{ "_class_name": "ACEStepTransformer2DModel", "_diffusers_version": "0.32.2", "attention_head_dim": 128, "in_channels": 8, "inner_dim": 2560, "lyric_encoder_vocab_size": 6693, "lyric_hidden_size": 1024, "max_height": 16, "max_position": 32768, "max_width": 32768, "mlp_ratio": 2.5, "num_attention_heads": 20, "num_layers": 24, "out_channels": 8, "patch_size": [ 16, 1 ], "rope_theta": 1000000.0, "speaker_embedding_dim": 512, "ssl_encoder_depths": [ 8, 8 ], "ssl_latent_dims": [ 1024, 768 ], "ssl_names": [ "mert", "m-hubert" ], "text_embedding_dim": 768 }