File size: 3,625 Bytes
5ffe9d5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
[
{
"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)",
"shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
"shape" : "[]",
"name" : "noise_pred",
"type" : "MultiArray"
}
],
"version" : "stabilityai\/stable-diffusion-2-1-base",
"modelParameters" : [
],
"author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-1-base",
"specificationVersion" : 7,
"storagePrecision" : "Float16",
"license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
"mlProgramOperationTypeHistogram" : {
"UpsampleNearestNeighbor" : 3,
"Ios16.reduceMean" : 218,
"Ios16.sin" : 1,
"Ios16.softmax" : 32,
"Split" : 16,
"Ios16.add" : 265,
"Concat" : 14,
"Ios16.realDiv" : 61,
"Ios16.square" : 61,
"ExpandDims" : 3,
"Ios16.sub" : 109,
"Ios16.cast" : 1,
"Ios16.conv" : 282,
"Ios16.gelu" : 16,
"Ios16.matmul" : 64,
"Ios16.reshape" : 282,
"Ios16.batchNorm" : 61,
"Ios16.rsqrt" : 48,
"Ios16.silu" : 47,
"Ios16.sqrt" : 61,
"SliceByIndex" : 2,
"Ios16.mul" : 193,
"Ios16.cos" : 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 2 × 4 × 64 × 64)",
"shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
"shape" : "[2, 4, 64, 64]",
"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 × 1024 × 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, 1024, 1, 77]",
"name" : "encoder_hidden_states",
"type" : "MultiArray"
}
],
"userDefinedMetadata" : {
"com.github.apple.coremltools.version" : "6.1",
"com.github.apple.coremltools.source" : "torch==1.13.1"
},
"generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_unet",
"method" : "predict"
}
] |