Text-to-Image
Core ML
stable-diffusion
core-ml
pcuenq's picture
pcuenq HF staff
VAE Encoder (#4)
a8bfcd1
raw
history blame
4.15 kB
[
{
"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)",
"shortDescription" : "The latent embeddings from the unet model from the input image.",
"shape" : "[]",
"name" : "latent_dist",
"type" : "MultiArray"
}
],
"version" : "stabilityai\/stable-diffusion-2-base",
"modelParameters" : [
],
"author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
"specificationVersion" : 7,
"storagePrecision" : "Float16",
"license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
"mlProgramOperationTypeHistogram" : {
"Transpose" : 7,
"Ios16.exp" : 1,
"Ios16.reduceMean" : 44,
"Ios16.softmax" : 1,
"Split" : 1,
"Ios16.linear" : 4,
"Ios16.add" : 35,
"Ios16.realDiv" : 22,
"Ios16.square" : 22,
"Pad" : 3,
"Ios16.sub" : 22,
"Ios16.cast" : 1,
"Ios16.clip" : 1,
"Ios16.conv" : 28,
"Ios16.matmul" : 2,
"Ios16.reshape" : 54,
"Ios16.batchNorm" : 22,
"Ios16.silu" : 21,
"Ios16.sqrt" : 22,
"Ios16.mul" : 6
},
"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 1 × 3 × 512 × 512)",
"shortDescription" : "An image of the correct size to create the latent space with, image2image and in-painting.",
"shape" : "[1, 3, 512, 512]",
"name" : "sample",
"type" : "MultiArray"
},
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
"shortDescription" : "Latent noise for `DiagonalGaussianDistribution` operation.",
"shape" : "[1, 4, 64, 64]",
"name" : "diagonal_noise",
"type" : "MultiArray"
},
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
"shortDescription" : "Latent noise for use with strength parameter of image2image",
"shape" : "[1, 4, 64, 64]",
"name" : "noise",
"type" : "MultiArray"
},
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 1 × 1)",
"shortDescription" : "Precalculated `sqrt_alphas_cumprod` value based on strength and the current schedular's alphasCumprod values",
"shape" : "[1, 1]",
"name" : "sqrt_alphas_cumprod",
"type" : "MultiArray"
},
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 1 × 1)",
"shortDescription" : "Precalculated `sqrt_one_minus_alphas_cumprod` value based on strength and the current schedular's alphasCumprod values",
"shape" : "[1, 1]",
"name" : "sqrt_one_minus_alphas_cumprod",
"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_base_vae_encoder",
"method" : "predict"
}
]