| [ |
| { |
| "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)", |
| "shortDescription" : "Identical to the input `images`. If safety checker detected any sensitive content, the corresponding image is replaced with a blank image (zeros)", |
| "shape" : "[]", |
| "name" : "filtered_images", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32)", |
| "shortDescription" : "Indicates whether the safety checker model found any sensitive content in the given image", |
| "shape" : "[]", |
| "name" : "has_nsfw_concepts", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32)", |
| "shortDescription" : "Concept scores are the scores before thresholding at zero yields the `has_nsfw_concepts` output. These scores can be used to tune the `adjustment` input", |
| "shape" : "[]", |
| "name" : "concept_scores", |
| "type" : "MultiArray" |
| } |
| ], |
| "version" : "CompVis\/stable-diffusion-v1-4", |
| "modelParameters" : [ |
|
|
| ], |
| "author" : "Please refer to the Model Card available at huggingface.co\/CompVis\/stable-diffusion-v1-4", |
| "specificationVersion" : 7, |
| "storagePrecision" : "Float16", |
| "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)", |
| "mlProgramOperationTypeHistogram" : { |
| "Transpose" : 121, |
| "Ios16.scatterNd" : 1, |
| "Ios16.softmax" : 24, |
| "Ios16.linear" : 147, |
| "Ios16.add" : 51, |
| "Concat" : 1, |
| "Ios16.realDiv" : 1, |
| "Ios16.sigmoid" : 24, |
| "Ios16.reduceSum" : 3, |
| "Tile" : 4, |
| "Ios16.greater" : 4, |
| "Shape" : 1, |
| "ExpandDims" : 5, |
| "Ios16.cast" : 9, |
| "Ios16.clip" : 1, |
| "Ios16.conv" : 1, |
| "Ios16.abs" : 1, |
| "Ios16.layerNorm" : 50, |
| "Ios16.matmul" : 48, |
| "Ios16.pow" : 2, |
| "Ios16.reshape" : 193, |
| "SliceByIndex" : 2, |
| "Ios16.mul" : 73, |
| "NonZero" : 1 |
| }, |
| "computePrecision" : "Mixed (Float32, Float16, 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" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 3 × 224 × 224)", |
| "shortDescription" : "The normalized image input tensor resized to (224x224) in channels-first (BCHW) format", |
| "shape" : "[1, 3, 224, 224]", |
| "name" : "clip_input", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 512 × 512 × 3)", |
| "shortDescription" : "Output of the vae_decoder (512x512) in channels-last (BHWC) format", |
| "shape" : "[1, 512, 512, 3]", |
| "name" : "images", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1)", |
| "shortDescription" : "Bias added to the concept scores to trade off increased recall for reduce precision in the safety checker classifier", |
| "shape" : "[1]", |
| "name" : "adjustment", |
| "type" : "MultiArray" |
| } |
| ], |
| "userDefinedMetadata" : { |
| "com.github.apple.coremltools.version" : "6.1", |
| "com.github.apple.coremltools.source" : "torch==1.13.0" |
| }, |
| "generatedClassName" : "Stable_Diffusion_version_CompVis_stable_diffusion_v1_4_safety_checker", |
| "method" : "predict" |
| } |
| ] |
