| { | |
| "dit_config": { | |
| "in_channels": 34, | |
| "out_channels": 32, | |
| "latent_h": 32, | |
| "panel_w": 32, | |
| "patch": 1, | |
| "d_model": 1024, | |
| "depth": 16, | |
| "heads": 16, | |
| "mlp_ratio": 3.0, | |
| "ctx_dim": 768, | |
| "n_tasks": 3 | |
| }, | |
| "lat_std": 0.98046875, | |
| "scaling_factor": 0.41407, | |
| "vae": "mit-han-lab/dc-ae-f32c32-sana-1.1-diffusers", | |
| "text_encoder": "openai/clip-vit-large-patch14", | |
| "resolution": 1024, | |
| "steps_trained": 100000 | |
| } |