{ "_class_name": "AutoencoderKLMiniMaxH3Image", "_diffusers_version": "0.43.0", "block_out_channels": [ 32, 32, 32, 32, 32, 32 ], "decoder_attention_head_dim": 32, "decoder_ffn_mult": 4, "decoder_norm_eps": 1e-05, "decoder_num_attention_heads": 2, "decoder_num_layers": 4, "decoder_num_register_tokens": 4, "decoder_rope_dim_ratio": 0.5, "decoder_rope_theta": 100.0, "in_channels": 3, "latent_channels": 8, "latents_mean": [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], "latents_std": [ 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ], "layers_per_block": 2, "norm_eps": 1e-06, "norm_num_groups": 32, "out_channels": 3, "spatial_downsample_factors": [ 2, 2, 2, 2, 1, 1 ], "spatial_padding_mode": "reflect", "temporal_downsample_factors": [ 1, 2, 2, 1, 1, 1 ] }