[ { "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 × 512 × 512 × 3)", "shortDescription" : "Identical to the input `images`. If safety checker detected any sensitive content, the corresponding image is replaced with a blank image (zeros)", "shape" : "[1, 512, 512, 3]", "name" : "filtered_images", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 1 × 1 × 1)", "shortDescription" : "Indicates whether the safety checker model found any sensitive content in the given image", "shape" : "[1, 1, 1, 1]", "name" : "has_nsfw_concepts", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 17)", "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" : "[1, 17]", "name" : "concept_scores", "type" : "MultiArray" } ], "version" : "clover-image-tiny-inpaint-v2", "modelParameters" : [ ], "author" : "Please refer to the Model Card available at huggingface.co\/clover-image-tiny-inpaint-v2", "specificationVersion" : 9, "storagePrecision" : "Float16", "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)", "mlProgramOperationTypeHistogram" : { "Ios18.expandDims" : 4, "Ios18.softmax" : 24, "Ios18.mul" : 73, "Ios18.matmul" : 48, "Ios18.realDiv" : 1, "Ios18.sigmoid" : 24, "Ios18.equal" : 1, "Ios18.greaterEqual" : 1, "Select" : 2, "Ios18.greater" : 4, "Tile" : 4, "Ios16.reduceSum" : 2, "Ios18.add" : 52, "Ios18.layerNorm" : 50, "Ios18.scatterNd" : 1, "Ios18.reshape" : 97, "Shape" : 1, "Ios18.maximum" : 1, "Ios18.linear" : 147, "Ios18.conv" : 1, "Ios18.concat" : 2, "Ios18.transpose" : 97, "Ios18.cast" : 7, "Ios18.sliceByIndex" : 2, "NonZero" : 1, "Ios16.reduceL2Norm" : 1 }, "computePrecision" : "Mixed (Float16, Float32, Int32)", "stateSchema" : [ ], "isUpdatable" : "0", "availability" : { "macOS" : "15.0", "tvOS" : "18.0", "visionOS" : "2.0", "watchOS" : "11.0", "iOS" : "18.0", "macCatalyst" : "18.0" }, "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.conversion_date" : "2026-08-11", "com.github.apple.coremltools.source" : "torch==2.7.0", "com.github.apple.coremltools.version" : "9.0", "com.github.apple.coremltools.source_dialect" : "TorchScript" }, "generatedClassName" : "Stable_Diffusion_version_clover_image_tiny_inpaint_v2_safety_checker", "method" : "predict" } ]