| { | |
| "_class_name": "MiniMaxH3ImageTransformer2DModel", | |
| "_diffusers_version": "0.42.0.dev0", | |
| "num_attention_heads": 56, | |
| "attention_head_dim": 128, | |
| "hidden_size": 5376, | |
| "num_layers": 50, | |
| "num_refiner_layers": 2, | |
| "ffn_dim": 14336, | |
| "in_channels": 24, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "text_dim": 5120, | |
| "freq_dim": 256, | |
| "time_embed_hidden_dim": 5376, | |
| "time_embed_dim": 2688, | |
| "rope_freq_dim": 16, | |
| "rope_theta": 10000.0, | |
| "norm_eps": 1e-05, | |
| "qk_norm_eps": 1e-05, | |
| "final_norm_eps": 1e-05, | |
| "num_pdd_heads": 6 | |
| } |