Hugging Face's logo

keras
/
stable_diffusion_3_medium

KerasHub
Model card Files Community
stable_diffusion_3_medium
File size: 3,108 Bytes 
78109f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "module": "keras_hub.src.models.stable_diffusion_3.stable_diffusion_3_backbone",
    "class_name": "StableDiffusion3Backbone",
    "config": {
        "name": "stable_diffusion_3_backbone",
        "trainable": true,
        "mmdit_patch_size": 2,
        "mmdit_hidden_dim": 1536,
        "mmdit_num_layers": 24,
        "mmdit_num_heads": 24,
        "mmdit_position_size": 192,
        "vae": {
            "module": "keras_hub.src.models.vae.vae_backbone",
            "class_name": "VAEBackbone",
            "config": {
                "name": "vae",
                "trainable": true,
                "encoder_num_filters": [
                    128,
                    256,
                    512,
                    512
                ],
                "encoder_num_blocks": [
                    2,
                    2,
                    2,
                    2
                ],
                "decoder_num_filters": [
                    512,
                    512,
                    256,
                    128
                ],
                "decoder_num_blocks": [
                    3,
                    3,
                    3,
                    3
                ],
                "sampler_method": "sample",
                "input_channels": 3,
                "sample_channels": 32,
                "output_channels": 3,
                "scale": 1.5305,
                "shift": 0.0609
            },
            "registered_name": "VAEBackbone"
        },
        "clip_l": {
            "module": "keras_hub.src.models.clip.clip_text_encoder",
            "class_name": "CLIPTextEncoder",
            "config": {
                "name": "clip_l",
                "trainable": true,
                "vocabulary_size": 49408,
                "embedding_dim": 768,
                "hidden_dim": 768,
                "num_layers": 12,
                "num_heads": 12,
                "intermediate_dim": 3072,
                "intermediate_activation": "quick_gelu",
                "intermediate_output_index": 10,
                "max_sequence_length": 77
            },
            "registered_name": "CLIPTextEncoder"
        },
        "clip_g": {
            "module": "keras_hub.src.models.clip.clip_text_encoder",
            "class_name": "CLIPTextEncoder",
            "config": {
                "name": "clip_g",
                "trainable": true,
                "vocabulary_size": 49408,
                "embedding_dim": 1280,
                "hidden_dim": 1280,
                "num_layers": 32,
                "num_heads": 20,
                "intermediate_dim": 5120,
                "intermediate_activation": "gelu",
                "intermediate_output_index": 30,
                "max_sequence_length": 77
            },
            "registered_name": "CLIPTextEncoder"
        },
        "t5": null,
        "latent_channels": 16,
        "output_channels": 3,
        "num_train_timesteps": 1000,
        "shift": 3.0,
        "height": 1024,
        "width": 1024
    },
    "registered_name": "keras_hub>StableDiffusion3Backbone"
}