Upload folder using huggingface_hub

coreml-segmind-small-sd.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858107b1008feef7199aa8b0c347031ea09e5d8564500e5b7ca0d12bccd1a6a4
+size 257136461

split_einsum_v2/compiled/TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63d66e6313807d2055471811f9b1b4e744ce078e4a7d81fb1e849e0486f58fb
+size 243

split_einsum_v2/compiled/TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81ff80d1029e1731bd5cc36ea371b9e44ba84c041d6427aab11d35c9eac8ecb
+size 804

split_einsum_v2/compiled/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" : "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" : "Vishnou\/tiny-sd",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/Vishnou\/tiny-sd",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (2 bits))",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 36,
+      "Ios16.layerNorm" : 25,
+      "Ios16.constexprLutToDense" : 86,
+      "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==2.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_Vishnou_tiny_sd_text_encoder",
+    "method" : "predict"
+  }
+]

split_einsum_v2/compiled/TextEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695cedd3fe1d0c0c1e6f8b164f777a15799baa94bd4a2e8646a0a7315c9016ea
+size 97331520

split_einsum_v2/compiled/Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1c36fee265a4c0aeb7be024e20e99cbcdf6bef049b7b146d85a17fc54d929b
+size 243

split_einsum_v2/compiled/Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdec370d624df53dfadfc25c68163d7c57043b5660d605cde57080f2ec4b4b7
+size 1237

split_einsum_v2/compiled/Unet.mlmodelc/metadata.json

@@ -0,0 +1,105 @@
+[
+  {
+    "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" : "Vishnou\/tiny-sd",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/Vishnou\/tiny-sd",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (2 bits))",
+    "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 18,
+      "UpsampleNearestNeighbor" : 2,
+      "Ios16.reduceMean" : 110,
+      "Ios16.sin" : 1,
+      "Ios16.softmax" : 528,
+      "Split" : 9,
+      "Ios16.add" : 136,
+      "Concat" : 122,
+      "Ios16.realDiv" : 28,
+      "Ios16.square" : 28,
+      "ExpandDims" : 3,
+      "Ios16.sub" : 55,
+      "Ios16.cast" : 1,
+      "Ios16.conv" : 151,
+      "Ios16.constexprLutToDense" : 164,
+      "Ios16.einsum" : 1056,
+      "Ios16.gelu" : 9,
+      "Ios16.batchNorm" : 28,
+      "Ios16.reshape" : 74,
+      "Ios16.rsqrt" : 27,
+      "Ios16.silu" : 21,
+      "Ios16.sqrt" : 28,
+      "Ios16.mul" : 619,
+      "Ios16.cos" : 1,
+      "SliceByIndex" : 914
+    },
+    "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==2.0.0",
+      "com.github.apple.ml-stable-diffusion.version" : "1.1.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_Vishnou_tiny_sd_unet",
+    "method" : "predict"
+  }
+]

split_einsum_v2/compiled/Unet.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43efdfd11a4566b30f384d7af3fe0800ac93fa66d3f5318931373f7dc9f99010
+size 81153024

split_einsum_v2/compiled/VAEDecoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a617ff81af12f111477d0bacf35c261fc1d6ffb349f5a0d4d181018a498885c3
+size 243

split_einsum_v2/compiled/VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497d6341788ca88e0f47651b1caef2a9248b394248d11df7758592b730c188c3
+size 731

split_einsum_v2/compiled/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" : "Vishnou\/tiny-sd",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/Vishnou\/tiny-sd",
+    "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==2.0.0"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_Vishnou_tiny_sd_vae_decoder",
+    "method" : "predict"
+  }
+]

split_einsum_v2/compiled/VAEDecoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119281547d5adfcf81db26e1a559cadaff78cf98a73a6b23ce3703f696611ea9
+size 98993280

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aeec082b948b799d5cb388742db9c5604ec937c8a51855fc50a72af4b3cd3f1
+size 171552

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_text_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c25c461bb8ed5ef16842e6b2fdec7b0af52c66b99053a99e7b479957ca2bc79
+size 97331520

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_text_encoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "0664121F-8D59-4133-8318-9F7CD3F61888": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "77053C11-42F1-47CC-BECF-48ED176A0866": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "77053C11-42F1-47CC-BECF-48ED176A0866"
+}

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfc9d817ab29f5ace8cad773057bdb13ceb5d4c5d7cee8a528ff66d8f3cb9f6
+size 1482960

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_unet.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b84516fae9a7739ae78b74b982a8e95f7c540a69e59f71e9009046621165571
+size 81153024

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_unet.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "2F55AF92-0FDB-48B2-A297-4E3EAD9981B2": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "CE21C288-55DC-45DD-B3E4-E9F37FD097ED": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "2F55AF92-0FDB-48B2-A297-4E3EAD9981B2"
+}

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386a357bf589f79ce0efbe29cdbdf757d14874c11fefd4a3c054b7581eda34d9
+size 155766

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_vae_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119281547d5adfcf81db26e1a559cadaff78cf98a73a6b23ce3703f696611ea9
+size 98993280

split_einsum_v2/packages/Stable_Diffusion_version_Vishnou_tiny-sd_vae_decoder.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "44E1D720-D7D3-42EA-AE59-C8211EA46CA5": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "50BACCF7-E5FA-4CD0-82B8-224D883BF33E": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "44E1D720-D7D3-42EA-AE59-C8211EA46CA5"
+}