Add 6-bit palettized CoreML Resources bundle

Resources/TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b1b8aef5cc0e40734d1110a6f8b9db13d47e46569a84712b5a218d39d42b66
+size 243

Resources/TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4112353c996bbec5e878feef1da00330f7cdf8c616d9a4f1cce0ece0c8ff8c0c
+size 970

Resources/TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,89 @@
+[
+  {
+    "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" : "\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "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" : 74,
+      "Transpose" : 48,
+      "Stack" : 1,
+      "Ios16.sigmoid" : 12,
+      "Ios16.linear" : 72,
+      "Ios16.add" : 37,
+      "Ios16.softmax" : 12,
+      "Ios16.matmul" : 24,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 48,
+      "Ios16.reduceArgmax" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 77)",
+        "shortDescription" : "The token ids that represent the input text",
+        "shape" : "[1, 77]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-06-22",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_m1_cyberrealistic_v9_diffusers_text_encoder",
+    "method" : "predict"
+  }
+]

Resources/TextEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff9e8cb03fb475cdf38c5417f1498c28e527ab882824e2dfb39b07dcbb03153
+size 139910080

Resources/Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97152e21b43fa5c6fddc6b19492ee847d28cc7d62b869f2284ed2b1308991844
+size 243

Resources/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b629d60086332c9fe0bf479dd9565f9a253f32a964601c751c8700de7065986e
+size 1403

Resources/Unet.mlmodelc/metadata.json

@@ -0,0 +1,110 @@
+[
+  {
+    "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" : "\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (6 bits))",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 32,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.reduceMean" : 122,
+      "Ios16.sin" : 1,
+      "Ios16.softmax" : 896,
+      "Split" : 16,
+      "Ios16.add" : 169,
+      "Concat" : 206,
+      "Ios16.realDiv" : 61,
+      "Ios16.square" : 61,
+      "ExpandDims" : 3,
+      "Ios16.sub" : 61,
+      "Ios16.sqrt" : 61,
+      "Ios16.conv" : 282,
+      "Ios16.constexprLutToDense" : 282,
+      "Ios16.einsum" : 1792,
+      "Ios16.layerNorm" : 48,
+      "SliceByIndex" : 1570,
+      "Ios16.batchNorm" : 61,
+      "Ios16.reshape" : 154,
+      "Ios16.silu" : 47,
+      "Ios16.gelu" : 16,
+      "Ios16.mul" : 913,
+      "Ios16.cos" : 1,
+      "Ios16.cast" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 4 × 64 × 64)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 64, 64]",
+        "name" : "sample",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2)",
+        "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule",
+        "shape" : "[2]",
+        "name" : "timestep",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 768 × 1 × 77)",
+        "shortDescription" : "Output embeddings from the associated text_encoder model to condition to generated image on text. A maximum of 77 tokens (~40 words) are allowed. Longer text is truncated. Shorter text does not reduce computation.",
+        "shape" : "[2, 768, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-06-22",
+      "com.github.apple.ml-stable-diffusion.version" : "1.1.0",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_m1_cyberrealistic_v9_diffusers_unet",
+    "method" : "predict"
+  }
+]

Resources/Unet.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb94804f746db7f42e05e3cee74edab7fd4af0848e829f845a34523b9e19294a
+size 645325440

Resources/VAEDecoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fde75218c3071d85fbeb5807160cb2f9aed134372f1dc821a31c762e326f73e
+size 243

Resources/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb8f902866f001c484353af8133c4986d1519a672cc5d54b10fbbb9a2335b07
+size 897

Resources/VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,81 @@
+[
+  {
+    "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" : "\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 2,
+      "Ios16.sub" : 30,
+      "Transpose" : 6,
+      "Ios16.sqrt" : 30,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.square" : 30,
+      "Ios16.add" : 46,
+      "Ios16.reduceMean" : 60,
+      "Ios16.realDiv" : 30,
+      "Ios16.conv" : 36,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.batchNorm" : 29,
+      "Ios16.softmax" : 1,
+      "Ios16.reshape" : 65,
+      "Ios16.silu" : 29
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 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.conversion_date" : "2026-06-22",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_m1_cyberrealistic_v9_diffusers_vae_decoder",
+    "method" : "predict"
+  }
+]

Resources/VAEDecoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c82c58d79c8f612c14437df9b7d354c68c66061242f2e9d9cbfedd1e2b2264e
+size 98993280

Resources/VAEEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a9ddd93b65c207948038f7d95c4e5e86658071e02d4abd593aa3bccc5aa5ac
+size 243

Resources/VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d52b977ac743580eebe9d1a97bc7b80271b2b5dc60fd2eb5f2316eb6533943b
+size 901

Resources/VAEEncoder.mlmodelc/metadata.json

@@ -0,0 +1,81 @@
+[
+  {
+    "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 × 8 × 64 × 64)",
+        "shortDescription" : "The latent embeddings from the unet model from the input image.",
+        "shape" : "[1, 8, 64, 64]",
+        "name" : "latent",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/\/Users\/m1\/cyberrealistic-v9-diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Pad" : 3,
+      "Ios16.cast" : 1,
+      "Ios16.mul" : 2,
+      "Ios16.sub" : 22,
+      "Ios16.sqrt" : 22,
+      "Transpose" : 6,
+      "Ios16.square" : 22,
+      "Ios16.add" : 34,
+      "Ios16.reduceMean" : 44,
+      "Ios16.realDiv" : 22,
+      "Ios16.conv" : 28,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.batchNorm" : 21,
+      "Ios16.softmax" : 1,
+      "Ios16.reshape" : 49,
+      "Ios16.silu" : 21
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 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" : "x",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-06-22",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version__Users_m1_cyberrealistic_v9_diffusers_vae_encoder",
+    "method" : "predict"
+  }
+]

Resources/VAEEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bf826e5ee1b455462aff0b34e3a469f5f58955ae715708962b1d81db92dc64
+size 68338112