initial commit

README.md

@@ -0,0 +1,12 @@
+# Core ML SD-Turbo (640x384)
+
+This repository contains pre-converted Core ML models of SD-Turbo for use on
+Apple silicon devices. I changed the resolution to make it handy for generating
+widescreen images.
+
+- Original model: [SD-Turbo]
+- Image resolution: 640x384
+- Tested on [keijiro/ml-stable-diffusion] v1.2.0
+
+[SD-Turbo]: https://huggingface.co/stabilityai/sd-turbo
+[keijiro/ml-stable-diffusion]: https://github.com/keijiro/ml-stable-diffusion

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920ce4c4b8e64b36950857debdfb2c770c3cbfccdde2c7b5088411f96163e1e2
+size 243

original/compiled/TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e23873394ad211ea22dcd3653e626f57353af8b938ffc07899daf1e44596a4
+size 933

original/compiled/TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,84 @@
+[
+  {
+    "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 1 × 77 × 1024)",
+        "shortDescription" : "The token embeddings as encoded by the Transformer model",
+        "shape" : "[1, 77, 1024]",
+        "name" : "last_hidden_state",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 1024)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[1, 1024]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 23,
+      "Ios16.layerNorm" : 47,
+      "Stack" : 1,
+      "Transpose" : 115,
+      "Ios16.linear" : 138,
+      "Ios16.add" : 70,
+      "Ios16.matmul" : 46,
+      "Ios16.gelu" : 23,
+      "Ios16.softmax" : 23,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 230,
+      "Ios16.reduceArgmax" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "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.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd_turbo_text_encoder",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b462f569021a6c18123a53ace80df1bf3ebb7d76c830b5394e37463af5a3969
+size 680811520

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2240ec844eced7b3018d6fd983d1779ea2376085ca080a8a3faa34f4f9515286
+size 243

original/compiled/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3ab6e861de0e74e94260a3a09196826b8652e0d3b15e6d17e743e2d5e05e0e
+size 1366

original/compiled/Unet.mlmodelc/metadata.json

@@ -0,0 +1,104 @@
+[
+  {
+    "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 2 × 4 × 48 × 80)",
+        "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
+        "shape" : "[2, 4, 48, 80]",
+        "name" : "noise_pred",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "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 (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "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.ml-stable-diffusion.version" : "1.1.0",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd_turbo_unet",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8679eecc6eb9650d756f5eccbe737bea7c170edeff4dd7b29e056895edea8e69
+size 1731897216

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1705b215a906dd84f7bd68f20e59da0b62f5302626abddf756f8e3a59ba247
+size 243

original/compiled/UnetChunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff00c69b6d8b0fa01cb5e4dfc0958096e1c994ec2bbb370151285d06717bb431
+size 783

original/compiled/UnetChunk1.mlmodelc/metadata.json

@@ -0,0 +1,217 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 48 × 80)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 48, 80]",
+        "name" : "input_61_cast_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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 (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.1",
+      "com.github.apple.coremltools.source" : "milinternal"
+    },
+    "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__Users_keijiro_Documents_StableDiffusion_sd_turbo_unet_chunk1",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3a9500cf3bae788e238558bbd67c60636ef1d05bbee12d37b821633e3a50d
+size 893467840

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec93d1b49276c8e187d539a2ef823cf6d424ed1eeef7948d262dede80162b7f9
+size 243

original/compiled/UnetChunk2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ce21144c753fcf1fd3f6848620443891d3991e6a61f76e08253ee5ee5f12ad
+size 764

original/compiled/UnetChunk2.mlmodelc/metadata.json

@@ -0,0 +1,204 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 4 × 48 × 80)",
+        "shortDescription" : "",
+        "shape" : "[2, 4, 48, 80]",
+        "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 (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.1",
+      "com.github.apple.coremltools.source" : "milinternal"
+    },
+    "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 × 320 × 48 × 80)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 48, 80]",
+        "name" : "input_7_cast_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "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_fp16",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd_turbo_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:c73b29d6f4f6869e8bd429ecc623ddb942c09a58ddaf28c45c29bd980f91dd2f
+size 838449152

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e78bc1d11a1933a094c31087b6e0777ae9507f41910157d93acd5543d0b2c66
+size 243

original/compiled/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa3328453c68eb0fcc87764eb793b6c596df47086a7d8e4d6ab821647a92c83
+size 860

original/compiled/VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,77 @@
+[
+  {
+    "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 1 × 3 × 384 × 640)",
+        "shortDescription" : "Generated image normalized to range [-1, 1]",
+        "shape" : "[1, 3, 384, 640]",
+        "name" : "image",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 1,
+      "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 (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "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.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.version" : "7.1",
+      "com.github.apple.coremltools.source" : "torch==2.1.2"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd_turbo_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:b5dd566219d197b1c1529f562512ad3d62938d69f9d677ba2ccbab2115fa1b17
+size 98993280

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af42e2250346e84df8eb6b54e2b3ed32baf91ee09f45a7988e0d61b76e1529d
+size 243

original/compiled/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e9255078ca27443e6e6462e3e66cdeb07e1605ce4903e43374e519de342225
+size 864

original/compiled/VAEEncoder.mlmodelc/metadata.json

@@ -0,0 +1,77 @@
+[
+  {
+    "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 1 × 8 × 48 × 80)",
+        "shortDescription" : "The latent embeddings from the unet model from the input image.",
+        "shape" : "[1, 8, 48, 80]",
+        "name" : "latent",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/keijiro\/Documents\/StableDiffusion\/sd-turbo",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Pad" : 3,
+      "Ios16.cast" : 1,
+      "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",
+      "visionOS" : "1.0",
+      "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" : "x",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd_turbo_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:dcdc23bf9f08f08d6f0ab3e7ea9754d6f141a9e6a6793754ec5345dc0a1d26bc
+size 68338112

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d669b52e19ada32ceaca821008075594b76f94bc3733ad63ba1546843fd30c39
+size 309358

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_text_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b462f569021a6c18123a53ace80df1bf3ebb7d76c830b5394e37463af5a3969
+size 680811520

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_text_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "36025034-B2D3-4233-AD02-0DB1B77DDB1E": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "375B9A50-6755-4DF5-A753-A79C660637E3": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "36025034-B2D3-4233-AD02-0DB1B77DDB1E"
+}

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be92f1bd1d9b91160157b48d1f9dc6c7bc6e5614c53ac009664045f46df86d4d
+size 807015

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8679eecc6eb9650d756f5eccbe737bea7c170edeff4dd7b29e056895edea8e69
+size 1731897216

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "7357471B-94B4-4242-8053-8D0335F1AF68": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "8B6BF4A3-F240-463D-A7D3-AF14E0FAA622": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "8B6BF4A3-F240-463D-A7D3-AF14E0FAA622"
+}

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet_chunk1.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e3de5f70f656ed5a591778749043487aa152110a82c567e427c6c8aa0974e5
+size 379601

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet_chunk1.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3a9500cf3bae788e238558bbd67c60636ef1d05bbee12d37b821633e3a50d
+size 893467840

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet_chunk1.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "7315655F-F31F-413A-8312-2DBD905B2D6A": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "D88B01D3-3A62-48E7-9909-FD4AEEE75890": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "D88B01D3-3A62-48E7-9909-FD4AEEE75890"
+}

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet_chunk2.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60d4220145874c2a87ad7e0b7578d5a08176b64e3b43e8f20bf405721144879
+size 436776

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet_chunk2.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73b29d6f4f6869e8bd429ecc623ddb942c09a58ddaf28c45c29bd980f91dd2f
+size 838449152

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_unet_chunk2.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "3A5B6AC1-ACDF-40CA-B731-326D0D840196": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "C0C4827C-2628-4DA0-9254-71BEBB465B93": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "C0C4827C-2628-4DA0-9254-71BEBB465B93"
+}

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80da90d966a924a0f84fd70125bb21b3761a6ff3c301c14aea6e03d2709dd928
+size 162330

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_vae_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dd566219d197b1c1529f562512ad3d62938d69f9d677ba2ccbab2115fa1b17
+size 98993280

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_vae_decoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "AEC14DF1-68C4-4AFA-917B-31B4C4290E65": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "E98CE0C7-337B-405F-80F3-396902C9F63E": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "E98CE0C7-337B-405F-80F3-396902C9F63E"
+}

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_vae_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d0d3ce669646ce11e686878b221e28f6189f27e44ae587150c74610511e432
+size 124327

original/packages/Stable_Diffusion_version__Users_keijiro_Documents_StableDiffusion_sd-turbo_vae_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcdc23bf9f08f08d6f0ab3e7ea9754d6f141a9e6a6793754ec5345dc0a1d26bc
+size 68338112