vae_config.json

{"base_dim": 96, "decoder_base_dim": null, "z_dim": 16, "dim_mult": [1, 2, 4, 4], "num_res_blocks": 2, "attn_scales": [], "temperal_downsample": [false, true, true], "dropout": 0.0, "latents_mean": [-0.7571, -0.7089, -0.9113, 0.1075, -0.1745, 0.9653, -0.1517, 1.5508, 0.4134, -0.0715, 0.5517, -0.3632, -0.1922, -0.9497, 0.2503, -0.2921], "latents_std": [2.8184, 1.4541, 2.3275, 2.6558, 1.2196, 1.7708, 2.6052, 2.0743, 3.2687, 2.1526, 2.8652, 1.5579, 1.6382, 1.1253, 2.8251, 1.916], "is_residual": false, "in_channels": 3, "out_channels": 3, "patch_size": null, "scale_factor_temporal": 4, "scale_factor_spatial": 8, "_use_default_values": ["patch_size", "out_channels", "in_channels", "scale_factor_temporal", "decoder_base_dim", "is_residual", "scale_factor_spatial"], "_class_name": "AutoencoderKLWan", "_diffusers_version": "0.33.0.dev0", "_name_or_path": "Bernini-R-1.3B-Diffusers"}