[ { "shortDescription" : "ControlNet is a neural network structure to control diffusion models by adding extra conditions. Please refer to https:\/\/arxiv.org\/abs\/2302.05543 for details.", "metadataOutputVersion" : "3.0", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 320 × 128 × 128)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 320, 128, 128]", "name" : "additional_residual_0", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 320 × 128 × 128)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 320, 128, 128]", "name" : "additional_residual_1", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 320 × 128 × 128)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 320, 128, 128]", "name" : "additional_residual_2", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 320 × 64 × 64)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 320, 64, 64]", "name" : "additional_residual_3", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 640 × 64 × 64)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 640, 64, 64]", "name" : "additional_residual_4", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 640 × 64 × 64)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 640, 64, 64]", "name" : "additional_residual_5", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 640 × 32 × 32)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 640, 32, 32]", "name" : "additional_residual_6", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 1280 × 32 × 32)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 1280, 32, 32]", "name" : "additional_residual_7", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 1280 × 32 × 32)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 1280, 32, 32]", "name" : "additional_residual_8", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 1280 × 32 × 32)", "shortDescription" : "One of the outputs of each downsampling block in ControlNet. The value added to the corresponding resnet output in UNet.", "shape" : "[1, 1280, 32, 32]", "name" : "additional_residual_9", "type" : "MultiArray" } ], "version" : "TheMistoAI\/MistoLine", "modelParameters" : [ ], "author" : "Please refer to the Model Card available at huggingface.co\/TheMistoAI\/MistoLine", "specificationVersion" : 7, "storagePrecision" : "Mixed (Float16, Palettized (6 bits))", "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)", "mlProgramOperationTypeHistogram" : { "Transpose" : 282, "Ios16.reduceMean" : 42, "Ios16.sin" : 2, "Ios16.softmax" : 68, "Split" : 34, "Ios16.linear" : 362, "Ios16.add" : 146, "Concat" : 5, "Ios16.realDiv" : 21, "Ios16.square" : 21, "ExpandDims" : 18, "Ios16.sub" : 21, "Ios16.cast" : 10, "Ios16.conv" : 39, "Ios16.constexprLutToDense" : 434, "Ios16.gelu" : 34, "Ios16.layerNorm" : 102, "Ios16.batchNorm" : 21, "Ios16.matmul" : 136, "Ios16.reshape" : 326, "Ios16.silu" : 26, "Ios16.sqrt" : 21, "Ios16.mul" : 114, "Ios16.cos" : 2, "SliceByIndex" : 4 }, "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 × 128 × 128)", "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion", "shape" : "[1, 4, 128, 128]", "name" : "sample", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule", "shape" : "[1]", "name" : "timestep", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 77 × 2048)", "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" : "[1, 77, 2048]", "name" : "encoder_hidden_states", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 3 × 1024 × 1024)", "shortDescription" : "An additional input image for ControlNet to condition the generated images.", "shape" : "[1, 3, 1024, 1024]", "name" : "controlnet_cond", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "conditioning_scale", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 1280)", "shortDescription" : "", "shape" : "[1, 1280]", "name" : "text_embeds", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 6)", "shortDescription" : "", "shape" : "[1, 6]", "name" : "time_ids", "type" : "MultiArray" } ], "userDefinedMetadata" : { "com.github.apple.coremltools.source_dialect" : "TorchScript", "com.github.apple.coremltools.source" : "torch==2.2.0", "com.github.apple.coremltools.version" : "7.2" }, "generatedClassName" : "ControlNet_TheMistoAI_MistoLine", "method" : "predict" } ]