[
  {
    "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" : "cyberdelia\/CyberRealistic@99827f96edd717dacb28c68560680c201c55df05",
    "modelParameters" : [

    ],
    "author" : "Cyberdelia; Core ML FP16 conversion prepared for LocalMuse",
    "specificationVersion" : 8,
    "storagePrecision" : "Float16",
    "license" : "See the original model terms at https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license",
    "mlProgramOperationTypeHistogram" : {
      "Pad" : 3,
      "Ios17.mul" : 2,
      "Ios17.sqrt" : 22,
      "Ios17.square" : 22,
      "Ios17.transpose" : 6,
      "Ios17.sub" : 22,
      "Ios17.linear" : 4,
      "Ios17.conv" : 28,
      "Ios17.matmul" : 2,
      "Ios17.add" : 34,
      "Ios17.realDiv" : 22,
      "Ios16.reduceMean" : 44,
      "Ios17.batchNorm" : 21,
      "Ios16.softmax" : 1,
      "Ios17.reshape" : 49,
      "Ios17.cast" : 1,
      "Ios16.silu" : 21
    },
    "computePrecision" : "Mixed (Float16, Float32, Int32)",
    "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" : "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.source_dialect" : "TorchScript",
      "com.github.apple.coremltools.source" : "torch==2.4.0",
      "com.github.apple.coremltools.version" : "8.3.0"
    },
    "generatedClassName" : "Stable_Diffusion_version_cyberdelia_CyberRealistic_vae_encoder",
    "method" : "predict"
  }
]