Text-to-Image
Core ML
stable-diffusion
core-ml
pcuenq HF staff commited on
Commit
39d5ff8
1 Parent(s): a6d2803

Add checkpoints

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. original/compiled/TextEncoder.mlmodelc/analytics/coremldata.bin +3 -0
  2. original/compiled/TextEncoder.mlmodelc/coremldata.bin +3 -0
  3. original/compiled/TextEncoder.mlmodelc/metadata.json +85 -0
  4. original/compiled/TextEncoder.mlmodelc/model.mil +3 -0
  5. original/compiled/TextEncoder.mlmodelc/weights/weight.bin +3 -0
  6. original/compiled/Unet.mlmodelc/analytics/coremldata.bin +3 -0
  7. original/compiled/Unet.mlmodelc/coremldata.bin +3 -0
  8. original/compiled/Unet.mlmodelc/metadata.json +101 -0
  9. original/compiled/Unet.mlmodelc/model.mil +3 -0
  10. original/compiled/Unet.mlmodelc/weights/weight.bin +3 -0
  11. original/compiled/UnetChunk1.mlmodelc/analytics/coremldata.bin +3 -0
  12. original/compiled/UnetChunk1.mlmodelc/coremldata.bin +3 -0
  13. original/compiled/UnetChunk1.mlmodelc/metadata.json +215 -0
  14. original/compiled/UnetChunk1.mlmodelc/model.mil +3 -0
  15. original/compiled/UnetChunk1.mlmodelc/weights/weight.bin +3 -0
  16. original/compiled/UnetChunk2.mlmodelc/analytics/coremldata.bin +3 -0
  17. original/compiled/UnetChunk2.mlmodelc/coremldata.bin +3 -0
  18. original/compiled/UnetChunk2.mlmodelc/metadata.json +202 -0
  19. original/compiled/UnetChunk2.mlmodelc/model.mil +3 -0
  20. original/compiled/UnetChunk2.mlmodelc/weights/weight.bin +3 -0
  21. original/compiled/VAEDecoder.mlmodelc/analytics/coremldata.bin +3 -0
  22. original/compiled/VAEDecoder.mlmodelc/coremldata.bin +3 -0
  23. original/compiled/VAEDecoder.mlmodelc/metadata.json +75 -0
  24. original/compiled/VAEDecoder.mlmodelc/model.mil +3 -0
  25. original/compiled/VAEDecoder.mlmodelc/weights/weight.bin +3 -0
  26. original/compiled/merges.txt +0 -0
  27. original/compiled/vocab.json +0 -0
  28. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel +3 -0
  29. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_text_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
  30. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_text_encoder.mlpackage/Manifest.json +18 -0
  31. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel +3 -0
  32. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
  33. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet.mlpackage/Manifest.json +18 -0
  34. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk1.mlpackage/Data/com.apple.CoreML/model.mlmodel +3 -0
  35. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk1.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
  36. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk1.mlpackage/Manifest.json +18 -0
  37. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk2.mlpackage/Data/com.apple.CoreML/model.mlmodel +3 -0
  38. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk2.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
  39. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk2.mlpackage/Manifest.json +18 -0
  40. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel +3 -0
  41. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
  42. original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_decoder.mlpackage/Manifest.json +18 -0
  43. split_einsum/compiled/TextEncoder.mlmodelc/analytics/coremldata.bin +3 -0
  44. split_einsum/compiled/TextEncoder.mlmodelc/coremldata.bin +3 -0
  45. split_einsum/compiled/TextEncoder.mlmodelc/metadata.json +85 -0
  46. split_einsum/compiled/TextEncoder.mlmodelc/model.mil +3 -0
  47. split_einsum/compiled/TextEncoder.mlmodelc/weights/weight.bin +3 -0
  48. split_einsum/compiled/Unet.mlmodelc/analytics/coremldata.bin +3 -0
  49. split_einsum/compiled/Unet.mlmodelc/coremldata.bin +3 -0
  50. split_einsum/compiled/Unet.mlmodelc/metadata.json +102 -0
original/compiled/TextEncoder.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77320e8a1011459dff4b3a384069fcb45370a5ec87ef845fed7651f4453f2984
3
+ size 207
original/compiled/TextEncoder.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14668c0a30131497354d488afdec77bd753ac59aaedfbcfe512ec6e2be5af63b
3
+ size 834
original/compiled/TextEncoder.mlmodelc/metadata.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "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.",
4
+ "metadataOutputVersion" : "3.0",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32)",
11
+ "shortDescription" : "The token embeddings as encoded by the Transformer model",
12
+ "shape" : "[]",
13
+ "name" : "last_hidden_state",
14
+ "type" : "MultiArray"
15
+ },
16
+ {
17
+ "hasShapeFlexibility" : "0",
18
+ "isOptional" : "0",
19
+ "dataType" : "Float32",
20
+ "formattedType" : "MultiArray (Float32)",
21
+ "shortDescription" : "The version of the `last_hidden_state` output after pooling",
22
+ "shape" : "[]",
23
+ "name" : "pooled_outputs",
24
+ "type" : "MultiArray"
25
+ }
26
+ ],
27
+ "version" : "stabilityai\/stable-diffusion-2-base",
28
+ "modelParameters" : [
29
+
30
+ ],
31
+ "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
32
+ "specificationVersion" : 7,
33
+ "storagePrecision" : "Float16",
34
+ "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
35
+ "mlProgramOperationTypeHistogram" : {
36
+ "Ios16.cast" : 3,
37
+ "Ios16.mul" : 23,
38
+ "Ios16.layerNorm" : 47,
39
+ "Ios16.sub" : 1,
40
+ "BandPart" : 1,
41
+ "Stack" : 1,
42
+ "Transpose" : 115,
43
+ "Ios16.linear" : 138,
44
+ "Ios16.add" : 70,
45
+ "Ios16.matmul" : 46,
46
+ "Ios16.gelu" : 23,
47
+ "Ios16.softmax" : 23,
48
+ "ExpandDims" : 1,
49
+ "Ios16.gather" : 1,
50
+ "Ios16.gatherNd" : 1,
51
+ "Ios16.reshape" : 230,
52
+ "Ios16.reduceArgmax" : 1
53
+ },
54
+ "computePrecision" : "Mixed (Float16, Float32, Int32)",
55
+ "isUpdatable" : "0",
56
+ "availability" : {
57
+ "macOS" : "13.0",
58
+ "tvOS" : "16.0",
59
+ "watchOS" : "9.0",
60
+ "iOS" : "16.0",
61
+ "macCatalyst" : "16.0"
62
+ },
63
+ "modelType" : {
64
+ "name" : "MLModelType_mlProgram"
65
+ },
66
+ "inputSchema" : [
67
+ {
68
+ "hasShapeFlexibility" : "0",
69
+ "isOptional" : "0",
70
+ "dataType" : "Float32",
71
+ "formattedType" : "MultiArray (Float32 1 × 77)",
72
+ "shortDescription" : "The token ids that represent the input text",
73
+ "shape" : "[1, 77]",
74
+ "name" : "input_ids",
75
+ "type" : "MultiArray"
76
+ }
77
+ ],
78
+ "userDefinedMetadata" : {
79
+ "com.github.apple.coremltools.version" : "6.1",
80
+ "com.github.apple.coremltools.source" : "torch==1.13.0"
81
+ },
82
+ "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_text_encoder",
83
+ "method" : "predict"
84
+ }
85
+ ]
original/compiled/TextEncoder.mlmodelc/model.mil ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3214a3aaa8cd8a7ab25040804d81ab0b6eb5a1a8eb07e3a240c1270e44135fad
3
+ size 320318
original/compiled/TextEncoder.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb9254ab40377228ca6d53e67f55d908a2ec6d6ce4a10a88b17b6e6bf245ce4
3
+ size 680811520
original/compiled/Unet.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c8b1a881a1d4aa593d38b5aff28214605ac9f75d9a832fcdb82d646ea61271
3
+ size 207
original/compiled/Unet.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29a62bd609fa8d005e854d7acbdc91a8787e59dc66a3c657eed9d8c03ae7efa
3
+ size 1215
original/compiled/Unet.mlmodelc/metadata.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "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.",
4
+ "metadataOutputVersion" : "3.0",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32)",
11
+ "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to faciliate the reverse diffusion (denoising) process",
12
+ "shape" : "[]",
13
+ "name" : "noise_pred",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "version" : "stabilityai\/stable-diffusion-2-base",
18
+ "modelParameters" : [
19
+
20
+ ],
21
+ "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
22
+ "specificationVersion" : 7,
23
+ "storagePrecision" : "Float16",
24
+ "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
25
+ "mlProgramOperationTypeHistogram" : {
26
+ "UpsampleNearestNeighbor" : 3,
27
+ "Ios16.reduceMean" : 218,
28
+ "Ios16.sin" : 1,
29
+ "Ios16.softmax" : 32,
30
+ "Split" : 16,
31
+ "Ios16.add" : 265,
32
+ "Concat" : 14,
33
+ "Ios16.realDiv" : 61,
34
+ "Ios16.square" : 61,
35
+ "ExpandDims" : 3,
36
+ "Ios16.sub" : 109,
37
+ "Ios16.cast" : 1,
38
+ "Ios16.conv" : 282,
39
+ "Ios16.gelu" : 16,
40
+ "Ios16.matmul" : 64,
41
+ "Ios16.reshape" : 282,
42
+ "Ios16.batchNorm" : 61,
43
+ "Ios16.rsqrt" : 48,
44
+ "Ios16.silu" : 47,
45
+ "Ios16.sqrt" : 61,
46
+ "SliceByIndex" : 2,
47
+ "Ios16.mul" : 193,
48
+ "Ios16.cos" : 1
49
+ },
50
+ "computePrecision" : "Mixed (Float32, Float16, Int32)",
51
+ "isUpdatable" : "0",
52
+ "availability" : {
53
+ "macOS" : "13.0",
54
+ "tvOS" : "16.0",
55
+ "watchOS" : "9.0",
56
+ "iOS" : "16.0",
57
+ "macCatalyst" : "16.0"
58
+ },
59
+ "modelType" : {
60
+ "name" : "MLModelType_mlProgram"
61
+ },
62
+ "inputSchema" : [
63
+ {
64
+ "hasShapeFlexibility" : "0",
65
+ "isOptional" : "0",
66
+ "dataType" : "Float16",
67
+ "formattedType" : "MultiArray (Float16 2 × 4 × 64 × 64)",
68
+ "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
69
+ "shape" : "[2, 4, 64, 64]",
70
+ "name" : "sample",
71
+ "type" : "MultiArray"
72
+ },
73
+ {
74
+ "hasShapeFlexibility" : "0",
75
+ "isOptional" : "0",
76
+ "dataType" : "Float16",
77
+ "formattedType" : "MultiArray (Float16 2)",
78
+ "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule",
79
+ "shape" : "[2]",
80
+ "name" : "timestep",
81
+ "type" : "MultiArray"
82
+ },
83
+ {
84
+ "hasShapeFlexibility" : "0",
85
+ "isOptional" : "0",
86
+ "dataType" : "Float16",
87
+ "formattedType" : "MultiArray (Float16 2 × 1024 × 1 × 77)",
88
+ "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.",
89
+ "shape" : "[2, 1024, 1, 77]",
90
+ "name" : "encoder_hidden_states",
91
+ "type" : "MultiArray"
92
+ }
93
+ ],
94
+ "userDefinedMetadata" : {
95
+ "com.github.apple.coremltools.version" : "6.1",
96
+ "com.github.apple.coremltools.source" : "torch==1.13.0"
97
+ },
98
+ "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_unet",
99
+ "method" : "predict"
100
+ }
101
+ ]
original/compiled/Unet.mlmodelc/model.mil ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca8b010530bb268ef86acd181d9003845cbadf90db3b50cc7008e5b8057b8e33
3
+ size 842346
original/compiled/Unet.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ba62298577f8d4cd8f72499b430dcd9f5bd97de97ef03a6fbbfa07d5084375
3
+ size 1732124416
original/compiled/UnetChunk1.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e26e6016c411b3a612de16c1a9a74cd3e087b9316042240f80be585c3734d8
3
+ size 207
original/compiled/UnetChunk1.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d483e20a35bcf48457e6feb8009c38294398cdafbf58bc01be010c9a11e42edd
3
+ size 528
original/compiled/UnetChunk1.mlmodelc/metadata.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "metadataOutputVersion" : "3.0",
4
+ "storagePrecision" : "Float16",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32)",
11
+ "shortDescription" : "",
12
+ "shape" : "[]",
13
+ "name" : "input_61_cast",
14
+ "type" : "MultiArray"
15
+ },
16
+ {
17
+ "hasShapeFlexibility" : "0",
18
+ "isOptional" : "0",
19
+ "dataType" : "Float32",
20
+ "formattedType" : "MultiArray (Float32)",
21
+ "shortDescription" : "",
22
+ "shape" : "[]",
23
+ "name" : "input_143_cast",
24
+ "type" : "MultiArray"
25
+ },
26
+ {
27
+ "hasShapeFlexibility" : "0",
28
+ "isOptional" : "0",
29
+ "dataType" : "Float32",
30
+ "formattedType" : "MultiArray (Float32)",
31
+ "shortDescription" : "",
32
+ "shape" : "[]",
33
+ "name" : "input_171_cast",
34
+ "type" : "MultiArray"
35
+ },
36
+ {
37
+ "hasShapeFlexibility" : "0",
38
+ "isOptional" : "0",
39
+ "dataType" : "Float32",
40
+ "formattedType" : "MultiArray (Float32)",
41
+ "shortDescription" : "",
42
+ "shape" : "[]",
43
+ "name" : "hidden_states_149_cast",
44
+ "type" : "MultiArray"
45
+ },
46
+ {
47
+ "hasShapeFlexibility" : "0",
48
+ "isOptional" : "0",
49
+ "dataType" : "Float32",
50
+ "formattedType" : "MultiArray (Float32)",
51
+ "shortDescription" : "",
52
+ "shape" : "[]",
53
+ "name" : "input_7_cast",
54
+ "type" : "MultiArray"
55
+ },
56
+ {
57
+ "hasShapeFlexibility" : "0",
58
+ "isOptional" : "0",
59
+ "dataType" : "Float32",
60
+ "formattedType" : "MultiArray (Float32)",
61
+ "shortDescription" : "",
62
+ "shape" : "[]",
63
+ "name" : "input_89_cast",
64
+ "type" : "MultiArray"
65
+ },
66
+ {
67
+ "hasShapeFlexibility" : "0",
68
+ "isOptional" : "0",
69
+ "dataType" : "Float32",
70
+ "formattedType" : "MultiArray (Float32)",
71
+ "shortDescription" : "",
72
+ "shape" : "[]",
73
+ "name" : "input_117_cast",
74
+ "type" : "MultiArray"
75
+ },
76
+ {
77
+ "hasShapeFlexibility" : "0",
78
+ "isOptional" : "0",
79
+ "dataType" : "Float32",
80
+ "formattedType" : "MultiArray (Float32)",
81
+ "shortDescription" : "",
82
+ "shape" : "[]",
83
+ "name" : "input_169_cast",
84
+ "type" : "MultiArray"
85
+ },
86
+ {
87
+ "hasShapeFlexibility" : "0",
88
+ "isOptional" : "0",
89
+ "dataType" : "Float32",
90
+ "formattedType" : "MultiArray (Float32)",
91
+ "shortDescription" : "",
92
+ "shape" : "[]",
93
+ "name" : "input_253_cast",
94
+ "type" : "MultiArray"
95
+ },
96
+ {
97
+ "hasShapeFlexibility" : "0",
98
+ "isOptional" : "0",
99
+ "dataType" : "Float32",
100
+ "formattedType" : "MultiArray (Float32)",
101
+ "shortDescription" : "",
102
+ "shape" : "[]",
103
+ "name" : "input_35_cast",
104
+ "type" : "MultiArray"
105
+ },
106
+ {
107
+ "hasShapeFlexibility" : "0",
108
+ "isOptional" : "0",
109
+ "dataType" : "Float32",
110
+ "formattedType" : "MultiArray (Float32)",
111
+ "shortDescription" : "",
112
+ "shape" : "[]",
113
+ "name" : "input_63_cast",
114
+ "type" : "MultiArray"
115
+ },
116
+ {
117
+ "hasShapeFlexibility" : "0",
118
+ "isOptional" : "0",
119
+ "dataType" : "Float32",
120
+ "formattedType" : "MultiArray (Float32)",
121
+ "shortDescription" : "",
122
+ "shape" : "[]",
123
+ "name" : "input_15_cast",
124
+ "type" : "MultiArray"
125
+ },
126
+ {
127
+ "hasShapeFlexibility" : "0",
128
+ "isOptional" : "0",
129
+ "dataType" : "Float32",
130
+ "formattedType" : "MultiArray (Float32)",
131
+ "shortDescription" : "",
132
+ "shape" : "[]",
133
+ "name" : "input_115_cast",
134
+ "type" : "MultiArray"
135
+ }
136
+ ],
137
+ "modelParameters" : [
138
+
139
+ ],
140
+ "specificationVersion" : 7,
141
+ "mlProgramOperationTypeHistogram" : {
142
+ "Ios16.reduceMean" : 104,
143
+ "Ios16.sin" : 1,
144
+ "Ios16.softmax" : 14,
145
+ "Split" : 7,
146
+ "Ios16.add" : 124,
147
+ "Concat" : 4,
148
+ "Ios16.realDiv" : 31,
149
+ "Ios16.square" : 31,
150
+ "ExpandDims" : 3,
151
+ "Ios16.sub" : 52,
152
+ "Ios16.cast" : 13,
153
+ "Ios16.conv" : 129,
154
+ "Ios16.gelu" : 7,
155
+ "Ios16.matmul" : 28,
156
+ "Ios16.reshape" : 132,
157
+ "Ios16.batchNorm" : 31,
158
+ "Ios16.rsqrt" : 21,
159
+ "Ios16.silu" : 26,
160
+ "Ios16.sqrt" : 31,
161
+ "SliceByIndex" : 2,
162
+ "Ios16.mul" : 85,
163
+ "Ios16.cos" : 1
164
+ },
165
+ "computePrecision" : "Mixed (Float32, Float16, Int32)",
166
+ "isUpdatable" : "0",
167
+ "availability" : {
168
+ "macOS" : "13.0",
169
+ "tvOS" : "16.0",
170
+ "watchOS" : "9.0",
171
+ "iOS" : "16.0",
172
+ "macCatalyst" : "16.0"
173
+ },
174
+ "modelType" : {
175
+ "name" : "MLModelType_mlProgram"
176
+ },
177
+ "userDefinedMetadata" : {
178
+
179
+ },
180
+ "inputSchema" : [
181
+ {
182
+ "hasShapeFlexibility" : "0",
183
+ "isOptional" : "0",
184
+ "dataType" : "Float16",
185
+ "formattedType" : "MultiArray (Float16 2 × 4 × 64 × 64)",
186
+ "shortDescription" : "",
187
+ "shape" : "[2, 4, 64, 64]",
188
+ "name" : "sample",
189
+ "type" : "MultiArray"
190
+ },
191
+ {
192
+ "hasShapeFlexibility" : "0",
193
+ "isOptional" : "0",
194
+ "dataType" : "Float16",
195
+ "formattedType" : "MultiArray (Float16 2)",
196
+ "shortDescription" : "",
197
+ "shape" : "[2]",
198
+ "name" : "timestep",
199
+ "type" : "MultiArray"
200
+ },
201
+ {
202
+ "hasShapeFlexibility" : "0",
203
+ "isOptional" : "0",
204
+ "dataType" : "Float16",
205
+ "formattedType" : "MultiArray (Float16 2 × 1024 × 1 × 77)",
206
+ "shortDescription" : "",
207
+ "shape" : "[2, 1024, 1, 77]",
208
+ "name" : "encoder_hidden_states",
209
+ "type" : "MultiArray"
210
+ }
211
+ ],
212
+ "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_unet_chunk1",
213
+ "method" : "predict"
214
+ }
215
+ ]
original/compiled/UnetChunk1.mlmodelc/model.mil ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a484de5d01f2148d262acabd675b487a099d65e118e925d212dc7ea67820f0
3
+ size 396377
original/compiled/UnetChunk1.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca43df7b15979733f57a0cceb2ebe8c6ecdd300ccdf5ec83195c3141eca368e
3
+ size 893578816
original/compiled/UnetChunk2.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73b0075468270609bfc62f9863c96a8df9634cb493d873b06d6cc608cf9c876
3
+ size 207
original/compiled/UnetChunk2.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f4e4f228d7c7c30a32e8e49c14d3f18035df8a946d23c61ba64be1bf9126ee
3
+ size 594
original/compiled/UnetChunk2.mlmodelc/metadata.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "metadataOutputVersion" : "3.0",
4
+ "storagePrecision" : "Float16",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32)",
11
+ "shortDescription" : "",
12
+ "shape" : "[]",
13
+ "name" : "noise_pred",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "modelParameters" : [
18
+
19
+ ],
20
+ "specificationVersion" : 7,
21
+ "mlProgramOperationTypeHistogram" : {
22
+ "Split" : 9,
23
+ "Concat" : 10,
24
+ "Ios16.cast" : 14,
25
+ "Ios16.mul" : 108,
26
+ "Ios16.rsqrt" : 27,
27
+ "Ios16.sqrt" : 30,
28
+ "Ios16.sub" : 57,
29
+ "UpsampleNearestNeighbor" : 3,
30
+ "Ios16.conv" : 153,
31
+ "Ios16.add" : 141,
32
+ "Ios16.realDiv" : 30,
33
+ "Ios16.matmul" : 36,
34
+ "Ios16.gelu" : 9,
35
+ "Ios16.reduceMean" : 114,
36
+ "Ios16.softmax" : 18,
37
+ "Ios16.batchNorm" : 30,
38
+ "Ios16.square" : 30,
39
+ "Ios16.reshape" : 150,
40
+ "Ios16.silu" : 21
41
+ },
42
+ "computePrecision" : "Mixed (Int32, Float16, Float32)",
43
+ "isUpdatable" : "0",
44
+ "availability" : {
45
+ "macOS" : "13.0",
46
+ "tvOS" : "16.0",
47
+ "watchOS" : "9.0",
48
+ "iOS" : "16.0",
49
+ "macCatalyst" : "16.0"
50
+ },
51
+ "modelType" : {
52
+ "name" : "MLModelType_mlProgram"
53
+ },
54
+ "userDefinedMetadata" : {
55
+
56
+ },
57
+ "inputSchema" : [
58
+ {
59
+ "hasShapeFlexibility" : "0",
60
+ "isOptional" : "0",
61
+ "dataType" : "Float16",
62
+ "formattedType" : "MultiArray (Float16 2 × 1024 × 1 × 77)",
63
+ "shortDescription" : "",
64
+ "shape" : "[2, 1024, 1, 77]",
65
+ "name" : "encoder_hidden_states",
66
+ "type" : "MultiArray"
67
+ },
68
+ {
69
+ "hasShapeFlexibility" : "0",
70
+ "isOptional" : "0",
71
+ "dataType" : "Float32",
72
+ "formattedType" : "MultiArray (Float32 2 × 640 × 32 × 32)",
73
+ "shortDescription" : "",
74
+ "shape" : "[2, 640, 32, 32]",
75
+ "name" : "input_89_cast",
76
+ "type" : "MultiArray"
77
+ },
78
+ {
79
+ "hasShapeFlexibility" : "0",
80
+ "isOptional" : "0",
81
+ "dataType" : "Float32",
82
+ "formattedType" : "MultiArray (Float32 2 × 640 × 16 × 16)",
83
+ "shortDescription" : "",
84
+ "shape" : "[2, 640, 16, 16]",
85
+ "name" : "input_117_cast",
86
+ "type" : "MultiArray"
87
+ },
88
+ {
89
+ "hasShapeFlexibility" : "0",
90
+ "isOptional" : "0",
91
+ "dataType" : "Float32",
92
+ "formattedType" : "MultiArray (Float32 2 × 1280 × 16 × 16)",
93
+ "shortDescription" : "",
94
+ "shape" : "[2, 1280, 16, 16]",
95
+ "name" : "input_143_cast",
96
+ "type" : "MultiArray"
97
+ },
98
+ {
99
+ "hasShapeFlexibility" : "0",
100
+ "isOptional" : "0",
101
+ "dataType" : "Float32",
102
+ "formattedType" : "MultiArray (Float32 2 × 1280 × 8 × 8)",
103
+ "shortDescription" : "",
104
+ "shape" : "[2, 1280, 8, 8]",
105
+ "name" : "input_171_cast",
106
+ "type" : "MultiArray"
107
+ },
108
+ {
109
+ "hasShapeFlexibility" : "0",
110
+ "isOptional" : "0",
111
+ "dataType" : "Float32",
112
+ "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
113
+ "shortDescription" : "",
114
+ "shape" : "[2, 320, 64, 64]",
115
+ "name" : "input_35_cast",
116
+ "type" : "MultiArray"
117
+ },
118
+ {
119
+ "hasShapeFlexibility" : "0",
120
+ "isOptional" : "0",
121
+ "dataType" : "Float32",
122
+ "formattedType" : "MultiArray (Float32 2 × 1280 × 8 × 8)",
123
+ "shortDescription" : "",
124
+ "shape" : "[2, 1280, 8, 8]",
125
+ "name" : "hidden_states_149_cast",
126
+ "type" : "MultiArray"
127
+ },
128
+ {
129
+ "hasShapeFlexibility" : "0",
130
+ "isOptional" : "0",
131
+ "dataType" : "Float32",
132
+ "formattedType" : "MultiArray (Float32 2 × 1280 × 1 × 1)",
133
+ "shortDescription" : "",
134
+ "shape" : "[2, 1280, 1, 1]",
135
+ "name" : "input_15_cast",
136
+ "type" : "MultiArray"
137
+ },
138
+ {
139
+ "hasShapeFlexibility" : "0",
140
+ "isOptional" : "0",
141
+ "dataType" : "Float32",
142
+ "formattedType" : "MultiArray (Float32 2 × 2560 × 8 × 8)",
143
+ "shortDescription" : "",
144
+ "shape" : "[2, 2560, 8, 8]",
145
+ "name" : "input_253_cast",
146
+ "type" : "MultiArray"
147
+ },
148
+ {
149
+ "hasShapeFlexibility" : "0",
150
+ "isOptional" : "0",
151
+ "dataType" : "Float32",
152
+ "formattedType" : "MultiArray (Float32 2 × 1280 × 16 × 16)",
153
+ "shortDescription" : "",
154
+ "shape" : "[2, 1280, 16, 16]",
155
+ "name" : "input_169_cast",
156
+ "type" : "MultiArray"
157
+ },
158
+ {
159
+ "hasShapeFlexibility" : "0",
160
+ "isOptional" : "0",
161
+ "dataType" : "Float32",
162
+ "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
163
+ "shortDescription" : "",
164
+ "shape" : "[2, 320, 64, 64]",
165
+ "name" : "input_7_cast",
166
+ "type" : "MultiArray"
167
+ },
168
+ {
169
+ "hasShapeFlexibility" : "0",
170
+ "isOptional" : "0",
171
+ "dataType" : "Float32",
172
+ "formattedType" : "MultiArray (Float32 2 × 320 × 64 × 64)",
173
+ "shortDescription" : "",
174
+ "shape" : "[2, 320, 64, 64]",
175
+ "name" : "input_61_cast",
176
+ "type" : "MultiArray"
177
+ },
178
+ {
179
+ "hasShapeFlexibility" : "0",
180
+ "isOptional" : "0",
181
+ "dataType" : "Float32",
182
+ "formattedType" : "MultiArray (Float32 2 × 640 × 32 × 32)",
183
+ "shortDescription" : "",
184
+ "shape" : "[2, 640, 32, 32]",
185
+ "name" : "input_115_cast",
186
+ "type" : "MultiArray"
187
+ },
188
+ {
189
+ "hasShapeFlexibility" : "0",
190
+ "isOptional" : "0",
191
+ "dataType" : "Float32",
192
+ "formattedType" : "MultiArray (Float32 2 × 320 × 32 × 32)",
193
+ "shortDescription" : "",
194
+ "shape" : "[2, 320, 32, 32]",
195
+ "name" : "input_63_cast",
196
+ "type" : "MultiArray"
197
+ }
198
+ ],
199
+ "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_unet_chunk2",
200
+ "method" : "predict"
201
+ }
202
+ ]
original/compiled/UnetChunk2.mlmodelc/model.mil ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e401ac837c0b9c1694ce25f168d4171984f61057914cf1930058259b18d84a0e
3
+ size 453215
original/compiled/UnetChunk2.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0247eb40d83edbae2bfe61471f42b6c11623521c0e11e1fd40c445c9eb217e05
3
+ size 838545664
original/compiled/VAEDecoder.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d835ab6a28507b9372228403ddcead3d2d823fcceb89b4e5b1bf77e4624bdb5
3
+ size 207
original/compiled/VAEDecoder.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a36c5656d3de3f3a98493d7b500b2523485b9250d7d445228140c86516cd61
3
+ size 764
original/compiled/VAEDecoder.mlmodelc/metadata.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "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.",
4
+ "metadataOutputVersion" : "3.0",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32)",
11
+ "shortDescription" : "Generated image normalized to range [-1, 1]",
12
+ "shape" : "[]",
13
+ "name" : "image",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "version" : "stabilityai\/stable-diffusion-2-base",
18
+ "modelParameters" : [
19
+
20
+ ],
21
+ "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
22
+ "specificationVersion" : 7,
23
+ "storagePrecision" : "Float16",
24
+ "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
25
+ "mlProgramOperationTypeHistogram" : {
26
+ "Ios16.cast" : 1,
27
+ "Ios16.mul" : 1,
28
+ "Ios16.sqrt" : 30,
29
+ "Ios16.sub" : 30,
30
+ "Transpose" : 3,
31
+ "UpsampleNearestNeighbor" : 3,
32
+ "Ios16.conv" : 36,
33
+ "Ios16.add" : 45,
34
+ "Ios16.linear" : 4,
35
+ "Ios16.matmul" : 2,
36
+ "Ios16.realDiv" : 30,
37
+ "Ios16.reduceMean" : 60,
38
+ "Ios16.softmax" : 1,
39
+ "Ios16.batchNorm" : 30,
40
+ "Ios16.square" : 30,
41
+ "Ios16.reshape" : 62,
42
+ "Ios16.silu" : 29
43
+ },
44
+ "computePrecision" : "Mixed (Float32, Float16, Int32)",
45
+ "isUpdatable" : "0",
46
+ "availability" : {
47
+ "macOS" : "13.0",
48
+ "tvOS" : "16.0",
49
+ "watchOS" : "9.0",
50
+ "iOS" : "16.0",
51
+ "macCatalyst" : "16.0"
52
+ },
53
+ "modelType" : {
54
+ "name" : "MLModelType_mlProgram"
55
+ },
56
+ "inputSchema" : [
57
+ {
58
+ "hasShapeFlexibility" : "0",
59
+ "isOptional" : "0",
60
+ "dataType" : "Float16",
61
+ "formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
62
+ "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
63
+ "shape" : "[1, 4, 64, 64]",
64
+ "name" : "z",
65
+ "type" : "MultiArray"
66
+ }
67
+ ],
68
+ "userDefinedMetadata" : {
69
+ "com.github.apple.coremltools.version" : "6.1",
70
+ "com.github.apple.coremltools.source" : "torch==1.13.0"
71
+ },
72
+ "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_vae_decoder",
73
+ "method" : "predict"
74
+ }
75
+ ]
original/compiled/VAEDecoder.mlmodelc/model.mil ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e81b2a9a82856be34e91448bc3c033b5ed03d5868f848c7cff5a0b3ef2e339
3
+ size 174068
original/compiled/VAEDecoder.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cfc4dd755c560d36fbddf7509bd5be22bd1cf99a4ef1b07ecb8cf53c65671e3
3
+ size 99039232
original/compiled/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
original/compiled/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_text_encoder.mlpackage/Data/com.apple.CoreML/model.mlmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a71924fd48ac4c9755a8593a2187eb762158c9b5496dc04be232ce7961aee98
3
+ size 272308
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_text_encoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb9254ab40377228ca6d53e67f55d908a2ec6d6ce4a10a88b17b6e6bf245ce4
3
+ size 680811520
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_text_encoder.mlpackage/Manifest.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fileFormatVersion": "1.0.0",
3
+ "itemInfoEntries": {
4
+ "14E34FFA-CEB6-4D04-98DA-8E00747528E2": {
5
+ "author": "com.apple.CoreML",
6
+ "description": "CoreML Model Specification",
7
+ "name": "model.mlmodel",
8
+ "path": "com.apple.CoreML/model.mlmodel"
9
+ },
10
+ "5CC49EC2-4BB4-4EE5-83DA-84AA4D4702C8": {
11
+ "author": "com.apple.CoreML",
12
+ "description": "CoreML Model Weights",
13
+ "name": "weights",
14
+ "path": "com.apple.CoreML/weights"
15
+ }
16
+ },
17
+ "rootModelIdentifier": "14E34FFA-CEB6-4D04-98DA-8E00747528E2"
18
+ }
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet.mlpackage/Data/com.apple.CoreML/model.mlmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f835e04916dab6caf34727d6f2e03812ed969bfeefdcda011477e23cd9ab34d1
3
+ size 723016
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet.mlpackage/Data/com.apple.CoreML/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ba62298577f8d4cd8f72499b430dcd9f5bd97de97ef03a6fbbfa07d5084375
3
+ size 1732124416
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet.mlpackage/Manifest.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fileFormatVersion": "1.0.0",
3
+ "itemInfoEntries": {
4
+ "60D57603-AC65-41C4-836C-8FD23D238E38": {
5
+ "author": "com.apple.CoreML",
6
+ "description": "CoreML Model Weights",
7
+ "name": "weights",
8
+ "path": "com.apple.CoreML/weights"
9
+ },
10
+ "880A4008-C0EF-4C86-9D55-3E0620077995": {
11
+ "author": "com.apple.CoreML",
12
+ "description": "CoreML Model Specification",
13
+ "name": "model.mlmodel",
14
+ "path": "com.apple.CoreML/model.mlmodel"
15
+ }
16
+ },
17
+ "rootModelIdentifier": "880A4008-C0EF-4C86-9D55-3E0620077995"
18
+ }
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk1.mlpackage/Data/com.apple.CoreML/model.mlmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6196485906b3848c2d08bbc814aadb9201446813ad1de633957529e3a6a54cc
3
+ size 339619
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk1.mlpackage/Data/com.apple.CoreML/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca43df7b15979733f57a0cceb2ebe8c6ecdd300ccdf5ec83195c3141eca368e
3
+ size 893578816
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk1.mlpackage/Manifest.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fileFormatVersion": "1.0.0",
3
+ "itemInfoEntries": {
4
+ "024005F0-7C72-4322-A540-A4A5F0C411AE": {
5
+ "author": "com.apple.CoreML",
6
+ "description": "CoreML Model Specification",
7
+ "name": "model.mlmodel",
8
+ "path": "com.apple.CoreML/model.mlmodel"
9
+ },
10
+ "16B70004-3583-4B73-8A40-E9E363157A2B": {
11
+ "author": "com.apple.CoreML",
12
+ "description": "CoreML Model Weights",
13
+ "name": "weights",
14
+ "path": "com.apple.CoreML/weights"
15
+ }
16
+ },
17
+ "rootModelIdentifier": "024005F0-7C72-4322-A540-A4A5F0C411AE"
18
+ }
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk2.mlpackage/Data/com.apple.CoreML/model.mlmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8358bea2a9640869d57dad1001f9dd666b8da9f8b654434920518ae7112ddacd
3
+ size 389721
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk2.mlpackage/Data/com.apple.CoreML/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0247eb40d83edbae2bfe61471f42b6c11623521c0e11e1fd40c445c9eb217e05
3
+ size 838545664
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_unet_chunk2.mlpackage/Manifest.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fileFormatVersion": "1.0.0",
3
+ "itemInfoEntries": {
4
+ "C2A2E846-6A7D-4431-B32C-4686A5335A7D": {
5
+ "author": "com.apple.CoreML",
6
+ "description": "CoreML Model Specification",
7
+ "name": "model.mlmodel",
8
+ "path": "com.apple.CoreML/model.mlmodel"
9
+ },
10
+ "FF6F2631-49A1-4696-AF9A-FE49A7854A05": {
11
+ "author": "com.apple.CoreML",
12
+ "description": "CoreML Model Weights",
13
+ "name": "weights",
14
+ "path": "com.apple.CoreML/weights"
15
+ }
16
+ },
17
+ "rootModelIdentifier": "C2A2E846-6A7D-4431-B32C-4686A5335A7D"
18
+ }
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_decoder.mlpackage/Data/com.apple.CoreML/model.mlmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0bf6de6c344653c0ee3f772a005668816c4a9387c3c67398ee698a7428a1b5
3
+ size 147330
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_decoder.mlpackage/Data/com.apple.CoreML/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cfc4dd755c560d36fbddf7509bd5be22bd1cf99a4ef1b07ecb8cf53c65671e3
3
+ size 99039232
original/packages/Stable_Diffusion_version_stabilityai_stable-diffusion-2-base_vae_decoder.mlpackage/Manifest.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fileFormatVersion": "1.0.0",
3
+ "itemInfoEntries": {
4
+ "4F88DC40-7018-4DBB-96A4-B91F46329C9D": {
5
+ "author": "com.apple.CoreML",
6
+ "description": "CoreML Model Weights",
7
+ "name": "weights",
8
+ "path": "com.apple.CoreML/weights"
9
+ },
10
+ "B2005FF8-44D3-4E91-B8A3-D3954E229386": {
11
+ "author": "com.apple.CoreML",
12
+ "description": "CoreML Model Specification",
13
+ "name": "model.mlmodel",
14
+ "path": "com.apple.CoreML/model.mlmodel"
15
+ }
16
+ },
17
+ "rootModelIdentifier": "B2005FF8-44D3-4E91-B8A3-D3954E229386"
18
+ }
split_einsum/compiled/TextEncoder.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77320e8a1011459dff4b3a384069fcb45370a5ec87ef845fed7651f4453f2984
3
+ size 207
split_einsum/compiled/TextEncoder.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14668c0a30131497354d488afdec77bd753ac59aaedfbcfe512ec6e2be5af63b
3
+ size 834
split_einsum/compiled/TextEncoder.mlmodelc/metadata.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "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.",
4
+ "metadataOutputVersion" : "3.0",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32)",
11
+ "shortDescription" : "The token embeddings as encoded by the Transformer model",
12
+ "shape" : "[]",
13
+ "name" : "last_hidden_state",
14
+ "type" : "MultiArray"
15
+ },
16
+ {
17
+ "hasShapeFlexibility" : "0",
18
+ "isOptional" : "0",
19
+ "dataType" : "Float32",
20
+ "formattedType" : "MultiArray (Float32)",
21
+ "shortDescription" : "The version of the `last_hidden_state` output after pooling",
22
+ "shape" : "[]",
23
+ "name" : "pooled_outputs",
24
+ "type" : "MultiArray"
25
+ }
26
+ ],
27
+ "version" : "stabilityai\/stable-diffusion-2-base",
28
+ "modelParameters" : [
29
+
30
+ ],
31
+ "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
32
+ "specificationVersion" : 7,
33
+ "storagePrecision" : "Float16",
34
+ "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
35
+ "mlProgramOperationTypeHistogram" : {
36
+ "Ios16.cast" : 3,
37
+ "Ios16.mul" : 23,
38
+ "Ios16.layerNorm" : 47,
39
+ "Ios16.sub" : 1,
40
+ "BandPart" : 1,
41
+ "Stack" : 1,
42
+ "Transpose" : 115,
43
+ "Ios16.linear" : 138,
44
+ "Ios16.add" : 70,
45
+ "Ios16.matmul" : 46,
46
+ "Ios16.gelu" : 23,
47
+ "Ios16.softmax" : 23,
48
+ "ExpandDims" : 1,
49
+ "Ios16.gather" : 1,
50
+ "Ios16.gatherNd" : 1,
51
+ "Ios16.reshape" : 230,
52
+ "Ios16.reduceArgmax" : 1
53
+ },
54
+ "computePrecision" : "Mixed (Float16, Float32, Int32)",
55
+ "isUpdatable" : "0",
56
+ "availability" : {
57
+ "macOS" : "13.0",
58
+ "tvOS" : "16.0",
59
+ "watchOS" : "9.0",
60
+ "iOS" : "16.0",
61
+ "macCatalyst" : "16.0"
62
+ },
63
+ "modelType" : {
64
+ "name" : "MLModelType_mlProgram"
65
+ },
66
+ "inputSchema" : [
67
+ {
68
+ "hasShapeFlexibility" : "0",
69
+ "isOptional" : "0",
70
+ "dataType" : "Float32",
71
+ "formattedType" : "MultiArray (Float32 1 × 77)",
72
+ "shortDescription" : "The token ids that represent the input text",
73
+ "shape" : "[1, 77]",
74
+ "name" : "input_ids",
75
+ "type" : "MultiArray"
76
+ }
77
+ ],
78
+ "userDefinedMetadata" : {
79
+ "com.github.apple.coremltools.version" : "6.1",
80
+ "com.github.apple.coremltools.source" : "torch==1.13.0"
81
+ },
82
+ "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_text_encoder",
83
+ "method" : "predict"
84
+ }
85
+ ]
split_einsum/compiled/TextEncoder.mlmodelc/model.mil ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3214a3aaa8cd8a7ab25040804d81ab0b6eb5a1a8eb07e3a240c1270e44135fad
3
+ size 320318
split_einsum/compiled/TextEncoder.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e45244e90a89457c6a650c37879413e8c61fd8858d9c4f79bc4f67f6af99628c
3
+ size 680811520
split_einsum/compiled/Unet.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:706232b3ea81300b6a69d984705a9983fe84afc6d07551ad20b46deb17403a28
3
+ size 207
split_einsum/compiled/Unet.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29a62bd609fa8d005e854d7acbdc91a8787e59dc66a3c657eed9d8c03ae7efa
3
+ size 1215
split_einsum/compiled/Unet.mlmodelc/metadata.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "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.",
4
+ "metadataOutputVersion" : "3.0",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32)",
11
+ "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to faciliate the reverse diffusion (denoising) process",
12
+ "shape" : "[]",
13
+ "name" : "noise_pred",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "version" : "stabilityai\/stable-diffusion-2-base",
18
+ "modelParameters" : [
19
+
20
+ ],
21
+ "author" : "Please refer to the Model Card available at huggingface.co\/stabilityai\/stable-diffusion-2-base",
22
+ "specificationVersion" : 7,
23
+ "storagePrecision" : "Float16",
24
+ "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
25
+ "mlProgramOperationTypeHistogram" : {
26
+ "Transpose" : 32,
27
+ "UpsampleNearestNeighbor" : 3,
28
+ "Ios16.reduceMean" : 218,
29
+ "Ios16.sin" : 1,
30
+ "Ios16.softmax" : 390,
31
+ "Split" : 16,
32
+ "Ios16.add" : 265,
33
+ "Concat" : 46,
34
+ "Ios16.realDiv" : 61,
35
+ "Ios16.square" : 61,
36
+ "ExpandDims" : 3,
37
+ "Ios16.sub" : 109,
38
+ "Ios16.cast" : 1,
39
+ "Ios16.conv" : 282,
40
+ "Ios16.einsum" : 780,
41
+ "Ios16.gelu" : 16,
42
+ "Ios16.reshape" : 154,
43
+ "Ios16.batchNorm" : 61,
44
+ "Ios16.rsqrt" : 48,
45
+ "Ios16.silu" : 47,
46
+ "Ios16.sqrt" : 61,
47
+ "SliceByIndex" : 1172,
48
+ "Ios16.mul" : 551,
49
+ "Ios16.cos" : 1
50
+ },
51
+ "computePrecision" : "Mixed (Float32, Float16, Int32)",
52
+ "isUpdatable" : "0",
53
+ "availability" : {
54
+ "macOS" : "13.0",
55
+ "tvOS" : "16.0",
56
+ "watchOS" : "9.0",
57
+ "iOS" : "16.0",
58
+ "macCatalyst" : "16.0"
59
+ },
60
+ "modelType" : {
61
+ "name" : "MLModelType_mlProgram"
62
+ },
63
+ "inputSchema" : [
64
+ {
65
+ "hasShapeFlexibility" : "0",
66
+ "isOptional" : "0",
67
+ "dataType" : "Float16",
68
+ "formattedType" : "MultiArray (Float16 2 × 4 × 64 × 64)",
69
+ "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
70
+ "shape" : "[2, 4, 64, 64]",
71
+ "name" : "sample",
72
+ "type" : "MultiArray"
73
+ },
74
+ {
75
+ "hasShapeFlexibility" : "0",
76
+ "isOptional" : "0",
77
+ "dataType" : "Float16",
78
+ "formattedType" : "MultiArray (Float16 2)",
79
+ "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule",
80
+ "shape" : "[2]",
81
+ "name" : "timestep",
82
+ "type" : "MultiArray"
83
+ },
84
+ {
85
+ "hasShapeFlexibility" : "0",
86
+ "isOptional" : "0",
87
+ "dataType" : "Float16",
88
+ "formattedType" : "MultiArray (Float16 2 × 1024 × 1 × 77)",
89
+ "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.",
90
+ "shape" : "[2, 1024, 1, 77]",
91
+ "name" : "encoder_hidden_states",
92
+ "type" : "MultiArray"
93
+ }
94
+ ],
95
+ "userDefinedMetadata" : {
96
+ "com.github.apple.coremltools.version" : "6.1",
97
+ "com.github.apple.coremltools.source" : "torch==1.13.0"
98
+ },
99
+ "generatedClassName" : "Stable_Diffusion_version_stabilityai_stable_diffusion_2_base_unet",
100
+ "method" : "predict"
101
+ }
102
+ ]