in scripts/convert_ltx_to_diffusers.py [0:0]
def get_vae_config(version: str) -> Dict[str, Any]:
if version in ["0.9.0"]:
config = {
"in_channels": 3,
"out_channels": 3,
"latent_channels": 128,
"block_out_channels": (128, 256, 512, 512),
"down_block_types": (
"LTXVideoDownBlock3D",
"LTXVideoDownBlock3D",
"LTXVideoDownBlock3D",
"LTXVideoDownBlock3D",
),
"decoder_block_out_channels": (128, 256, 512, 512),
"layers_per_block": (4, 3, 3, 3, 4),
"decoder_layers_per_block": (4, 3, 3, 3, 4),
"spatio_temporal_scaling": (True, True, True, False),
"decoder_spatio_temporal_scaling": (True, True, True, False),
"decoder_inject_noise": (False, False, False, False, False),
"downsample_type": ("conv", "conv", "conv", "conv"),
"upsample_residual": (False, False, False, False),
"upsample_factor": (1, 1, 1, 1),
"patch_size": 4,
"patch_size_t": 1,
"resnet_norm_eps": 1e-6,
"scaling_factor": 1.0,
"encoder_causal": True,
"decoder_causal": False,
"timestep_conditioning": False,
}
elif version in ["0.9.1"]:
config = {
"in_channels": 3,
"out_channels": 3,
"latent_channels": 128,
"block_out_channels": (128, 256, 512, 512),
"down_block_types": (
"LTXVideoDownBlock3D",
"LTXVideoDownBlock3D",
"LTXVideoDownBlock3D",
"LTXVideoDownBlock3D",
),
"decoder_block_out_channels": (256, 512, 1024),
"layers_per_block": (4, 3, 3, 3, 4),
"decoder_layers_per_block": (5, 6, 7, 8),
"spatio_temporal_scaling": (True, True, True, False),
"decoder_spatio_temporal_scaling": (True, True, True),
"decoder_inject_noise": (True, True, True, False),
"downsample_type": ("conv", "conv", "conv", "conv"),
"upsample_residual": (True, True, True),
"upsample_factor": (2, 2, 2),
"timestep_conditioning": True,
"patch_size": 4,
"patch_size_t": 1,
"resnet_norm_eps": 1e-6,
"scaling_factor": 1.0,
"encoder_causal": True,
"decoder_causal": False,
}
VAE_KEYS_RENAME_DICT.update(VAE_091_RENAME_DICT)
elif version in ["0.9.5"]:
config = {
"in_channels": 3,
"out_channels": 3,
"latent_channels": 128,
"block_out_channels": (128, 256, 512, 1024, 2048),
"down_block_types": (
"LTXVideo095DownBlock3D",
"LTXVideo095DownBlock3D",
"LTXVideo095DownBlock3D",
"LTXVideo095DownBlock3D",
),
"decoder_block_out_channels": (256, 512, 1024),
"layers_per_block": (4, 6, 6, 2, 2),
"decoder_layers_per_block": (5, 5, 5, 5),
"spatio_temporal_scaling": (True, True, True, True),
"decoder_spatio_temporal_scaling": (True, True, True),
"decoder_inject_noise": (False, False, False, False),
"downsample_type": ("spatial", "temporal", "spatiotemporal", "spatiotemporal"),
"upsample_residual": (True, True, True),
"upsample_factor": (2, 2, 2),
"timestep_conditioning": True,
"patch_size": 4,
"patch_size_t": 1,
"resnet_norm_eps": 1e-6,
"scaling_factor": 1.0,
"encoder_causal": True,
"decoder_causal": False,
"spatial_compression_ratio": 32,
"temporal_compression_ratio": 8,
}
VAE_KEYS_RENAME_DICT.update(VAE_095_RENAME_DICT)
elif version in ["0.9.7"]:
config = {
"in_channels": 3,
"out_channels": 3,
"latent_channels": 128,
"block_out_channels": (128, 256, 512, 1024, 2048),
"down_block_types": (
"LTXVideo095DownBlock3D",
"LTXVideo095DownBlock3D",
"LTXVideo095DownBlock3D",
"LTXVideo095DownBlock3D",
),
"decoder_block_out_channels": (256, 512, 1024),
"layers_per_block": (4, 6, 6, 2, 2),
"decoder_layers_per_block": (5, 5, 5, 5),
"spatio_temporal_scaling": (True, True, True, True),
"decoder_spatio_temporal_scaling": (True, True, True),
"decoder_inject_noise": (False, False, False, False),
"downsample_type": ("spatial", "temporal", "spatiotemporal", "spatiotemporal"),
"upsample_residual": (True, True, True),
"upsample_factor": (2, 2, 2),
"timestep_conditioning": True,
"patch_size": 4,
"patch_size_t": 1,
"resnet_norm_eps": 1e-6,
"scaling_factor": 1.0,
"encoder_causal": True,
"decoder_causal": False,
"spatial_compression_ratio": 32,
"temporal_compression_ratio": 8,
}
VAE_KEYS_RENAME_DICT.update(VAE_095_RENAME_DICT)
return config