original/compiled/VAEDecoder.mlmodelc/metadata.json

[
  {
    "shortDescription" : "This is a model that can be used to generate and modify images based on text prompts.It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT\/G and CLIP-ViT\/L).Please refer to https:\/\/arxiv.org\/abs\/2307.01952 for details",
    "metadataOutputVersion" : "3.0",
    "outputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float32",
        "formattedType" : "MultiArray (Float32)",
        "shortDescription" : "Generated image normalized to range [-1, 1]",
        "shape" : "[]",
        "name" : "image",
        "type" : "MultiArray"
      }
    ],
    "version" : "stabilityai\/stable-diffusion-xl-base-0.9",
    "modelParameters" : [

    ],
    "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9",
    "specificationVersion" : 7,
    "storagePrecision" : "Float32",
    "license" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9\/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",
      "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 × 128 × 128)",
        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
        "shape" : "[1, 4, 128, 128]",
        "name" : "z",
        "type" : "MultiArray"
      }
    ],
    "userDefinedMetadata" : {
      "com.github.apple.coremltools.version" : "7.0b1",
      "com.github.apple.coremltools.source" : "torch==2.1.0.dev20230718"
    },
    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_0_9_vae_decoder",
    "method" : "predict"
  }
]