| [ | |
| { | |
| "shortDescription" : "Stable Diffusion generates images conditioned on text 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 2 × 4 × 128 × 128)", | |
| "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process", | |
| "shape" : "[2, 4, 128, 128]", | |
| "name" : "noise_pred", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "version" : "stabilityai\/stable-diffusion-xl-refiner-1.0", | |
| "modelParameters" : [ | |
| ], | |
| "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0", | |
| "specificationVersion" : 7, | |
| "storagePrecision" : "Float16", | |
| "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)", | |
| "mlProgramOperationTypeHistogram" : { | |
| "UpsampleNearestNeighbor" : 3, | |
| "Ios16.reduceMean" : 376, | |
| "Ios16.sin" : 2, | |
| "Ios16.softmax" : 88, | |
| "Split" : 44, | |
| "Ios16.add" : 508, | |
| "Concat" : 17, | |
| "Ios16.realDiv" : 56, | |
| "Ios16.square" : 56, | |
| "ExpandDims" : 6, | |
| "Ios16.sub" : 188, | |
| "Ios16.cast" : 1, | |
| "Ios16.conv" : 554, | |
| "Ios16.gelu" : 44, | |
| "Ios16.matmul" : 176, | |
| "Ios16.reshape" : 488, | |
| "Ios16.batchNorm" : 56, | |
| "Ios16.rsqrt" : 132, | |
| "Ios16.silu" : 48, | |
| "Ios16.sqrt" : 56, | |
| "SliceByIndex" : 4, | |
| "Ios16.mul" : 530, | |
| "Ios16.cos" : 2 | |
| }, | |
| "computePrecision" : "Mixed (Float16, Float32, Int32)", | |
| "isUpdatable" : "0", | |
| "availability" : { | |
| "macOS" : "13.0", | |
| "tvOS" : "16.0", | |
| "visionOS" : "1.0", | |
| "watchOS" : "9.0", | |
| "iOS" : "16.0", | |
| "macCatalyst" : "16.0" | |
| }, | |
| "modelType" : { | |
| "name" : "MLModelType_mlProgram" | |
| }, | |
| "inputSchema" : [ | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float16", | |
| "formattedType" : "MultiArray (Float16 2 × 4 × 128 × 128)", | |
| "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion", | |
| "shape" : "[2, 4, 128, 128]", | |
| "name" : "sample", | |
| "type" : "MultiArray" | |
| }, | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float16", | |
| "formattedType" : "MultiArray (Float16 2)", | |
| "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule", | |
| "shape" : "[2]", | |
| "name" : "timestep", | |
| "type" : "MultiArray" | |
| }, | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float16", | |
| "formattedType" : "MultiArray (Float16 2 × 1280 × 1 × 77)", | |
| "shortDescription" : "Output embeddings from the associated text_encoder model to condition to generated image on text. A maximum of 77 tokens (~40 words) are allowed. Longer text is truncated. Shorter text does not reduce computation.", | |
| "shape" : "[2, 1280, 1, 77]", | |
| "name" : "encoder_hidden_states", | |
| "type" : "MultiArray" | |
| }, | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float16", | |
| "formattedType" : "MultiArray (Float16 2 × 5)", | |
| "shortDescription" : "Additional embeddings that if specified are added to the embeddings that are passed along to the UNet blocks.", | |
| "shape" : "[2, 5]", | |
| "name" : "time_ids", | |
| "type" : "MultiArray" | |
| }, | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float16", | |
| "formattedType" : "MultiArray (Float16 2 × 1280)", | |
| "shortDescription" : "Additional embeddings from text_encoder_2 that if specified are added to the embeddings that are passed along to the UNet blocks.", | |
| "shape" : "[2, 1280]", | |
| "name" : "text_embeds", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "userDefinedMetadata" : { | |
| "com.github.apple.coremltools.version" : "7.0", | |
| "com.github.apple.coremltools.source" : "torch==2.0.1", | |
| "com.github.apple.ml-stable-diffusion.version" : "1.0.0" | |
| }, | |
| "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_xl_base_1_0_refiner", | |
| "method" : "predict" | |
| } | |
| ] |