[ { "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" : "The token embeddings as encoded by the Transformer model", "shape" : "[]", "name" : "last_hidden_state", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32)", "shortDescription" : "The version of the `last_hidden_state` output after pooling", "shape" : "[]", "name" : "pooled_outputs", "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" : "Float16", "license" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-0.9\/blob\/main\/LICENSE.md", "mlProgramOperationTypeHistogram" : { "Ios16.cast" : 2, "Ios16.mul" : 32, "Ios16.layerNorm" : 65, "Ios16.constexprLutToDense" : 227, "Stack" : 1, "Transpose" : 160, "Ios16.linear" : 193, "Ios16.add" : 97, "Ios16.matmul" : 64, "Ios16.gelu" : 32, "Ios16.softmax" : 32, "Ios16.gatherNd" : 1, "Ios16.gather" : 1, "Ios16.reshape" : 320, "Ios16.reduceArgmax" : 1 }, "computePrecision" : "Mixed (Float32, Int32, Float16)", "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" : "Int32", "formattedType" : "MultiArray (Int32 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" : "7.0b1", "com.github.apple.coremltools.source" : "torch==2.1.0.dev20230718" }, "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_0_9_text_encoder_2", "method" : "predict" } ]