| [ | |
| { | |
| "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 latent embeddings from the unet model from the input image.", | |
| "shape" : "[]", | |
| "name" : "latent", | |
| "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" : { | |
| "Pad" : 3, | |
| "Ios16.cast" : 2, | |
| "Ios16.mul" : 2, | |
| "Ios16.sqrt" : 22, | |
| "Ios16.sub" : 22, | |
| "Transpose" : 6, | |
| "Ios16.conv" : 28, | |
| "Ios16.add" : 34, | |
| "Ios16.linear" : 4, | |
| "Ios16.matmul" : 2, | |
| "Ios16.realDiv" : 22, | |
| "Ios16.reduceMean" : 44, | |
| "Ios16.softmax" : 1, | |
| "Ios16.batchNorm" : 21, | |
| "Ios16.square" : 22, | |
| "Ios16.reshape" : 49, | |
| "Ios16.silu" : 21 | |
| }, | |
| "computePrecision" : "Mixed (Float16, 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 × 3 × 1024 × 1024)", | |
| "shortDescription" : "The input image to base the initial latents on normalized to range [-1, 1]", | |
| "shape" : "[1, 3, 1024, 1024]", | |
| "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_encoder", | |
| "method" : "predict" | |
| } | |
| ] |