[ { "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" : "cyberdelia\/CyberRealistic@99827f96edd717dacb28c68560680c201c55df05 + latent-consistency\/lcm-lora-sdv1-5@cf2fced511dbe7e26c8d1d397e728fbab875db4b", "modelParameters" : [ ], "author" : "Cyberdelia + Latent Consistency Models; Core ML 6-bit palettized conversion prepared for LocalMuse", "specificationVersion" : 8, "storagePrecision" : "Mixed (Float16, Palettized (6 bits))", "license" : "See the original model terms at https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license", "mlProgramOperationTypeHistogram" : { "Ios17.mul" : 36, "Ios17.reduceArgmax" : 1, "Ios17.linear" : 72, "Ios17.transpose" : 48, "Select" : 1, "Ios16.constexprLutToDense" : 74, "Ios17.matmul" : 24, "Stack" : 1, "Ios17.gatherNd" : 1, "Ios16.sigmoid" : 12, "Ios17.add" : 38, "Ios17.gather" : 1, "Ios16.softmax" : 12, "Ios17.greaterEqual" : 1, "Ios17.reshape" : 48, "Ios17.layerNorm" : 25, "Ios17.cast" : 4 }, "computePrecision" : "Mixed (Float16, Float32, Int32, UInt16)", "stateSchema" : [ ], "isUpdatable" : "0", "availability" : { "macOS" : "14.0", "tvOS" : "17.0", "visionOS" : "1.0", "watchOS" : "10.0", "iOS" : "17.0", "macCatalyst" : "17.0" }, "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" : "8.3.0", "com.github.apple.coremltools.source" : "torch==2.4.0", "com.github.apple.coremltools.source_dialect" : "TorchScript" }, "generatedClassName" : "Stable_Diffusion_version_cyberdelia_CyberRealistic_text_encoder", "method" : "predict" } ]