Add files for stable-diffusion-1-4-palettized

coreml-stable-diffusion-1-4-palettized_original_compiled.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9523a8d63dfee7f8044e62fa636c6945b859bbaebd388685088a33c1cfe07e7d
+size 1563648735

coreml-stable-diffusion-1-4-palettized_split_einsum_v2_compiled.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fabf8f28478473abcf1c6288d35cc6faf1a399b09cb4813a8cb8bc44de2b734e
+size 1565721660

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9069793905bd64c61471662d247051f975c417659c7a9dd4ed535bb9f09563
+size 207

original/compiled/SafetyChecker.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb231ab31095b3b27b7f8e4b94b2554adcc3def4c6c486b6b6da81b55207a616
+size 1413

original/compiled/SafetyChecker.mlmodelc/metadata.json

@@ -0,0 +1,122 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Identical to the input `images`. If safety checker detected any sensitive content, the corresponding image is replaced with a blank image (zeros)",
+        "shape" : "[]",
+        "name" : "filtered_images",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Indicates whether the safety checker model found any sensitive content in the given image",
+        "shape" : "[]",
+        "name" : "has_nsfw_concepts",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Concept scores are the scores before thresholding at zero yields the `has_nsfw_concepts` output. These scores can be used to tune the `adjustment` input",
+        "shape" : "[]",
+        "name" : "concept_scores",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "CompVis\/stable-diffusion-v1-4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/CompVis\/stable-diffusion-v1-4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 121,
+      "Ios16.scatterNd" : 1,
+      "Ios16.softmax" : 24,
+      "Ios16.linear" : 147,
+      "Ios16.add" : 51,
+      "Concat" : 1,
+      "Ios16.realDiv" : 1,
+      "Ios16.sigmoid" : 24,
+      "Ios16.reduceSum" : 3,
+      "Tile" : 4,
+      "Ios16.greater" : 4,
+      "Shape" : 1,
+      "ExpandDims" : 5,
+      "Ios16.cast" : 7,
+      "Ios16.clip" : 1,
+      "Ios16.conv" : 1,
+      "Ios16.abs" : 1,
+      "Ios16.layerNorm" : 50,
+      "Ios16.matmul" : 48,
+      "Ios16.pow" : 2,
+      "Ios16.reshape" : 193,
+      "SliceByIndex" : 2,
+      "Ios16.mul" : 73,
+      "NonZero" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3 × 224 × 224)",
+        "shortDescription" : "The normalized image input tensor resized to (224x224) in channels-first (BCHW) format",
+        "shape" : "[1, 3, 224, 224]",
+        "name" : "clip_input",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 512 × 3)",
+        "shortDescription" : "Output of the vae_decoder (512x512) in channels-last (BHWC) format",
+        "shape" : "[1, 512, 512, 3]",
+        "name" : "images",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1)",
+        "shortDescription" : "Bias added to the concept scores to trade off increased recall for reduce precision in the safety checker classifier",
+        "shape" : "[1]",
+        "name" : "adjustment",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_CompVis_stable_diffusion_v1_4_safety_checker",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fc2c3d772614a206c40e0b0bb6202bcbc429df958d0f1d2ec59c8275869097
+size 607990114

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270b2f4719eeacb851afbd8e0b6b1945050a6ffee57f04ec85227727e8bf5e04
+size 207

original/compiled/TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad93f2ba70a018ed815f96bc3353134260a67adb0eec25e729f45941f1370233
+size 823

original/compiled/TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,83 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The token embeddings as encoded by the Transformer model",
+        "shape" : "[]",
+        "name" : "last_hidden_state",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "CompVis\/stable-diffusion-v1-4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/CompVis\/stable-diffusion-v1-4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (6 bits))",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 36,
+      "Ios16.layerNorm" : 25,
+      "Ios16.constexprLutToDense" : 86,
+      "Stack" : 1,
+      "Transpose" : 60,
+      "Ios16.sigmoid" : 12,
+      "Ios16.linear" : 72,
+      "Ios16.add" : 37,
+      "Ios16.matmul" : 24,
+      "Ios16.softmax" : 12,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 120,
+      "Ios16.reduceArgmax" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 77)",
+        "shortDescription" : "The token ids that represent the input text",
+        "shape" : "[1, 77]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_CompVis_stable_diffusion_v1_4_text_encoder",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d832c2bdadc6d96cd14ed8b6894087751bbc1c37eb3429aecfa0ca027c79a5
+size 139866304

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5bef2e6bb8b2c406480292c435d3ff26f887c78994f858289206a7bdcb3fa3
+size 207

original/compiled/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7326bbcb8bd21b4e6708c398c897a22138037ace2f7ed254e93865499fd230e3
+size 1205

original/compiled/Unet.mlmodelc/metadata.json

@@ -0,0 +1,102 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
+        "shape" : "[]",
+        "name" : "noise_pred",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "CompVis\/stable-diffusion-v1-4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/CompVis\/stable-diffusion-v1-4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (6 bits))",
+    "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.constexprLutToDense" : 310,
+      "Ios16.gelu" : 16,
+      "Ios16.matmul" : 64,
+      "Ios16.batchNorm" : 61,
+      "Ios16.reshape" : 282,
+      "Ios16.rsqrt" : 48,
+      "Ios16.silu" : 47,
+      "Ios16.sqrt" : 61,
+      "Ios16.mul" : 193,
+      "Ios16.cos" : 1,
+      "SliceByIndex" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "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.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_CompVis_stable_diffusion_v1_4_unet",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ddc23a22d36976ef9f3aa7a3e0beeae533a51c4ebd46599f16f0b256b4e7e3
+size 645167616

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19eed961c0dd59703cc3d761df7de50759835a065caa165f50d13fed19fd7b3
+size 207

original/compiled/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fbe012c1925cee16f8490b1b342ff87f5dc9c8b1569ec15a81b0ab8db12134d
+size 753

original/compiled/VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,75 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Generated image normalized to range [-1, 1]",
+        "shape" : "[]",
+        "name" : "image",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "CompVis\/stable-diffusion-v1-4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/CompVis\/stable-diffusion-v1-4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 1,
+      "Ios16.sqrt" : 30,
+      "Ios16.sub" : 30,
+      "Transpose" : 7,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.conv" : 36,
+      "Ios16.add" : 45,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.realDiv" : 30,
+      "Ios16.reduceMean" : 60,
+      "Ios16.softmax" : 1,
+      "Ios16.batchNorm" : 30,
+      "Ios16.square" : 30,
+      "Ios16.reshape" : 70,
+      "Ios16.silu" : 29
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "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.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_CompVis_stable_diffusion_v1_4_vae_decoder",
+    "method" : "predict"
+  }
+]

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcb7ec979c9067bf1e3a25928e02df738f4c34ecb4a6de4ec657c25475851d3
+size 98993280

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18cd21de2cf3de6163f4b61bbbcf75ee60239a26067a44767ec3c6275ba53070
+size 207

original/compiled/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29273c145926933c9b20973beda0064ccefb537fac7743c700e11596bb11e92e
+size 759

original/compiled/VAEEncoder.mlmodelc/metadata.json

@@ -0,0 +1,75 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "The latent embeddings from the unet model from the input image.",
+        "shape" : "[]",
+        "name" : "latent",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "CompVis\/stable-diffusion-v1-4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/CompVis\/stable-diffusion-v1-4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Pad" : 3,
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 1,
+      "Ios16.sqrt" : 22,
+      "Ios16.sub" : 22,
+      "Transpose" : 7,
+      "Ios16.conv" : 28,
+      "Ios16.add" : 33,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.realDiv" : 22,
+      "Ios16.reduceMean" : 44,
+      "Ios16.softmax" : 1,
+      "Ios16.batchNorm" : 22,
+      "Ios16.square" : 22,
+      "Ios16.reshape" : 54,
+      "Ios16.silu" : 21
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "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" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_CompVis_stable_diffusion_v1_4_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:aa4cfc0f490c3d5f3c14d3046b35de4f4d2fb553351f2f552656c40a61cc2cd1
+size 68338112

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_safety_checker.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e6833d6fec4a1fbc394fd135ac77401f7a2c3cb48036ff3b6f85a713771f4e
+size 319163

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_safety_checker.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fc2c3d772614a206c40e0b0bb6202bcbc429df958d0f1d2ec59c8275869097
+size 607990114

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_safety_checker.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "A425DC83-318C-4D07-A405-9FDE9CAB1497": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "DF944445-24E2-4231-BEE1-48CF0817E853": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "DF944445-24E2-4231-BEE1-48CF0817E853"
+}

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323ef5b7416de3b25b370fd43645849e4a2166622bbe74bbba27843b9f927f5a
+size 174141

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_text_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d832c2bdadc6d96cd14ed8b6894087751bbc1c37eb3429aecfa0ca027c79a5
+size 139866304

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_text_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "8236094C-73BB-4C6B-8A08-1CDFD1B83108": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "9F51C68A-8A14-459A-B832-0FAE6FC3F130": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "9F51C68A-8A14-459A-B832-0FAE6FC3F130"
+}

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d121bf489e7808748a49c82e55dbbc9b761719ac3ecdafbcfb2aefa45732aecb
+size 822616

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_unet.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ddc23a22d36976ef9f3aa7a3e0beeae533a51c4ebd46599f16f0b256b4e7e3
+size 645167616

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_unet.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "4F0632EB-C2D8-4F4E-A452-2D3CCDE99DE1": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "86303345-1359-4F60-B769-2BE1E0EDB222": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "4F0632EB-C2D8-4F4E-A452-2D3CCDE99DE1"
+}

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060d79be82c2f22f453b8b9b9744623caf7b6bad7070caa37de5ce7e2ebeddec
+size 156810

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_vae_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcb7ec979c9067bf1e3a25928e02df738f4c34ecb4a6de4ec657c25475851d3
+size 98993280

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_vae_decoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "7F1E9335-2C45-4345-B0F3-C813658B2A17": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "8A5BE951-F50F-40C8-B9FB-3D8FB0DD7BFA": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "7F1E9335-2C45-4345-B0F3-C813658B2A17"
+}

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_vae_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e23068aa1c9252c34a1f025b8ebb5cdd394af2a3a2ed0c3d46a67454b7af89
+size 120679

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_vae_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4cfc0f490c3d5f3c14d3046b35de4f4d2fb553351f2f552656c40a61cc2cd1
+size 68338112

original/packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_vae_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "155D7B02-326E-4795-B625-92CCDC5BB42A": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "90BF0499-C384-44F1-8626-6B8A06CE606E": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "90BF0499-C384-44F1-8626-6B8A06CE606E"
+}

split_einsum_v2/compiled/SafetyChecker.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9069793905bd64c61471662d247051f975c417659c7a9dd4ed535bb9f09563
+size 207

split_einsum_v2/compiled/SafetyChecker.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb231ab31095b3b27b7f8e4b94b2554adcc3def4c6c486b6b6da81b55207a616
+size 1413

split_einsum_v2/compiled/SafetyChecker.mlmodelc/metadata.json

@@ -0,0 +1,122 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Identical to the input `images`. If safety checker detected any sensitive content, the corresponding image is replaced with a blank image (zeros)",
+        "shape" : "[]",
+        "name" : "filtered_images",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Indicates whether the safety checker model found any sensitive content in the given image",
+        "shape" : "[]",
+        "name" : "has_nsfw_concepts",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "Concept scores are the scores before thresholding at zero yields the `has_nsfw_concepts` output. These scores can be used to tune the `adjustment` input",
+        "shape" : "[]",
+        "name" : "concept_scores",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "CompVis\/stable-diffusion-v1-4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/CompVis\/stable-diffusion-v1-4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 121,
+      "Ios16.scatterNd" : 1,
+      "Ios16.softmax" : 24,
+      "Ios16.linear" : 147,
+      "Ios16.add" : 51,
+      "Concat" : 1,
+      "Ios16.realDiv" : 1,
+      "Ios16.sigmoid" : 24,
+      "Ios16.reduceSum" : 3,
+      "Tile" : 4,
+      "Ios16.greater" : 4,
+      "Shape" : 1,
+      "ExpandDims" : 5,
+      "Ios16.cast" : 7,
+      "Ios16.clip" : 1,
+      "Ios16.conv" : 1,
+      "Ios16.abs" : 1,
+      "Ios16.layerNorm" : 50,
+      "Ios16.matmul" : 48,
+      "Ios16.pow" : 2,
+      "Ios16.reshape" : 193,
+      "SliceByIndex" : 2,
+      "Ios16.mul" : 73,
+      "NonZero" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3 × 224 × 224)",
+        "shortDescription" : "The normalized image input tensor resized to (224x224) in channels-first (BCHW) format",
+        "shape" : "[1, 3, 224, 224]",
+        "name" : "clip_input",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 512 × 3)",
+        "shortDescription" : "Output of the vae_decoder (512x512) in channels-last (BHWC) format",
+        "shape" : "[1, 512, 512, 3]",
+        "name" : "images",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1)",
+        "shortDescription" : "Bias added to the concept scores to trade off increased recall for reduce precision in the safety checker classifier",
+        "shape" : "[1]",
+        "name" : "adjustment",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_CompVis_stable_diffusion_v1_4_safety_checker",
+    "method" : "predict"
+  }
+]

split_einsum_v2/compiled/SafetyChecker.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d6b7eb1e335140c10536c384a610aa05a0c21b01242eed905bca5abc64667c
+size 607990114

split_einsum_v2/compiled/TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270b2f4719eeacb851afbd8e0b6b1945050a6ffee57f04ec85227727e8bf5e04
+size 207