| { | |
| "type": "original", | |
| "imagen": { | |
| "video": false, | |
| "timesteps": [1024, 512, 512], | |
| "image_sizes": [64, 256, 1024], | |
| "random_crop_sizes": [null, 64, 256], | |
| "condition_on_text": true, | |
| "cond_drop_prob": 0.1, | |
| "text_encoder_name": "google/t5-v1_1-large", | |
| "unets": [ | |
| { | |
| "dim": 512, | |
| "dim_mults": [1, 2, 3, 4], | |
| "num_resnet_blocks": 3, | |
| "layer_attns": [false, true, true, true], | |
| "layer_cross_attns": [false, true, true, true], | |
| "attn_heads": 8 | |
| }, | |
| { | |
| "dim": 128, | |
| "dim_mults": [1, 2, 4, 8], | |
| "num_resnet_blocks": [2, 4, 8, 8], | |
| "layer_attns": [false, false, false, true], | |
| "layer_cross_attns": [false, false, false, true], | |
| "attn_heads": 8 | |
| }, | |
| { | |
| "dim": 128, | |
| "dim_mults": [1, 2, 4, 8], | |
| "num_resnet_blocks": [2, 4, 8, 8], | |
| "layer_attns": false, | |
| "layer_cross_attns": [false, false, false, true], | |
| "attn_heads": 8 | |
| } | |
| ] | |
| }, | |
| "trainer": { | |
| "lr": 1e-4 | |
| }, | |
| "dataset_name": "laion/laion2B-en", | |
| "dataset": { | |
| "batch_size": 2048, | |
| "shuffle": true | |
| }, | |
| "image_label": null, | |
| "url_label": "URL", | |
| "text_label": "TEXT", | |
| "checkpoint_path": "./imagen.pt" | |
| } | |