+    "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 × 48 × 80)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 48, 80]",
+        "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 × 1024 × 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, 1024, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "6.3.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_unet",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5e055d2afc94a8f40eb370f896c1fc38bf6846dfff6b8b5938d8faeca4c528
+size 1732124416

original/compiled/UnetChunk1.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91131d35858ad1e809cf82518baed6c67b76f95604cc993edd4dfe3e000c50b
+size 207

original/compiled/UnetChunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985b94a86efb8fbbe2c9805a84516c80efa5fc09983a189342f07a79652bc490
+size 528

original/compiled/UnetChunk1.mlmodelc/metadata.json

@@ -0,0 +1,215 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_115_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_61_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_35_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_169_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "hidden_states_149_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_15_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_143_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_89_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_117_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_171_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_253_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_7_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "input_63_cast",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.reduceMean" : 104,
+      "Ios16.sin" : 1,
+      "Ios16.softmax" : 14,
+      "Split" : 7,
+      "Ios16.add" : 124,
+      "Concat" : 4,
+      "Ios16.realDiv" : 31,
+      "Ios16.square" : 31,
+      "ExpandDims" : 3,
+      "Ios16.sub" : 52,
+      "Ios16.cast" : 13,
+      "Ios16.conv" : 129,
+      "Ios16.gelu" : 7,
+      "Ios16.matmul" : 28,
+      "Ios16.reshape" : 132,
+      "Ios16.batchNorm" : 31,
+      "Ios16.rsqrt" : 21,
+      "Ios16.silu" : 26,
+      "Ios16.sqrt" : 31,
+      "SliceByIndex" : 2,
+      "Ios16.mul" : 85,
+      "Ios16.cos" : 1
+    },
+    "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"
+    },
+    "userDefinedMetadata" : {
+
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 4 × 48 × 80)",
+        "shortDescription" : "",
+        "shape" : "[2, 4, 48, 80]",
+        "name" : "sample",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2)",
+        "shortDescription" : "",
+        "shape" : "[2]",
+        "name" : "timestep",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 1024 × 1 × 77)",
+        "shortDescription" : "",
+        "shape" : "[2, 1024, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_unet_chunk1",
+    "method" : "predict"
+  }
+]

original/compiled/UnetChunk1.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929b834e3a62a566f4acfd448fe509f4c48f3fad8e2f6f67fe59f353455840a6
+size 893578816

original/compiled/UnetChunk2.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ba1d4578b3d9eaefa1793064088f4a1235b203e1de42b097b64d35959a6f02
+size 207

original/compiled/UnetChunk2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a85a46b55dd4b6dfeb74dfb46d78adc9d94bfea17b324daa6474a3278cf872
+size 594

original/compiled/UnetChunk2.mlmodelc/metadata.json

@@ -0,0 +1,202 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "noise_pred",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Split" : 9,
+      "Concat" : 10,
+      "Ios16.cast" : 14,
+      "Ios16.mul" : 108,
+      "Ios16.rsqrt" : 27,
+      "Ios16.sqrt" : 30,
+      "Ios16.sub" : 57,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.conv" : 153,
+      "Ios16.add" : 141,
+      "Ios16.realDiv" : 30,
+      "Ios16.matmul" : 36,
+      "Ios16.gelu" : 9,
+      "Ios16.reduceMean" : 114,
+      "Ios16.softmax" : 18,
+      "Ios16.batchNorm" : 30,
+      "Ios16.square" : 30,
+      "Ios16.reshape" : 150,
+      "Ios16.silu" : 21
+    },
+    "computePrecision" : "Mixed (Int32, Float16, Float32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 1024 × 1 × 77)",
+        "shortDescription" : "",
+        "shape" : "[2, 1024, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 1 × 1)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 1, 1]",
+        "name" : "input_15_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 48 × 80)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 48, 80]",
+        "name" : "input_7_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 6 × 10)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 6, 10]",
+        "name" : "input_171_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 2560 × 6 × 10)",
+        "shortDescription" : "",
+        "shape" : "[2, 2560, 6, 10]",
+        "name" : "input_253_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 640 × 24 × 40)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 24, 40]",
+        "name" : "input_115_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 48 × 80)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 48, 80]",
+        "name" : "input_35_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 48 × 80)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 48, 80]",
+        "name" : "input_61_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 24 × 40)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 24, 40]",
+        "name" : "input_63_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 640 × 12 × 20)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 12, 20]",
+        "name" : "input_117_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 640 × 24 × 40)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 24, 40]",
+        "name" : "input_89_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 12 × 20)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 12, 20]",
+        "name" : "input_143_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 6 × 10)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 6, 10]",
+        "name" : "hidden_states_149_cast",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 12 × 20)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 12, 20]",
+        "name" : "input_169_cast",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_unet_chunk2",
+    "method" : "predict"
+  }
+]

original/compiled/UnetChunk2.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32ee4c5cf0782e7f1c87332028b67346838cf8c2a7f5409c9c7026f857d9a0d
+size 838545664

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270ca43f586412d4438e626d71c4dfcf27f62c8d633ca1e61b486350b4c9adeb
+size 207

original/compiled/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522f8987457717dac193f49f8b98d71ef73cea7158f4cdff0b5d281b4f0ef485
+size 769

original/compiled/VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,75 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 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-2-1-base",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-1-base",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 1,
+      "Ios16.sqrt" : 30,
+      "Ios16.sub" : 30,
+      "Transpose" : 7,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.conv" : 36,
+      "Ios16.add" : 45,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.realDiv" : 30,
+      "Ios16.reduceMean" : 60,
+      "Ios16.softmax" : 1,
+      "Ios16.batchNorm" : 30,
+      "Ios16.square" : 30,
+      "Ios16.reshape" : 70,
+      "Ios16.silu" : 29
+    },
+    "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 1 × 4 × 48 × 80)",
+        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
+        "shape" : "[1, 4, 48, 80]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "6.3.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_vae_decoder",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bea6b8a1dba785c095e69e49e832f89250fa72c03948c0e304bf633b499d8df
+size 99039232

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6830b3d85d9d546202a82686d64032e8b6b49893e47c662c11f186e93ab31852
+size 207

original/compiled/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ce36698eb3a9f3a51b16a4420d58fc2cc26d8e1f2dcf09a544b0bb4fe80fb4
+size 775

original/compiled/VAEEncoder.mlmodelc/metadata.json

@@ -0,0 +1,75 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 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-2-1-base",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-1-base",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Pad" : 3,
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 1,
+      "Ios16.sqrt" : 22,
+      "Ios16.sub" : 22,
+      "Transpose" : 7,
+      "Ios16.conv" : 28,
+      "Ios16.add" : 33,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.realDiv" : 22,
+      "Ios16.reduceMean" : 44,
+      "Ios16.softmax" : 1,
+      "Ios16.batchNorm" : 22,
+      "Ios16.square" : 22,
+      "Ios16.reshape" : 54,
+      "Ios16.silu" : 21
+    },
+    "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 1 × 3 × 384 × 640)",
+        "shortDescription" : "The input image to base the initial latents on normalized to range [-1, 1]",
+        "shape" : "[1, 3, 384, 640]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "6.3.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_vae_encoder",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545d9c851507e0aee8b19ca2d4d0db68e21c78cb497875675842b252520bb088
+size 68370240

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cda7b8645d33b2b547d4e3939e85bac597fcbc1ea8404c0a6d6a1bd21a0884
+size 272314

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_text_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011f1d70fc59a4b2159595ffe0b9af6819c78553c79238d3e5da98a922f7b404
+size 680811520

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_text_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "0EBED1E9-C3A8-4F86-A3E5-3BE9D04FC4FE": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "ED8AC212-885A-41CB-82E8-81BDC914C5AE": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "ED8AC212-885A-41CB-82E8-81BDC914C5AE"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257b86ad60867af8fb0e3ae9fe3296ddff4bf77fefe4cef01ab0f6f8d57d29c6
+size 723023

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5e055d2afc94a8f40eb370f896c1fc38bf6846dfff6b8b5938d8faeca4c528
+size 1732124416

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "1E368FC1-440F-4774-AEF6-2D7C56F31C60": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "841BAB75-CD8F-4B56-B646-6BFC8301E276": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "841BAB75-CD8F-4B56-B646-6BFC8301E276"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet_chunk1.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8882ff7eefceffba1da1b9d5e1851f6cfccc9a2b86ecba36f34a8a295872211
+size 339619

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet_chunk1.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929b834e3a62a566f4acfd448fe509f4c48f3fad8e2f6f67fe59f353455840a6
+size 893578816

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet_chunk1.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "A2014855-F820-4EDA-B40A-E5FBF1FA669D": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "A3E0308E-461A-455A-976F-4D1854B25B99": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "A3E0308E-461A-455A-976F-4D1854B25B99"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet_chunk2.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5a054da84cbac1316bedf84ef8f92c13a73bb11759bb770553a84d32b4d36d
+size 389721

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet_chunk2.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32ee4c5cf0782e7f1c87332028b67346838cf8c2a7f5409c9c7026f857d9a0d
+size 838545664

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_unet_chunk2.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "77906117-66FB-4AE3-A8DF-0355F3C41735": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "A20BE417-C9A8-49F1-AED6-3279AE0BE316": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "77906117-66FB-4AE3-A8DF-0355F3C41735"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686b5f5b5806751d735dcab925d40cbb562c224151e7871e394b69e60e4e7e1a
+size 149737

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_vae_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bea6b8a1dba785c095e69e49e832f89250fa72c03948c0e304bf633b499d8df
+size 99039232

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_vae_decoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "55551C79-D9A3-4001-98F2-0F98319F2B76": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "7751D913-CEF3-4D58-ADC4-BEBC83C640FC": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "7751D913-CEF3-4D58-ADC4-BEBC83C640FC"
+}

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_vae_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27550b8a29e2ec14992d761111dc32829f374507aa8c886b006451980932de1
+size 114871

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-1-base_vae_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545d9c851507e0aee8b19ca2d4d0db68e21c78cb497875675842b252520bb088
+size 68370240