| { | |
| "module": "keras_hub.src.models.stable_diffusion_3.stable_diffusion_3_backbone", | |
| "class_name": "StableDiffusion3Backbone", | |
| "config": { | |
| "name": "stable_diffusion_3.5_backbone", | |
| "trainable": true, | |
| "mmdit_patch_size": 2, | |
| "mmdit_hidden_dim": 2432, | |
| "mmdit_num_layers": 38, | |
| "mmdit_num_heads": 38, | |
| "mmdit_position_size": 192, | |
| "mmdit_qk_norm": "rms_norm", | |
| "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, | |
| "image_shape": [ | |
| 1024, | |
| 1024, | |
| 3 | |
| ] | |
| }, | |
| "registered_name": "keras_hub>StableDiffusion3Backbone" | |
| } |