darkmaniac7 commited on
Commit
cee25c3
·
verified ·
1 Parent(s): deb387d

ReV Animated 6-bit loose Resources

Browse files
TokForge-ReV-Animated-CoreML-6bit/Resources/TextEncoder.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd08e47a7b1275fa68d7c8918dc9856fc661e8dec271cbcae0535618867df78e
3
+ size 243
TokForge-ReV-Animated-CoreML-6bit/Resources/TextEncoder.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:741becffcb49f4ce95271987538b5e931044c670ba36e06e8777e52fe07a40b0
3
+ size 958
TokForge-ReV-Animated-CoreML-6bit/Resources/TextEncoder.mlmodelc/metadata.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 1 × 77 × 768)",
11
+ "shortDescription" : "The token embeddings as encoded by the Transformer model",
12
+ "shape" : "[1, 77, 768]",
13
+ "name" : "last_hidden_state",
14
+ "type" : "MultiArray"
15
+ },
16
+ {
17
+ "hasShapeFlexibility" : "0",
18
+ "isOptional" : "0",
19
+ "dataType" : "Float32",
20
+ "formattedType" : "MultiArray (Float32 1 × 768)",
21
+ "shortDescription" : "The version of the `last_hidden_state` output after pooling",
22
+ "shape" : "[1, 768]",
23
+ "name" : "pooled_outputs",
24
+ "type" : "MultiArray"
25
+ }
26
+ ],
27
+ "version" : "stablediffusionapi\/rev-animated",
28
+ "modelParameters" : [
29
+
30
+ ],
31
+ "author" : "Please refer to the Model Card available at huggingface.co\/stablediffusionapi\/rev-animated",
32
+ "specificationVersion" : 7,
33
+ "storagePrecision" : "Mixed (Float16, Palettized (6 bits))",
34
+ "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
35
+ "mlProgramOperationTypeHistogram" : {
36
+ "Ios16.cast" : 3,
37
+ "Ios16.mul" : 36,
38
+ "Ios16.layerNorm" : 25,
39
+ "Ios16.constexprLutToDense" : 74,
40
+ "Transpose" : 48,
41
+ "Stack" : 1,
42
+ "Ios16.sigmoid" : 12,
43
+ "Ios16.linear" : 72,
44
+ "Ios16.add" : 37,
45
+ "Ios16.softmax" : 12,
46
+ "Ios16.matmul" : 24,
47
+ "Ios16.gatherNd" : 1,
48
+ "Ios16.gather" : 1,
49
+ "Ios16.reshape" : 48,
50
+ "Ios16.reduceArgmax" : 1
51
+ },
52
+ "computePrecision" : "Mixed (Float16, Float32, Int32)",
53
+ "stateSchema" : [
54
+
55
+ ],
56
+ "isUpdatable" : "0",
57
+ "availability" : {
58
+ "macOS" : "13.0",
59
+ "tvOS" : "16.0",
60
+ "visionOS" : "1.0",
61
+ "watchOS" : "9.0",
62
+ "iOS" : "16.0",
63
+ "macCatalyst" : "16.0"
64
+ },
65
+ "modelType" : {
66
+ "name" : "MLModelType_mlProgram"
67
+ },
68
+ "inputSchema" : [
69
+ {
70
+ "hasShapeFlexibility" : "0",
71
+ "isOptional" : "0",
72
+ "dataType" : "Float32",
73
+ "formattedType" : "MultiArray (Float32 1 × 77)",
74
+ "shortDescription" : "The token ids that represent the input text",
75
+ "shape" : "[1, 77]",
76
+ "name" : "input_ids",
77
+ "type" : "MultiArray"
78
+ }
79
+ ],
80
+ "userDefinedMetadata" : {
81
+ "com.github.apple.coremltools.conversion_date" : "2026-06-25",
82
+ "com.github.apple.coremltools.source" : "torch==2.7.0",
83
+ "com.github.apple.coremltools.version" : "9.0",
84
+ "com.github.apple.coremltools.source_dialect" : "TorchScript"
85
+ },
86
+ "generatedClassName" : "Stable_Diffusion_version_stablediffusionapi_rev_animated_text_encoder",
87
+ "method" : "predict"
88
+ }
89
+ ]
TokForge-ReV-Animated-CoreML-6bit/Resources/TextEncoder.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
TokForge-ReV-Animated-CoreML-6bit/Resources/TextEncoder.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482da2b8bd69d6cb5a1d5d8ff9ccacd598da00e8c83b2ad2f13aeed0a6d475f1
3
+ size 139910080
TokForge-ReV-Animated-CoreML-6bit/Resources/Unet.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d400da32e63b39fdec9a04d6b1d7c2e469b0c9b9bb4c86f521b4f8f316103d17
3
+ size 243
TokForge-ReV-Animated-CoreML-6bit/Resources/Unet.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6681e110597188afc68732a1e0ca1ed5e9d7bc109a5a27e3aadcaced7b5544c4
3
+ size 1391
TokForge-ReV-Animated-CoreML-6bit/Resources/Unet.mlmodelc/metadata.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 2 × 4 × 64 × 64)",
11
+ "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
12
+ "shape" : "[2, 4, 64, 64]",
13
+ "name" : "noise_pred",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "version" : "stablediffusionapi\/rev-animated",
18
+ "modelParameters" : [
19
+
20
+ ],
21
+ "author" : "Please refer to the Model Card available at huggingface.co\/stablediffusionapi\/rev-animated",
22
+ "specificationVersion" : 7,
23
+ "storagePrecision" : "Mixed (Float16, Palettized (6 bits))",
24
+ "license" : "OpenRAIL (https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license)",
25
+ "mlProgramOperationTypeHistogram" : {
26
+ "Transpose" : 32,
27
+ "UpsampleNearestNeighbor" : 3,
28
+ "Ios16.reduceMean" : 122,
29
+ "Ios16.sin" : 1,
30
+ "Ios16.softmax" : 896,
31
+ "Split" : 16,
32
+ "Ios16.add" : 169,
33
+ "Concat" : 206,
34
+ "Ios16.realDiv" : 61,
35
+ "Ios16.square" : 61,
36
+ "ExpandDims" : 3,
37
+ "Ios16.sub" : 61,
38
+ "Ios16.sqrt" : 61,
39
+ "Ios16.conv" : 282,
40
+ "Ios16.constexprLutToDense" : 282,
41
+ "Ios16.einsum" : 1792,
42
+ "Ios16.layerNorm" : 48,
43
+ "SliceByIndex" : 1570,
44
+ "Ios16.batchNorm" : 61,
45
+ "Ios16.reshape" : 154,
46
+ "Ios16.silu" : 47,
47
+ "Ios16.gelu" : 16,
48
+ "Ios16.mul" : 913,
49
+ "Ios16.cos" : 1,
50
+ "Ios16.cast" : 1
51
+ },
52
+ "computePrecision" : "Mixed (Float16, Float32, Int32)",
53
+ "stateSchema" : [
54
+
55
+ ],
56
+ "isUpdatable" : "0",
57
+ "availability" : {
58
+ "macOS" : "13.0",
59
+ "tvOS" : "16.0",
60
+ "visionOS" : "1.0",
61
+ "watchOS" : "9.0",
62
+ "iOS" : "16.0",
63
+ "macCatalyst" : "16.0"
64
+ },
65
+ "modelType" : {
66
+ "name" : "MLModelType_mlProgram"
67
+ },
68
+ "inputSchema" : [
69
+ {
70
+ "hasShapeFlexibility" : "0",
71
+ "isOptional" : "0",
72
+ "dataType" : "Float16",
73
+ "formattedType" : "MultiArray (Float16 2 × 4 × 64 × 64)",
74
+ "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
75
+ "shape" : "[2, 4, 64, 64]",
76
+ "name" : "sample",
77
+ "type" : "MultiArray"
78
+ },
79
+ {
80
+ "hasShapeFlexibility" : "0",
81
+ "isOptional" : "0",
82
+ "dataType" : "Float16",
83
+ "formattedType" : "MultiArray (Float16 2)",
84
+ "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule",
85
+ "shape" : "[2]",
86
+ "name" : "timestep",
87
+ "type" : "MultiArray"
88
+ },
89
+ {
90
+ "hasShapeFlexibility" : "0",
91
+ "isOptional" : "0",
92
+ "dataType" : "Float16",
93
+ "formattedType" : "MultiArray (Float16 2 × 768 × 1 × 77)",
94
+ "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.",
95
+ "shape" : "[2, 768, 1, 77]",
96
+ "name" : "encoder_hidden_states",
97
+ "type" : "MultiArray"
98
+ }
99
+ ],
100
+ "userDefinedMetadata" : {
101
+ "com.github.apple.coremltools.conversion_date" : "2026-06-25",
102
+ "com.github.apple.ml-stable-diffusion.version" : "1.1.0",
103
+ "com.github.apple.coremltools.source" : "torch==2.7.0",
104
+ "com.github.apple.coremltools.version" : "9.0",
105
+ "com.github.apple.coremltools.source_dialect" : "TorchScript"
106
+ },
107
+ "generatedClassName" : "Stable_Diffusion_version_stablediffusionapi_rev_animated_unet",
108
+ "method" : "predict"
109
+ }
110
+ ]
TokForge-ReV-Animated-CoreML-6bit/Resources/Unet.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
TokForge-ReV-Animated-CoreML-6bit/Resources/Unet.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa40f47bd4dc139f8e7c5a64ed6b5c9608c5f284e12211a3c7b04b112d9aed60
3
+ size 645325440
TokForge-ReV-Animated-CoreML-6bit/Resources/VAEDecoder.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c57f8cfa8f8421cf8220390cf3fb3fbec0843005b31bdcb2a340a19bdf48b10
3
+ size 243
TokForge-ReV-Animated-CoreML-6bit/Resources/VAEDecoder.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42d19ae10bbe78f1cf4136902d00bf3ffd998e74b3f6061381061475c616337
3
+ size 885
TokForge-ReV-Animated-CoreML-6bit/Resources/VAEDecoder.mlmodelc/metadata.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 1 × 3 × 512 × 512)",
11
+ "shortDescription" : "Generated image normalized to range [-1, 1]",
12
+ "shape" : "[1, 3, 512, 512]",
13
+ "name" : "image",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "version" : "stablediffusionapi\/rev-animated",
18
+ "modelParameters" : [
19
+
20
+ ],
21
+ "author" : "Please refer to the Model Card available at huggingface.co\/stablediffusionapi\/rev-animated",
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" : 2,
28
+ "Ios16.sub" : 30,
29
+ "Transpose" : 6,
30
+ "Ios16.sqrt" : 30,
31
+ "UpsampleNearestNeighbor" : 3,
32
+ "Ios16.square" : 30,
33
+ "Ios16.add" : 46,
34
+ "Ios16.reduceMean" : 60,
35
+ "Ios16.realDiv" : 30,
36
+ "Ios16.conv" : 36,
37
+ "Ios16.linear" : 4,
38
+ "Ios16.matmul" : 2,
39
+ "Ios16.batchNorm" : 29,
40
+ "Ios16.softmax" : 1,
41
+ "Ios16.reshape" : 65,
42
+ "Ios16.silu" : 29
43
+ },
44
+ "computePrecision" : "Mixed (Float16, Float32, Int32)",
45
+ "stateSchema" : [
46
+
47
+ ],
48
+ "isUpdatable" : "0",
49
+ "availability" : {
50
+ "macOS" : "13.0",
51
+ "tvOS" : "16.0",
52
+ "visionOS" : "1.0",
53
+ "watchOS" : "9.0",
54
+ "iOS" : "16.0",
55
+ "macCatalyst" : "16.0"
56
+ },
57
+ "modelType" : {
58
+ "name" : "MLModelType_mlProgram"
59
+ },
60
+ "inputSchema" : [
61
+ {
62
+ "hasShapeFlexibility" : "0",
63
+ "isOptional" : "0",
64
+ "dataType" : "Float16",
65
+ "formattedType" : "MultiArray (Float16 1 × 4 × 64 × 64)",
66
+ "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
67
+ "shape" : "[1, 4, 64, 64]",
68
+ "name" : "z",
69
+ "type" : "MultiArray"
70
+ }
71
+ ],
72
+ "userDefinedMetadata" : {
73
+ "com.github.apple.coremltools.conversion_date" : "2026-06-25",
74
+ "com.github.apple.coremltools.source" : "torch==2.7.0",
75
+ "com.github.apple.coremltools.version" : "9.0",
76
+ "com.github.apple.coremltools.source_dialect" : "TorchScript"
77
+ },
78
+ "generatedClassName" : "Stable_Diffusion_version_stablediffusionapi_rev_animated_vae_decoder",
79
+ "method" : "predict"
80
+ }
81
+ ]
TokForge-ReV-Animated-CoreML-6bit/Resources/VAEDecoder.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
TokForge-ReV-Animated-CoreML-6bit/Resources/VAEDecoder.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5def6f980a7722b3ea417d971143cb042e354f2a7c894caa3ba9f6d983460007
3
+ size 98993280
TokForge-ReV-Animated-CoreML-6bit/Resources/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
TokForge-ReV-Animated-CoreML-6bit/Resources/vocab.json ADDED
The diff for this file is too large to render. See raw diff