Automated CoreML conversion

TextEncoder.mlmodelc/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

TextEncoder.mlmodelc/analytics/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57af1deeaa8109ec88e5265189ee9396a24a6bbc6a991e9b693fcc53bd192f4
+size 243

TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b82ee4ea1c0df9e022c5fd01f8713f1522dd87c49efc957dd7ac40af4a600f
+size 984

TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,87 @@
+[
+  {
+    "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 × 768)",
+        "shortDescription" : "The token embeddings as encoded by the Transformer model",
+        "shape" : "[1, 77, 768]",
+        "name" : "last_hidden_state",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 768)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[1, 768]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "\/Volumes\/ShadowKey\/ConversionWorkspace\/perfectdeliberate_v5sd15\/Diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Volumes\/ShadowKey\/ConversionWorkspace\/perfectdeliberate_v5sd15\/Diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 36,
+      "Ios16.layerNorm" : 25,
+      "Transpose" : 48,
+      "Stack" : 1,
+      "Ios16.sigmoid" : 12,
+      "Ios16.linear" : 72,
+      "Ios16.add" : 37,
+      "Ios16.softmax" : 12,
+      "Ios16.matmul" : 24,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 48,
+      "Ios16.reduceArgmax" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "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==2.8.0",
+      "com.github.apple.coremltools.version" : "8.3.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Volumes_ShadowKey_ConversionWorkspace_perfectdeliberate_v5sd15_Diffusers_text_encoder",
+    "method" : "predict"
+  }
+]

TextEncoder.mlmodelc/weights/._weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

TextEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d851dfa8b9ced7545f178065ee84865163f3829c42f2c1f4847ccc973e67b5e4
+size 246145536

Unet.mlmodelc/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

Unet.mlmodelc/analytics/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892fb02d80e9591fce01cf6a3216ed19648cdab7155031ea223d06c935bb0b00
+size 243

Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5528df759a080292e2b38877c88aa5331529c5895342790a065b4b8c9d55ea24
+size 1417

Unet.mlmodelc/metadata.json

@@ -0,0 +1,108 @@
+[
+  {
+    "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" : "\/Volumes\/ShadowKey\/ConversionWorkspace\/perfectdeliberate_v5sd15\/Diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Volumes\/ShadowKey\/ConversionWorkspace\/perfectdeliberate_v5sd15\/Diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 32,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.reduceMean" : 122,
+      "Ios16.sin" : 1,
+      "Ios16.softmax" : 896,
+      "Split" : 16,
+      "Ios16.add" : 169,
+      "Concat" : 206,
+      "Ios16.realDiv" : 61,
+      "Ios16.square" : 61,
+      "ExpandDims" : 3,
+      "Ios16.sub" : 61,
+      "Ios16.sqrt" : 61,
+      "Ios16.einsum" : 1792,
+      "Ios16.conv" : 282,
+      "Ios16.reshape" : 154,
+      "Ios16.layerNorm" : 48,
+      "SliceByIndex" : 1570,
+      "Ios16.batchNorm" : 61,
+      "Ios16.silu" : 47,
+      "Ios16.gelu" : 16,
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 913,
+      "Ios16.cos" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "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 × 768 × 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, 768, 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==2.8.0",
+      "com.github.apple.coremltools.version" : "8.3.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Volumes_ShadowKey_ConversionWorkspace_perfectdeliberate_v5sd15_Diffusers_unet",
+    "method" : "predict"
+  }
+]

Unet.mlmodelc/weights/._weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

Unet.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a45a7a61ab8487c7b676de26468e12b5b93a29d3f9320596237fbc75433cea
+size 1719117696

UnetChunk1.mlmodelc/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

UnetChunk1.mlmodelc/analytics/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

UnetChunk1.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa54940b6a1c88a1cf7e93ffcddf5ddcebc7405425ef8ea6510e2ceeabcce4d
+size 243

UnetChunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9334a4d4fd9cc7abf64950dae49428b6bcfb6668550b5ae79c64ae08c3e101
+size 684

UnetChunk1.mlmodelc/metadata.json

@@ -0,0 +1,220 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "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 × 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 × 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 × 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 × 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 × 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 × 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 × 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_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 × 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 × 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 × 64 × 64)",
+        "shortDescription" : "",
+        "shape" : "[2, 320, 64, 64]",
+        "name" : "input_61_cast_fp16",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 14,
+      "Ios16.reduceMean" : 62,
+      "Ios16.sin" : 1,
+      "Ios16.softmax" : 368,
+      "Split" : 7,
+      "Ios16.add" : 82,
+      "Concat" : 82,
+      "Ios16.realDiv" : 31,
+      "Ios16.square" : 31,
+      "ExpandDims" : 3,
+      "Ios16.sub" : 31,
+      "Ios16.sqrt" : 31,
+      "Ios16.einsum" : 736,
+      "Ios16.conv" : 129,
+      "Ios16.reshape" : 76,
+      "Ios16.layerNorm" : 21,
+      "SliceByIndex" : 658,
+      "Ios16.batchNorm" : 31,
+      "Ios16.silu" : 26,
+      "Ios16.gelu" : 7,
+      "Ios16.cast" : 13,
+      "Ios16.mul" : 376,
+      "Ios16.cos" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+
+    ],
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "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 × 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 × 768 × 1 × 77)",
+        "shortDescription" : "",
+        "shape" : "[2, 768, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Stable_Diffusion_version__Volumes_ShadowKey_ConversionWorkspace_perfectdeliberate_v5sd15_Diffusers_unet_chunk1",
+    "method" : "predict"
+  }
+]

UnetChunk1.mlmodelc/weights/._weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

UnetChunk1.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291e14ce6b791844800c14e5c165d50902d6d837d01de72af4ecd027c3831a7c
+size 887569600

UnetChunk2.mlmodelc/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096

UnetChunk2.mlmodelc/analytics/._coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc3b99f3bf21b54dcb8386ca6156717439ceef73cfb7c48c06cc93cbf3e62c1
+size 4096