Initial commit

SafetyChecker.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b0bf1174de40d589a2f5a77b6782ce86136a9e44a916e90f056f2167335ace
+size 243

SafetyChecker.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a711fac00518725af06c2f9d60696c1ecb65b67f3bebc420cdea5942b58516c
+size 1411

SafetyChecker.mlmodelc/metadata.json

@@ -0,0 +1,123 @@
+[
+  {
+    "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 × 512 × 512 × 3)",
+        "shortDescription" : "Identical to the input `images`. If safety checker detected any sensitive content, the corresponding image is replaced with a blank image (zeros)",
+        "shape" : "[1, 512, 512, 3]",
+        "name" : "filtered_images",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 1 × 1 × 1)",
+        "shortDescription" : "Indicates whether the safety checker model found any sensitive content in the given image",
+        "shape" : "[1, 1, 1, 1]",
+        "name" : "has_nsfw_concepts",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 17)",
+        "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" : "[1, 17]",
+        "name" : "concept_scores",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "Meina\/MeinaHentai_V4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/Meina\/MeinaHentai_V4",
+    "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",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3 × 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" : "7.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_Meina_MeinaHentai_V4_safety_checker",
+    "method" : "predict"
+  }
+]

SafetyChecker.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efaedaa8ce3c917d547c03355833923eab9ab6bfb15e42306d8673ca896328f
+size 607990114

TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904bcf94bad606dc531d861c5239cf2506dbe41de0ab57c2b4150df7ff796704
+size 243

TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6859d33d2accf86f3103b22ca1d0145563cc244fd68bb0c7bf511b743d932a07
+size 814

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 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" : "Meina\/MeinaHentai_V4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/Meina\/MeinaHentai_V4",
+    "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",
+      "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.version" : "7.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_Meina_MeinaHentai_V4_text_encoder",
+    "method" : "predict"
+  }
+]

TextEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d075762f637618c4681a816b814820a3221fc64f14a45a7c271c65d5a6fde817
+size 246145536

Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5107178b776e7254fda43189acf05dd2fd43e076630fbd80dd01b8114a605ace
+size 243

Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd27a152072ca7b65afb7f66f8f32e7db94413006fa3d13c48581dfe07d8f43
+size 1247

Unet.mlmodelc/metadata.json

@@ -0,0 +1,104 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 4 × 64 × 64)",
+        "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
+        "shape" : "[2, 4, 64, 64]",
+        "name" : "noise_pred",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "Meina\/MeinaHentai_V4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/Meina\/MeinaHentai_V4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 32,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.reduceMean" : 218,
+      "Ios16.sin" : 1,
+      "Ios16.softmax" : 256,
+      "Split" : 16,
+      "Ios16.add" : 265,
+      "Concat" : 46,
+      "Ios16.realDiv" : 61,
+      "Ios16.square" : 61,
+      "ExpandDims" : 3,
+      "Ios16.sub" : 109,
+      "Ios16.cast" : 1,
+      "Ios16.conv" : 282,
+      "Ios16.einsum" : 512,
+      "Ios16.gelu" : 16,
+      "Ios16.reshape" : 154,
+      "Ios16.batchNorm" : 61,
+      "Ios16.rsqrt" : 48,
+      "Ios16.silu" : 47,
+      "Ios16.sqrt" : 61,
+      "SliceByIndex" : 770,
+      "Ios16.mul" : 417,
+      "Ios16.cos" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 4 × 64 × 64)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 64, 64]",
+        "name" : "sample",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2)",
+        "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule",
+        "shape" : "[2]",
+        "name" : "timestep",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 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" : "7.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.1",
+      "com.github.apple.ml-stable-diffusion.version" : "1.1.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_Meina_MeinaHentai_V4_unet",
+    "method" : "predict"
+  }
+]

Unet.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530dd850c56dbf8cab096b4ddef0cf19504db9ec41c0a33d01134a0bfc3a5f9d
+size 1719117696

VAEDecoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a773c70dab197f30135eb6bdf95b4839f44d16a9c1ad88c60eaa3ff17e93f1
+size 243

VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce0af71733fce8ea2c5ff9c52f74090d7c87dbc7977320ea2745ca1279b51d0
+size 741

VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,76 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 3 × 512 × 512)",
+        "shortDescription" : "Generated image normalized to range [-1, 1]",
+        "shape" : "[1, 3, 512, 512]",
+        "name" : "image",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "Meina\/MeinaHentai_V4",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/Meina\/MeinaHentai_V4",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 2,
+      "Ios16.sqrt" : 30,
+      "Ios16.sub" : 30,
+      "Transpose" : 6,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.conv" : 36,
+      "Ios16.add" : 46,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.realDiv" : 30,
+      "Ios16.reduceMean" : 60,
+      "Ios16.softmax" : 1,
+      "Ios16.batchNorm" : 29,
+      "Ios16.square" : 30,
+      "Ios16.reshape" : 65,
+      "Ios16.silu" : 29
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
+        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
+        "shape" : "[1, 4, 64, 64]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "7.0",
+      "com.github.apple.coremltools.source" : "torch==2.0.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_Meina_MeinaHentai_V4_vae_decoder",
+    "method" : "predict"
+  }
+]

VAEDecoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af0701e94d0e5ff97b292b9a3f35efa642a5c4af40f383243fdc4fb96123cb6
+size 98993280