Text-to-Image
Core ML
stable-diffusion
core-ml
File size: 2,481 Bytes
5ffe9d5
 
 
 
 
 
 
 
 
 
 
 
3ec1302
5ffe9d5
 
 
 
 
 
 
 
 
 
 
 
 
 
3ec1302
 
 
 
5ffe9d5
3ec1302
 
5ffe9d5
3ec1302
 
 
5ffe9d5
3ec1302
 
 
5ffe9d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ec1302
5ffe9d5
3ec1302
5ffe9d5
 
 
 
3ec1302
 
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
[
  {
    "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",
        "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" : {
      "Pad" : 3,
      "Ios16.cast" : 1,
      "Ios16.mul" : 1,
      "Ios16.sqrt" : 22,
      "Ios16.sub" : 22,
      "Transpose" : 7,
      "Ios16.conv" : 28,
      "Ios16.add" : 33,
      "Ios16.linear" : 4,
      "Ios16.matmul" : 2,
      "Ios16.realDiv" : 22,
      "Ios16.reduceMean" : 44,
      "Ios16.softmax" : 1,
      "Ios16.batchNorm" : 22,
      "Ios16.square" : 22,
      "Ios16.reshape" : 54,
      "Ios16.silu" : 21
    },
    "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" : "The input image to base the initial latents on normalized to range [-1, 1]",
        "shape" : "[1, 3, 512, 512]",
        "name" : "z",
        "type" : "MultiArray"
      }
    ],
    "userDefinedMetadata" : {
      "com.github.apple.coremltools.version" : "6.3.0",
      "com.github.apple.coremltools.source" : "torch==2.0.0"
    },
    "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_1_base_vae_encoder",
    "method" : "predict"
  }
]