Upload folder using huggingface_hub

q8/audio_vae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f56bdec4c877bb1db6f3e6d65c1cff6a1147a91c4a25b809e14dba4c1d5b30
+size 63836683

q8/config.json

@@ -0,0 +1,46 @@
+{
+  "model_type": "AudioVideo",
+  "num_attention_heads": 32,
+  "attention_head_dim": 128,
+  "in_channels": 128,
+  "out_channels": 128,
+  "num_layers": 48,
+  "cross_attention_dim": 4096,
+  "caption_channels": null,
+  "audio_num_attention_heads": 32,
+  "audio_attention_head_dim": 64,
+  "audio_in_channels": 128,
+  "audio_out_channels": 128,
+  "audio_cross_attention_dim": 2048,
+  "positional_embedding_theta": 10000.0,
+  "positional_embedding_max_pos": [
+    20,
+    2048,
+    2048
+  ],
+  "audio_positional_embedding_max_pos": [
+    20
+  ],
+  "timestep_scale_multiplier": 1000,
+  "av_ca_timestep_scale_multiplier": 1000,
+  "norm_eps": 1e-06,
+  "audio_sample_rate": 24000,
+  "audio_latent_sample_rate": 16000,
+  "audio_hop_length": 160,
+  "audio_latent_channels": 8,
+  "audio_mel_bins": 16,
+  "model_version": "2.3.0",
+  "is_v2": true,
+  "apply_gated_attention": true,
+  "cross_attention_adaln": true,
+  "connector_positional_embedding_max_pos": [
+    4096
+  ],
+  "connector_rope_type": "SPLIT",
+  "connector_num_attention_heads": 32,
+  "connector_attention_head_dim": 128,
+  "audio_connector_num_attention_heads": 32,
+  "audio_connector_attention_head_dim": 64,
+  "caption_projection_first_linear": false,
+  "caption_projection_second_linear": false
+}

q8/connector.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1576c14ac7f7596a41e39e835d6d3e136567922c31edcd4f693b492d46c8541
+size 6344493078

q8/embedded_config.json

@@ -0,0 +1,302 @@
+{
+  "transformer": {
+    "_class_name": "AVTransformer3DModel",
+    "attention_head_dim": 128,
+    "attention_type": "default",
+    "caption_channels": 3840,
+    "cross_attention_dim": 4096,
+    "in_channels": 128,
+    "norm_eps": 1e-06,
+    "num_attention_heads": 32,
+    "num_layers": 48,
+    "out_channels": 128,
+    "audio_num_attention_heads": 32,
+    "audio_attention_head_dim": 64,
+    "audio_out_channels": 128,
+    "audio_cross_attention_dim": 2048,
+    "audio_positional_embedding_max_pos": [
+      20
+    ],
+    "use_embeddings_connector": true,
+    "connector_attention_head_dim": 128,
+    "connector_num_attention_heads": 32,
+    "connector_num_layers": 8,
+    "connector_positional_embedding_max_pos": [
+      4096
+    ],
+    "connector_num_learnable_registers": 128,
+    "use_middle_indices_grid": true,
+    "apply_gated_attention": true,
+    "connector_apply_gated_attention": true,
+    "caption_projection_first_linear": false,
+    "caption_projection_second_linear": false,
+    "audio_connector_attention_head_dim": 64,
+    "audio_connector_num_attention_heads": 32,
+    "cross_attention_adaln": true,
+    "text_encoder_norm_type": "per_token_rms",
+    "rope_type": "split",
+    "frequencies_precision": "float64",
+    "positional_embedding_theta": 10000.0,
+    "positional_embedding_max_pos": [
+      20,
+      2048,
+      2048
+    ],
+    "timestep_scale_multiplier": 1000,
+    "av_ca_timestep_scale_multiplier": 1000.0
+  },
+  "vae": {
+    "_class_name": "CausalVideoAutoencoder",
+    "dims": 3,
+    "in_channels": 3,
+    "out_channels": 3,
+    "latent_channels": 128,
+    "patch_size": 4,
+    "norm_layer": "pixel_norm",
+    "spatial_padding_mode": "zeros",
+    "timestep_conditioning": false,
+    "decoder_blocks": [
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_space",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 6
+        }
+      ],
+      [
+        "compress_time",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_all",
+        {
+          "multiplier": 1
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ],
+      [
+        "compress_all",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ]
+    ],
+    "encoder_blocks": [
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_space_res",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 6
+        }
+      ],
+      [
+        "compress_time_res",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_all_res",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ],
+      [
+        "compress_all_res",
+        {
+          "multiplier": 1
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ]
+    ]
+  },
+  "audio_vae": {
+    "model": {
+      "params": {
+        "ddconfig": {
+          "double_z": true,
+          "mel_bins": 64,
+          "z_channels": 8,
+          "resolution": 256,
+          "in_channels": 2,
+          "out_ch": 2,
+          "ch": 128,
+          "ch_mult": [
+            1,
+            2,
+            4
+          ],
+          "num_res_blocks": 2,
+          "dropout": 0.0,
+          "mid_block_add_attention": false,
+          "norm_type": "pixel",
+          "causality_axis": "height"
+        },
+        "sampling_rate": 16000
+      }
+    }
+  },
+  "scheduler": {
+    "_class_name": "RectifiedFlowScheduler",
+    "_diffusers_version": "0.25.1",
+    "num_train_timesteps": 1000,
+    "sampler": "LinearQuadratic"
+  },
+  "vocoder": {
+    "vocoder": {
+      "upsample_initial_channel": 1536,
+      "resblock": "AMP1",
+      "upsample_rates": [
+        5,
+        2,
+        2,
+        2,
+        2,
+        2
+      ],
+      "resblock_kernel_sizes": [
+        3,
+        7,
+        11
+      ],
+      "upsample_kernel_sizes": [
+        11,
+        4,
+        4,
+        4,
+        4,
+        4
+      ],
+      "resblock_dilation_sizes": [
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ]
+      ],
+      "stereo": true,
+      "use_tanh_at_final": false,
+      "activation": "snakebeta",
+      "use_bias_at_final": false
+    },
+    "bwe": {
+      "upsample_initial_channel": 512,
+      "resblock": "AMP1",
+      "upsample_rates": [
+        6,
+        5,
+        2,
+        2,
+        2
+      ],
+      "resblock_kernel_sizes": [
+        3,
+        7,
+        11
+      ],
+      "upsample_kernel_sizes": [
+        12,
+        11,
+        4,
+        4,
+        4
+      ],
+      "resblock_dilation_sizes": [
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ]
+      ],
+      "stereo": true,
+      "use_tanh_at_final": false,
+      "activation": "snakebeta",
+      "use_bias_at_final": false,
+      "apply_final_activation": false,
+      "input_sampling_rate": 16000,
+      "output_sampling_rate": 48000,
+      "hop_length": 80,
+      "n_fft": 512,
+      "win_size": 512,
+      "num_mels": 64
+    }
+  }
+}

q8/quantize_config.json

@@ -0,0 +1,6 @@
+{
+  "quantization": {
+    "bits": 8,
+    "group_size": 64
+  }
+}

q8/split_model.json

@@ -0,0 +1,21 @@
+{
+  "format": "split",
+  "model_version": "2.3.0",
+  "components": [
+    "transformer",
+    "connector",
+    "vae_decoder",
+    "vae_encoder",
+    "audio_vae",
+    "vocoder",
+    "upsampler",
+    "spatial_upscaler_x2_v1_1",
+    "spatial_upscaler_x1_5_v1_0",
+    "temporal_upscaler_x2_v1_0"
+  ],
+  "source": "Lightricks/LTX-2.3",
+  "variant": "distilled",
+  "quantized": true,
+  "quantization_bits": 8,
+  "quantization_group_size": 64
+}

q8/transformer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bf61ac46ade3ab05e502aa1e7da661dfb3dc540ff28cce027e4a3dccd45f60
+size 20614103249

q8/upsampler.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1565b9c57755dbaba28df25d1774f72f156f2bdfe9a367fc42dffbfacecc55f0
+size 995743275

q8/vae_decoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd16e95613cb6c9c58327f0071c43b84a94c892eab8a91d2a0f4c13c223261c8
+size 814348489

q8/vae_encoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d4c4df1effa2bca48c0ed02034ff94d3c1ba14ef8e0fd980c0ab02a8b9f616
+size 637884283

q8/vocoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:605fbb97e03599b1831fca6b9507b51a537d5978416a8c0a1254a6c0bbfd24bd
+size 258304257