Adding files

TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc42c2465771ddb06778190f611cc29696fb0a5f64b327ba01fefa0db1b0e94b
+size 243

TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4f8bbf1a17a22e5912d0bd547d84d8c7b0c94822c4ac59fa1ff043c2e16b33
+size 961

TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,84 @@
+[
+  {
+    "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" : "Hidden states after the encoder layers",
+        "shape" : "[1, 77, 768]",
+        "name" : "hidden_embeds",
+        "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" : "turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "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.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers_text_encoder",
+    "method" : "predict"
+  }
+]

TextEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8fb36808ab8d86254cae8c934591223124ffff0c8c6b213c52d9e3986d4ae0
+size 246145536

TextEncoder2.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939e4df0cbed526bc2ace0f21bff7b4345562068bc2bbbfb49ff5f3d04b217b8
+size 243

TextEncoder2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccab3111a97ae96a289f1e1809711f79d52fe4598fa7e56ed070a30b949131cc
+size 961

TextEncoder2.mlmodelc/metadata.json

@@ -0,0 +1,84 @@
+[
+  {
+    "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 × 1280)",
+        "shortDescription" : "Hidden states after the encoder layers",
+        "shape" : "[1, 77, 1280]",
+        "name" : "hidden_embeds",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 1280)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[1, 1280]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "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",
+      "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.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers_text_encoder_2",
+    "method" : "predict"
+  }
+]

TextEncoder2.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09358857334c71c8993aa4565766dd5dbc3c56cfe0ebca5b188369026ed0a900
+size 1389367424

Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc04a07715e0400945008ef2fb3360f59a61069b9c2d5793afb253318688df13
+size 243

Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149a68be62f848a315718547537f6d154b4b98a333819cfb7b0c25be5cbbb515
+size 1713

Unet.mlmodelc/metadata.json

@@ -0,0 +1,124 @@
+[
+  {
+    "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 × 96 × 96)",
+        "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
+        "shape" : "[2, 4, 96, 96]",
+        "name" : "noise_pred",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float16",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "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" : 676,
+      "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",
+      "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 × 96 × 96)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 96, 96]",
+        "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 2 × 6)",
+        "shortDescription" : "Additional embeddings that if specified are added to the embeddings that are passed along to the UNet blocks.",
+        "shape" : "[2, 6]",
+        "name" : "time_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 1280)",
+        "shortDescription" : "Additional embeddings from text_encoder_2 that if specified are added to the embeddings that are passed along to the UNet blocks.",
+        "shape" : "[2, 1280]",
+        "name" : "text_embeds",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.ml-stable-diffusion.version" : "1.1.0",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers_unet",
+    "method" : "predict"
+  }
+]

Unet.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca61a9e9d3ae653611841f73322138edc73ce5b0067dd3013c6424454b6f401c
+size 5135067072

VAEDecoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18191a2b07696a539adfb10f33899c47b8bf1640b95d77a7da0b8872e2f02289
+size 243

VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ff78fb3be7dba159a45ef2fb91a6d9adf150ebeea2d978ed2e0de46d8103fe
+size 910

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 × 768 × 768)",
+        "shortDescription" : "Generated image normalized to range [-1, 1]",
+        "shape" : "[1, 3, 768, 768]",
+        "name" : "image",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float32",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "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",
+      "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 × 4 × 96 × 96)",
+        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
+        "shape" : "[1, 4, 96, 96]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers_vae_decoder",
+    "method" : "predict"
+  }
+]

VAEDecoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07e9d7970c403188483df17fa736254aa9e1201f395a7fb05a8ccacf9e9a807
+size 197977216

VAEEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd09da9da725147cd68f67d424955f7f7c95bfd4fa8392d387c0f7b47884ac98
+size 243

VAEEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c641e2ef913abeaa33d28050f3acf074c56a4d07f56cc4a843d169285156541b
+size 914

VAEEncoder.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 × 8 × 96 × 96)",
+        "shortDescription" : "The latent embeddings from the unet model from the input image.",
+        "shape" : "[1, 8, 96, 96]",
+        "name" : "latent",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float32",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "mlProgramOperationTypeHistogram" : {
+      "Pad" : 3,
+      "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 (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 × 3 × 768 × 768)",
+        "shortDescription" : "The input image to base the initial latents on normalized to range [-1, 1]",
+        "shape" : "[1, 3, 768, 768]",
+        "name" : "x",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.2",
+      "com.github.apple.coremltools.version" : "7.1"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_turbovisionxlSuperFastXLBasedOnNew_tvxlV431Bakedvae_diffusers_vae_encoder",
+    "method" : "predict"
+  }
+]

VAEEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b07c246e38dc348797d1c723bf6eaa325fbd4d5cc38430d76eac757128b164a
+size 136668992