VAE Encoder (#4)

.gitignore

@@ -0,0 +1,2 @@
+.DS_Store
+

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee76fbae1fa08a0d7bd18b2eb1f0324f9fdba01656f441a3e8357f08bb6345a
+size 207

original/compiled/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854e552c6e9273ef52b93a0fd2013399421450f497fcd327eb8aa371a2e5f46d
+size 1284

original/compiled/VAEEncoder.mlmodelc/metadata.json

@@ -0,0 +1,118 @@
+[
+  {
+    "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_dist",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stabilityai\/stable-diffusion-2-base",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 7,
+      "Ios16.exp" : 1,
+      "Ios16.reduceMean" : 44,
+      "Ios16.softmax" : 1,
+      "Split" : 1,
+      "Ios16.linear" : 4,
+      "Ios16.add" : 35,
+      "Ios16.realDiv" : 22,
+      "Ios16.square" : 22,
+      "Pad" : 3,
+      "Ios16.sub" : 22,
+      "Ios16.cast" : 1,
+      "Ios16.clip" : 1,
+      "Ios16.conv" : 28,
+      "Ios16.matmul" : 2,
+      "Ios16.reshape" : 54,
+      "Ios16.batchNorm" : 22,
+      "Ios16.silu" : 21,
+      "Ios16.sqrt" : 22,
+      "Ios16.mul" : 6
+    },
+    "computePrecision" : "Mixed (Float32, Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3 × 512 × 512)",
+        "shortDescription" : "An image of the correct size to create the latent space with, image2image and in-painting.",
+        "shape" : "[1, 3, 512, 512]",
+        "name" : "sample",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
+        "shortDescription" : "Latent noise for `DiagonalGaussianDistribution` operation.",
+        "shape" : "[1, 4, 64, 64]",
+        "name" : "diagonal_noise",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
+        "shortDescription" : "Latent noise for use with strength parameter of image2image",
+        "shape" : "[1, 4, 64, 64]",
+        "name" : "noise",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1)",
+        "shortDescription" : "Precalculated `sqrt_alphas_cumprod` value based on strength and the current schedular's alphasCumprod values",
+        "shape" : "[1, 1]",
+        "name" : "sqrt_alphas_cumprod",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1)",
+        "shortDescription" : "Precalculated `sqrt_one_minus_alphas_cumprod` value based on strength and the current schedular's alphasCumprod values",
+        "shape" : "[1, 1]",
+        "name" : "sqrt_one_minus_alphas_cumprod",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "6.1",
+      "com.github.apple.coremltools.source" : "torch==1.13.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_vae_encoder",
+    "method" : "predict"
+  }
+]

original/compiled/VAEEncoder.mlmodelc/model.mil

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd529b933adc7e28b4057051eb816d753241246416bceacf25eb844e2b64d4a
+size 137752

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7ad3fbf4898564c46e08732ce223712961270064549b06bdc95ec22a6e88b1
+size 68370240

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69544ea13c1a7b3115c01eb2e775a10136832d6ff91a074faf11b75f241d726c
+size 117460

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7ad3fbf4898564c46e08732ce223712961270064549b06bdc95ec22a6e88b1
+size 68370240

original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "38BC24FA-2978-4B03-AF04-231A43CBF74C": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "4627B776-3BCE-4766-960C-5877AC8F5A80": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "4627B776-3BCE-4766-960C-5877AC8F5A80"
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee76fbae1fa08a0d7bd18b2eb1f0324f9fdba01656f441a3e8357f08bb6345a
+size 207

split_einsum/compiled/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854e552c6e9273ef52b93a0fd2013399421450f497fcd327eb8aa371a2e5f46d
+size 1284

split_einsum/compiled/VAEEncoder.mlmodelc/metadata.json

@@ -0,0 +1,118 @@
+[
+  {
+    "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_dist",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stabilityai\/stable-diffusion-2-base",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 7,
+      "Ios16.exp" : 1,
+      "Ios16.reduceMean" : 44,
+      "Ios16.softmax" : 1,
+      "Split" : 1,
+      "Ios16.linear" : 4,
+      "Ios16.add" : 35,
+      "Ios16.realDiv" : 22,
+      "Ios16.square" : 22,
+      "Pad" : 3,
+      "Ios16.sub" : 22,
+      "Ios16.cast" : 1,
+      "Ios16.clip" : 1,
+      "Ios16.conv" : 28,
+      "Ios16.matmul" : 2,
+      "Ios16.reshape" : 54,
+      "Ios16.batchNorm" : 22,
+      "Ios16.silu" : 21,
+      "Ios16.sqrt" : 22,
+      "Ios16.mul" : 6
+    },
+    "computePrecision" : "Mixed (Float32, Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3 × 512 × 512)",
+        "shortDescription" : "An image of the correct size to create the latent space with, image2image and in-painting.",
+        "shape" : "[1, 3, 512, 512]",
+        "name" : "sample",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
+        "shortDescription" : "Latent noise for `DiagonalGaussianDistribution` operation.",
+        "shape" : "[1, 4, 64, 64]",
+        "name" : "diagonal_noise",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
+        "shortDescription" : "Latent noise for use with strength parameter of image2image",
+        "shape" : "[1, 4, 64, 64]",
+        "name" : "noise",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1)",
+        "shortDescription" : "Precalculated `sqrt_alphas_cumprod` value based on strength and the current schedular's alphasCumprod values",
+        "shape" : "[1, 1]",
+        "name" : "sqrt_alphas_cumprod",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1)",
+        "shortDescription" : "Precalculated `sqrt_one_minus_alphas_cumprod` value based on strength and the current schedular's alphasCumprod values",
+        "shape" : "[1, 1]",
+        "name" : "sqrt_one_minus_alphas_cumprod",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "6.1",
+      "com.github.apple.coremltools.source" : "torch==1.13.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_vae_encoder",
+    "method" : "predict"
+  }
+]

split_einsum/compiled/VAEEncoder.mlmodelc/model.mil

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd529b933adc7e28b4057051eb816d753241246416bceacf25eb844e2b64d4a
+size 137752

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5061f127d29e767db8e4703bdfaf6cf2e944d5d8a27e807c78828496de3ce267
+size 68370240

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69544ea13c1a7b3115c01eb2e775a10136832d6ff91a074faf11b75f241d726c
+size 117460

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5061f127d29e767db8e4703bdfaf6cf2e944d5d8a27e807c78828496de3ce267
+size 68370240

split_einsum/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "260E53C9-7E53-4C87-9FA8-161CC0D21FDF": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "70A48119-9715-487C-9953-FCA2BCE32D24": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "260E53C9-7E53-4C87-9FA8-161CC0D21FDF"
+}