Upload files with `sana-upload`.

Upload transformer/diffusion_pytorch_model-00005-of-00008.safetensors
Upload transformer/diffusion_pytorch_model-00006-of-00008.safetensors
Upload transformer/diffusion_pytorch_model-00002-of-00008.safetensors
Upload transformer/diffusion_pytorch_model-00003-of-00008.safetensors
Upload transformer/diffusion_pytorch_model-00007-of-00008.safetensors
Upload transformer/diffusion_pytorch_model-00004-of-00008.safetensors
Upload vae/config.json
Upload vae/diffusion_pytorch_model.safetensors
Upload vocoder/config.json
Upload vocoder/diffusion_pytorch_model.safetensors

transformer/diffusion_pytorch_model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0c73535077cdd40c44dc4a17a84c4cd110fa2ca692211737360adb7d169008
+size 4944487248

transformer/diffusion_pytorch_model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd60f01d4234cc4016c8b55cdcfc570ed9155f2b69e9ececde563db70e7df16f
+size 4994661712

transformer/diffusion_pytorch_model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a7733ddbc8b2c32b6d997e1332206c3cb0308be45268dc06033aa7884793f3
+size 4927859352

transformer/diffusion_pytorch_model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23de83b6aea3f6eb39c0f10b55f4ef972c2be576522af25f9daf6d2b49097c82
+size 4977604280

transformer/diffusion_pytorch_model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b8b093eb6125e7533c78b089da64fe50167d4a458994eba44966435c99d0ed
+size 4994844576

transformer/diffusion_pytorch_model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795542ccb575328eaf288aa725ae14bd69df57f9fad6336232b8dc09410397ba
+size 4994386864

vae/config.json

@@ -0,0 +1,93 @@
+{
+  "_class_name": "AutoencoderKLLTX2Video",
+  "_diffusers_version": "0.37.0.dev0",
+  "block_out_channels": [
+    256,
+    512,
+    1024,
+    1024
+  ],
+  "decoder_block_out_channels": [
+    256,
+    512,
+    512,
+    1024
+  ],
+  "decoder_causal": false,
+  "decoder_inject_noise": [
+    false,
+    false,
+    false,
+    false,
+    false
+  ],
+  "decoder_layers_per_block": [
+    4,
+    6,
+    4,
+    2,
+    2
+  ],
+  "decoder_spatial_padding_mode": "zeros",
+  "decoder_spatio_temporal_scaling": [
+    true,
+    true,
+    true,
+    true
+  ],
+  "down_block_types": [
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D"
+  ],
+  "downsample_type": [
+    "spatial",
+    "temporal",
+    "spatiotemporal",
+    "spatiotemporal"
+  ],
+  "encoder_causal": true,
+  "encoder_spatial_padding_mode": "zeros",
+  "in_channels": 3,
+  "latent_channels": 128,
+  "layers_per_block": [
+    4,
+    6,
+    4,
+    2,
+    2
+  ],
+  "out_channels": 3,
+  "patch_size": 4,
+  "patch_size_t": 1,
+  "resnet_norm_eps": 1e-06,
+  "scaling_factor": 1.0,
+  "spatial_compression_ratio": 32,
+  "spatio_temporal_scaling": [
+    true,
+    true,
+    true,
+    true
+  ],
+  "temporal_compression_ratio": 8,
+  "timestep_conditioning": false,
+  "upsample_factor": [
+    2,
+    2,
+    1,
+    2
+  ],
+  "upsample_residual": [
+    false,
+    false,
+    false,
+    false
+  ],
+  "upsample_type": [
+    "spatiotemporal",
+    "spatiotemporal",
+    "temporal",
+    "spatial"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425f0dfa227dee5d0ff3d9720563370810409a439c302ca74f0f944057ce55c5
+size 1452233194

vocoder/config.json

@@ -0,0 +1,104 @@
+{
+  "_class_name": "LTX2VocoderWithBWE",
+  "_diffusers_version": "0.37.0.dev0",
+  "act_fn": "snakebeta",
+  "antialias": true,
+  "antialias_kernel_size": 12,
+  "antialias_ratio": 2,
+  "bwe_act_fn": "snakebeta",
+  "bwe_antialias": true,
+  "bwe_antialias_kernel_size": 12,
+  "bwe_antialias_ratio": 2,
+  "bwe_final_act_fn": null,
+  "bwe_final_bias": false,
+  "bwe_hidden_channels": 512,
+  "bwe_in_channels": 128,
+  "bwe_leaky_relu_negative_slope": 0.1,
+  "bwe_out_channels": 2,
+  "bwe_resnet_dilations": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "bwe_resnet_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "bwe_upsample_factors": [
+    6,
+    5,
+    2,
+    2,
+    2
+  ],
+  "bwe_upsample_kernel_sizes": [
+    12,
+    11,
+    4,
+    4,
+    4
+  ],
+  "filter_length": 512,
+  "final_act_fn": null,
+  "final_bias": false,
+  "hidden_channels": 1536,
+  "hop_length": 80,
+  "in_channels": 128,
+  "input_sampling_rate": 16000,
+  "leaky_relu_negative_slope": 0.1,
+  "num_mel_channels": 64,
+  "out_channels": 2,
+  "output_sampling_rate": 48000,
+  "resnet_dilations": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resnet_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "upsample_factors": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "upsample_kernel_sizes": [
+    11,
+    4,
+    4,
+    4,
+    4,
+    4
+  ],
+  "window_length": 512
+}

vocoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99dde145a982974bc4c39608b3b929f232f0126a55d8326a47ad54f486ae23c
+size 258305056