initial commit

README.md

@@ -0,0 +1,11 @@
+# Core ML SD-Turbo
+
+This repository contains pre-converted Core ML models of SD-Turbo for use on
+Apple silicon devices.
+
+- Original model: [SD-Turbo]
+- Image resolution: 512x512
+- 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 sha256:8d908cb3e7b049a90cc7034a3cb0401e0e39dddbf809c7d80dd8b4c717f62336
+size 680811520

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46784d0d79d744b18b3c6dbc0f0c96d240d21a89a61ff37ca11114a48bf8f855
+size 243

original/compiled/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5798236e063a304a3ac0cfa3aea151db8ef75eca82cda9304da96e28f558636
+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 × 64 × 64)",
+        "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
+        "shape" : "[2, 4, 64, 64]",
+        "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 × 64 × 64)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 64, 64]",
+        "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:bb20f6bf1733f790d19887ad6254714eeca950528b42d48b583f5c54320543fe
+size 1731897216

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af13b5d1e7e4efafd051689b1be90d8265294aa3c27087fba811d9fe0fd876e
+size 243

original/compiled/UnetChunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9121cfcdc4ff3c56c67e9900dd73cf7bc1e8f609ecee3312ced4ec635c5313d
+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 × 640 × 32 × 32)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 32, 32]",
+        "name" : "input_89_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 2560 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[2, 2560, 8, 8]",
+        "name" : "input_253_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 32 × 32)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 32, 32]",
+        "name" : "input_63_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 64, 64]",
+        "name" : "input_61_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 16 × 16)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 16, 16]",
+        "name" : "input_143_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 8, 8]",
+        "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 × 16 × 16)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 16, 16]",
+        "name" : "input_117_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 640 × 32 × 32)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 32, 32]",
+        "name" : "input_115_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 64, 64]",
+        "name" : "input_7_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 8, 8]",
+        "name" : "input_171_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 16 × 16)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 16, 16]",
+        "name" : "input_169_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 64, 64]",
+        "name" : "input_35_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 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 4, 64, 64]",
+        "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 sha256:1b2380c301a33955b5c2e38423a66bb579db9d2917f5d37fc1ef8ed621912e37
+size 893467840

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ecd53c3bb364134c54e689779d98410f8a4cdd7ece795f3b3995bd98efbcb9
+size 243

original/compiled/UnetChunk2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2609f3c42dc85a8a690333ad8fbe659c7e0e9546505c5de6693984d5296cdd78
+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 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 4, 64, 64]",
+        "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 × 32 × 32)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 32, 32]",
+        "name" : "input_63_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 64, 64]",
+        "name" : "input_61_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 16 × 16)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 16, 16]",
+        "name" : "input_143_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 8, 8]",
+        "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 × 16 × 16)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 16, 16]",
+        "name" : "input_117_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 640 × 32 × 32)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 32, 32]",
+        "name" : "input_115_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 64, 64]",
+        "name" : "input_7_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 2560 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[2, 2560, 8, 8]",
+        "name" : "input_253_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 16 × 16)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 16, 16]",
+        "name" : "input_169_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 1280 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280, 8, 8]",
+        "name" : "input_171_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 64, 64]",
+        "name" : "input_35_cast_fp16",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 640 × 32 × 32)",
+        "shortDescription" : "",
+        "shape" : "[2, 640, 32, 32]",
+        "name" : "input_89_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 sha256:001ac2b9963b6a4eeaffb93bad2064dbc757d8d2f22e976b0b510c819ba886b3
+size 838449152

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba66996567b4c732d4c966b356dc9f02b9a1d864ac07fd27298c0f32928c4ee
+size 243

original/compiled/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d8d86168bf12660dafd6a0c17ebba7ea909d78c149ba367aabbd2f4740a79d
+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 × 512 × 512)",
+        "shortDescription" : "Generated image normalized to range [-1, 1]",
+        "shape" : "[1, 3, 512, 512]",
+        "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 × 64 × 64)",
+        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
+        "shape" : "[1, 4, 64, 64]",
+        "name" : "z",
+        "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_decoder",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56ea51637e17c1b8cdf4264e8f08314a38ff199ea77ea19f305d307632b553c
+size 98993280

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818f30f361159858da0f157a27e051605cae233f2560b287f8e96de3470efc9e
+size 243

original/compiled/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c908ef771ec4d0c7b39a78c0677f5c0d7c53e5a0383179fa2a959f2f818d95
+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 × 64 × 64)",
+        "shortDescription" : "The latent embeddings from the unet model from the input image.",
+        "shape" : "[1, 8, 64, 64]",
+        "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 × 512 × 512)",
+        "shortDescription" : "The input image to base the initial latents on normalized to range [-1, 1]",
+        "shape" : "[1, 3, 512, 512]",
+        "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 sha256:45dfc77533a728e5fef2d3f4304eb815a6fadc664a3ece43253999484a26f3fd
+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 sha256:8d908cb3e7b049a90cc7034a3cb0401e0e39dddbf809c7d80dd8b4c717f62336
+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": {
+        "38684E42-4FDC-4D3C-B09B-566A4D2C07F5": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "B32F4451-DF49-4FF0-A82E-CB8F2A39C591": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "B32F4451-DF49-4FF0-A82E-CB8F2A39C591"
+}

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 sha256:7bd10c5bb7f5dded97c30176a4b2a36d22f14ef90230ea47bbc2fad3d23b9840
+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:bb20f6bf1733f790d19887ad6254714eeca950528b42d48b583f5c54320543fe
+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": {
+        "158EE137-4319-4F40-8679-4D30860A68EA": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "52FD5EE2-9DC7-4050-8BB9-8ADD6CD7F5D1": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "158EE137-4319-4F40-8679-4D30860A68EA"
+}

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 sha256:0e1400afa1a2bf70726998d120a70d5ade0466131e261ac6a79902e96d2042e5
+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 sha256:1b2380c301a33955b5c2e38423a66bb579db9d2917f5d37fc1ef8ed621912e37
+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": {
+        "139F851F-4E05-490A-BA89-0459BE675B85": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "EA3DC66B-CFF3-40CD-BA48-50D32CD456D9": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "139F851F-4E05-490A-BA89-0459BE675B85"
+}

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:b1fb72f640b944e6e77ba0c16583963d0a32f06537d1973100a1a6f9a42eaa75
+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 sha256:001ac2b9963b6a4eeaffb93bad2064dbc757d8d2f22e976b0b510c819ba886b3
+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": {
+        "1C101A64-C99D-446E-83B6-B41F0EBAAF07": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "641FBB26-20BE-4A92-BFFA-F55F7FD586AC": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "641FBB26-20BE-4A92-BFFA-F55F7FD586AC"
+}

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:f6813de5d89b463003bd11445a94aaac5a3b3cf12812f9a08e0d56e19cf5174e
+size 162395

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:e56ea51637e17c1b8cdf4264e8f08314a38ff199ea77ea19f305d307632b553c
+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": {
+        "6C09948A-2434-4AB5-9D6E-059EA35283B8": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "803169B2-34B0-478E-B2B8-98E87C1C2316": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "6C09948A-2434-4AB5-9D6E-059EA35283B8"
+}

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 sha256:9c712dedaef585c551a7e219518d4db10ee080075620286729ec3b2fd264bff5
+size 124372

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 sha256:45dfc77533a728e5fef2d3f4304eb815a6fadc664a3ece43253999484a26f3fd
+size 68338112