Use compiled coreml models

mlpackages/.gitattributes

@@ -1,36 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-01.png filter=lfs diff=lfs merge=lfs -text

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder.mlpackage/Data/com.apple.CoreML/FeatureDescriptions.json

@@ -1,18 +0,0 @@
-{
-  "Outputs" : {
-    "pooled_outputs" : {
-      "MLFeatureShortDescription" : "The version of the `last_hidden_state` output after pooling"
-    },
-    "hidden_embeds" : {
-      "MLFeatureShortDescription" : "Hidden states after the encoder layers"
-    }
-  },
-  "Inputs" : {
-    "input_ids" : {
-      "MLFeatureShortDescription" : "The token ids that represent the input text"
-    }
-  },
-  "TrainingInputs" : {
-
-  }
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder.mlpackage/Data/com.apple.CoreML/Metadata.json

@@ -1,10 +0,0 @@
-{
-  "MLModelVersionStringKey" : "stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelDescriptionKey" : "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.",
-  "MLModelCreatorDefinedKey" : {
-    "com.github.apple.coremltools.version" : "7.0b1",
-    "com.github.apple.coremltools.source" : "torch==2.0.1+cu117"
-  },
-  "MLModelAuthorKey" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelLicenseKey" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder.mlpackage/Manifest.json

@@ -1,30 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "2E437C75-2D29-4906-9BBF-06B4F60AF608": {
-            "author": "com.apple.CoreML",
-            "description": "External Metadata Overlay",
-            "name": "Metadata.json",
-            "path": "com.apple.CoreML/Metadata.json"
-        },
-        "3d765fc2-d834-4477-9cf7-818901242816": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "58CF0F86-0A4C-4478-B878-FB21979F2094": {
-            "author": "com.apple.CoreML",
-            "description": "External FeatureDescription Overlay",
-            "name": "FeatureDescriptions.json",
-            "path": "com.apple.CoreML/FeatureDescriptions.json"
-        },
-        "5fc727d7-449d-4885-8c48-b3b711dfed7b": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "5fc727d7-449d-4885-8c48-b3b711dfed7b"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder_2.mlpackage/Data/com.apple.CoreML/FeatureDescriptions.json

@@ -1,18 +0,0 @@
-{
-  "Outputs" : {
-    "pooled_outputs" : {
-      "MLFeatureShortDescription" : "The version of the `last_hidden_state` output after pooling"
-    },
-    "hidden_embeds" : {
-      "MLFeatureShortDescription" : "Hidden states after the encoder layers"
-    }
-  },
-  "Inputs" : {
-    "input_ids" : {
-      "MLFeatureShortDescription" : "The token ids that represent the input text"
-    }
-  },
-  "TrainingInputs" : {
-
-  }
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder_2.mlpackage/Data/com.apple.CoreML/Metadata.json

@@ -1,10 +0,0 @@
-{
-  "MLModelVersionStringKey" : "stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelDescriptionKey" : "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.",
-  "MLModelCreatorDefinedKey" : {
-    "com.github.apple.coremltools.version" : "7.0b1",
-    "com.github.apple.coremltools.source" : "torch==2.0.1+cu117"
-  },
-  "MLModelAuthorKey" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelLicenseKey" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder_2.mlpackage/Manifest.json

@@ -1,30 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "1003fcc7-51c2-44b1-bfd2-71eaffb11598": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "5bff403e-2a80-4472-b7fe-4c3438e76e85": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        },
-        "66E76242-93D0-4D4D-8D64-697552EC6C38": {
-            "author": "com.apple.CoreML",
-            "description": "External FeatureDescription Overlay",
-            "name": "FeatureDescriptions.json",
-            "path": "com.apple.CoreML/FeatureDescriptions.json"
-        },
-        "8DF8F909-251F-4BFD-BFA3-F72860B2F27D": {
-            "author": "com.apple.CoreML",
-            "description": "External Metadata Overlay",
-            "name": "Metadata.json",
-            "path": "com.apple.CoreML/Metadata.json"
-        }
-    },
-    "rootModelIdentifier": "5bff403e-2a80-4472-b7fe-4c3438e76e85"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_unet.mlpackage/Data/com.apple.CoreML/FeatureDescriptions.json

@@ -1,27 +0,0 @@
-{
-  "Outputs" : {
-    "noise_pred" : {
-      "MLFeatureShortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process"
-    }
-  },
-  "Inputs" : {
-    "encoder_hidden_states" : {
-      "MLFeatureShortDescription" : "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."
-    },
-    "sample" : {
-      "MLFeatureShortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion"
-    },
-    "timestep" : {
-      "MLFeatureShortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule"
-    },
-    "time_ids" : {
-      "MLFeatureShortDescription" : ""
-    },
-    "text_embeds" : {
-      "MLFeatureShortDescription" : ""
-    }
-  },
-  "TrainingInputs" : {
-
-  }
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_unet.mlpackage/Data/com.apple.CoreML/Metadata.json

@@ -1,11 +0,0 @@
-{
-  "MLModelVersionStringKey" : "stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelDescriptionKey" : "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.",
-  "MLModelCreatorDefinedKey" : {
-    "com.github.apple.coremltools.version" : "7.0b1",
-    "com.github.apple.coremltools.source" : "torch==2.0.1+cu117",
-    "com.github.apple.ml-stable-diffusion.version" : "1.0.0"
-  },
-  "MLModelAuthorKey" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelLicenseKey" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d76b3e630fc6936ba2b10f20364290b702e2a1a4d44b2d147133a52dd86bbe5a
-size 2028342

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_unet.mlpackage/Manifest.json

@@ -1,30 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "018FAE61-4A61-4AC6-A136-4E007EDFC6B2": {
-            "author": "com.apple.CoreML",
-            "description": "External Metadata Overlay",
-            "name": "Metadata.json",
-            "path": "com.apple.CoreML/Metadata.json"
-        },
-        "55cd366d-d242-44ae-ac6b-0316d8671233": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "7F4E1119-020E-4F7A-BC28-AB8F3F0119EE": {
-            "author": "com.apple.CoreML",
-            "description": "External FeatureDescription Overlay",
-            "name": "FeatureDescriptions.json",
-            "path": "com.apple.CoreML/FeatureDescriptions.json"
-        },
-        "c34397a4-1dac-4188-a5c0-ea4e42c7e4e9": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "c34397a4-1dac-4188-a5c0-ea4e42c7e4e9"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_decoder.mlpackage/Data/com.apple.CoreML/FeatureDescriptions.json

@@ -1,15 +0,0 @@
-{
-  "Outputs" : {
-    "image" : {
-      "MLFeatureShortDescription" : "Generated image normalized to range [-1, 1]"
-    }
-  },
-  "Inputs" : {
-    "z" : {
-      "MLFeatureShortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion"
-    }
-  },
-  "TrainingInputs" : {
-
-  }
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_decoder.mlpackage/Data/com.apple.CoreML/Metadata.json

@@ -1,10 +0,0 @@
-{
-  "MLModelVersionStringKey" : "stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelDescriptionKey" : "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.",
-  "MLModelCreatorDefinedKey" : {
-    "com.github.apple.coremltools.version" : "7.0b1",
-    "com.github.apple.coremltools.source" : "torch==2.0.1"
-  },
-  "MLModelAuthorKey" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelLicenseKey" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_decoder.mlpackage/Manifest.json

@@ -1,30 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "0C4B4A84-E58C-4B55-9232-7AD156C36DF1": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        },
-        "63939630-D849-41F2-B7BB-9439F4215E25": {
-            "author": "com.apple.CoreML",
-            "description": "External FeatureDescription Overlay",
-            "name": "FeatureDescriptions.json",
-            "path": "com.apple.CoreML/FeatureDescriptions.json"
-        },
-        "920AF9A5-7F1B-4655-9367-780D11D0CACC": {
-            "author": "com.apple.CoreML",
-            "description": "External Metadata Overlay",
-            "name": "Metadata.json",
-            "path": "com.apple.CoreML/Metadata.json"
-        },
-        "FF129861-DA4E-4A61-A51B-4E991CC3DAEA": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        }
-    },
-    "rootModelIdentifier": "0C4B4A84-E58C-4B55-9232-7AD156C36DF1"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_encoder.mlpackage/Data/com.apple.CoreML/FeatureDescriptions.json

@@ -1,15 +0,0 @@
-{
-  "Outputs" : {
-    "latent" : {
-      "MLFeatureShortDescription" : "The latent embeddings from the unet model from the input image."
-    }
-  },
-  "Inputs" : {
-    "z" : {
-      "MLFeatureShortDescription" : "The input image to base the initial latents on normalized to range [-1, 1]"
-    }
-  },
-  "TrainingInputs" : {
-
-  }
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_encoder.mlpackage/Data/com.apple.CoreML/Metadata.json

@@ -1,10 +0,0 @@
-{
-  "MLModelVersionStringKey" : "stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelDescriptionKey" : "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.",
-  "MLModelCreatorDefinedKey" : {
-    "com.github.apple.coremltools.version" : "7.0b1",
-    "com.github.apple.coremltools.source" : "torch==2.0.1+cu117"
-  },
-  "MLModelAuthorKey" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0",
-  "MLModelLicenseKey" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)"
-}

mlpackages/Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_encoder.mlpackage/Manifest.json

@@ -1,30 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "3B5695B7-E904-4965-8B20-FCA04DC0C035": {
-            "author": "com.apple.CoreML",
-            "description": "External FeatureDescription Overlay",
-            "name": "FeatureDescriptions.json",
-            "path": "com.apple.CoreML/FeatureDescriptions.json"
-        },
-        "78a885c8-8779-418b-9bfe-cf0ac2e82e6f": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "7EE511A5-DB53-4061-8155-ED696C539F30": {
-            "author": "com.apple.CoreML",
-            "description": "External Metadata Overlay",
-            "name": "Metadata.json",
-            "path": "com.apple.CoreML/Metadata.json"
-        },
-        "9e7ab831-1e35-4406-be6a-48236315c9c4": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "9e7ab831-1e35-4406-be6a-48236315c9c4"
-}

mlpackages/{Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder_2.mlpackage/Data/com.apple.CoreML/model.mlmodel → TextEncoder.mlmodelc/analytics/coremldata.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb832076a7e67ff890e274281c5bf83c3be6743b8214d0c6df95b88fce6711f
-size 418221
+oid sha256:f732919fa370a1b7b09ec2b227539269b6543149a2b0dbae95cc4cf350e4b697
+size 207

mlpackages/{Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel → TextEncoder.mlmodelc/coremldata.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee32c2ed8e0d8dc35e513bd328fda885af82ec3d252f50037cc70fc5d966860d
-size 119397
+oid sha256:9ff26866d8d8fbb4e53a0628f8aab5f7edf1b3ec763a96e6812c8f7fbf4c9827
+size 825

mlpackages/TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,82 @@
+[
+  {
+    "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" : "Hidden states after the encoder layers",
+        "shape" : "[]",
+        "name" : "hidden_embeds",
+        "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" : "diffusers\/stable-diffusion-xl-base-1.0",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/diffusers\/stable-diffusion-xl-base-1.0",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 36,
+      "Ios16.layerNorm" : 25,
+      "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+cu117"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_diffusers_stable_diffusion_xl_base_1_0_text_encoder",
+    "method" : "predict"
+  }
+]

mlpackages/{Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel → TextEncoder2.mlmodelc/analytics/coremldata.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb66e41edf6678acc5df408ffb294157df24996f810f649d953d2997df2f40cc
-size 143700
+oid sha256:eef66b480388714bb62f2f0f2f97a8953e44acbb00b25f9a9fd63c759f4f0e83
+size 207

mlpackages/{Stable_Diffusion_version_womboai_coreml-stable-diffusion-xl-base-1.0_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel → TextEncoder2.mlmodelc/coremldata.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fc64f553e0f6be677899106f40ed3bf85eceb3d0b55f90022252cb8dff1d4a
-size 161160
+oid sha256:9ff26866d8d8fbb4e53a0628f8aab5f7edf1b3ec763a96e6812c8f7fbf4c9827
+size 825

mlpackages/TextEncoder2.mlmodelc/metadata.json

@@ -0,0 +1,82 @@
+[
+  {
+    "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" : "Hidden states after the encoder layers",
+        "shape" : "[]",
+        "name" : "hidden_embeds",
+        "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" : "diffusers\/stable-diffusion-xl-base-1.0",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/diffusers\/stable-diffusion-xl-base-1.0",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 32,
+      "Ios16.layerNorm" : 65,
+      "Stack" : 1,
+      "Transpose" : 160,
+      "Ios16.linear" : 193,
+      "Ios16.add" : 97,
+      "Ios16.matmul" : 64,
+      "Ios16.gelu" : 32,
+      "Ios16.softmax" : 32,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 320,
+      "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+cu117"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_diffusers_stable_diffusion_xl_base_1_0_text_encoder_2",
+    "method" : "predict"
+  }
+]

mlpackages/Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3831a13c76df3097f4ae659ef46a7f6604f93b45c1a5f8d14e362424d15e1f
+size 207

mlpackages/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aea3887ffdc8e059925f3981259e1cd3227b827e5f91edff613c73ac0ea16f6
+size 1338

mlpackages/Unet.mlmodelc/metadata.json

@@ -0,0 +1,122 @@
+[
+  {
+    "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" : "diffusers\/stable-diffusion-xl-base-1.0",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/diffusers\/stable-diffusion-xl-base-1.0",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "UpsampleNearestNeighbor" : 2,
+      "Ios16.reduceMean" : 512,
+      "Ios16.sin" : 2,
+      "Ios16.softmax" : 140,
+      "Split" : 70,
+      "Ios16.add" : 722,
+      "Concat" : 14,
+      "Ios16.realDiv" : 46,
+      "Ios16.square" : 46,
+      "ExpandDims" : 6,
+      "Ios16.sub" : 256,
+      "Ios16.cast" : 1,
+      "Ios16.conv" : 794,
+      "Ios16.gelu" : 70,
+      "Ios16.matmul" : 280,
+      "Ios16.reshape" : 675,
+      "Ios16.batchNorm" : 46,
+      "Ios16.rsqrt" : 210,
+      "Ios16.silu" : 38,
+      "Ios16.sqrt" : 46,
+      "SliceByIndex" : 4,
+      "Ios16.mul" : 842,
+      "Ios16.cos" : 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 × 128 × 128)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 128, 128]",
+        "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 × 2048 × 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, 2048, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 12)",
+        "shortDescription" : "",
+        "shape" : "[12]",
+        "name" : "time_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 1280)",
+        "shortDescription" : "",
+        "shape" : "[2, 1280]",
+        "name" : "text_embeds",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1+cu117",
+      "com.github.apple.ml-stable-diffusion.version" : "1.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_diffusers_stable_diffusion_xl_base_1_0_unet",
+    "method" : "predict"
+  }
+]

mlpackages/VAEDecoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac2854504d7f6bfdc5645982dd965cca9cc8c12b9fdd2493cf50cd583684cc2
+size 207

mlpackages/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766fce2585587fe93a1d32e09bc4d63ad45335ea62239f11b193e481b5888258
+size 773

mlpackages/VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,74 @@
+[
+  {
+    "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" : "diffusers\/stable-diffusion-xl-base-1.0",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/diffusers\/stable-diffusion-xl-base-1.0",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float32",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "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 (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 × 4 × 128 × 128)",
+        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
+        "shape" : "[1, 4, 128, 128]",
+        "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_diffusers_stable_diffusion_xl_base_1_0_vae_decoder",
+    "method" : "predict"
+  }
+]

mlpackages/VAEEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e44297c358d64101602d9abfe4d6c9fb96ddb3b120f84fbb74001aa4312cf93
+size 207

mlpackages/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7269e365034d061c3ad035d9a5b7c38864d7db71bee6fb7545c97a4942a865f1
+size 783

mlpackages/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" : "diffusers\/stable-diffusion-xl-base-1.0",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/diffusers\/stable-diffusion-xl-base-1.0",
+    "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",
+      "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 × 1024 × 1024)",
+        "shortDescription" : "The input image to base the initial latents on normalized to range [-1, 1]",
+        "shape" : "[1, 3, 1024, 1024]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0b1",
+      "com.github.apple.coremltools.source" : "torch==2.0.1+cu117"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_diffusers_stable_diffusion_xl_base_1_0_vae_encoder",
+    "method" : "predict"
+  }
+]