Upload 6 files

Spectro-v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63111264103e4bb8e7f5f7a653e9417d83c84759a48a945f9fabf7f7ea0d9984
+size 9370440316

scheduler/scheduler_config.json

@@ -0,0 +1,10 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.25.1",
+  "num_train_timesteps": 1000,
+  "shifting": "SD3",
+  "base_resolution": null,
+  "target_shift_terminal": 0.1,
+  "scheduler_name": "Spectro-Scheduler",
+  "created_by": "SVECTOR"
+}

unet/Spectro-unet-v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3faca364772f7af538d0e41b3b475d99ed529406668aa3b7d4930bae302951e
+size 7693623048

unet/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "Transformer3DModel",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "Spectro/XL-2-256x256",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "attention_type": "default",
+  "caption_channels": 4096,
+  "cross_attention_dim": 2048,
+  "double_self_attention": false,
+  "dropout": 0.0,
+  "in_channels": 128,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "norm_num_groups": 32,
+  "num_attention_heads": 32,
+  "num_embeds_ada_norm": 1000,
+  "num_layers": 28,
+  "num_vector_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 128,
+  "project_to_2d_pos": true,
+  "upcast_attention": false,
+  "use_linear_projection": false,
+  "qk_norm": "rms_norm",
+  "standardization_norm": "rms_norm",
+  "positional_embedding_type": "rope",
+  "positional_embedding_theta": 10000.0,
+  "positional_embedding_max_pos": [
+    20,
+    2048,
+    2048
+  ],
+  "timestep_scale_multiplier": 1000,
+  "model_name": "Spectro-UNet",
+  "created_by": "SVECTOR"
+}

vae/Spectro-vae-v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a7a7e59e14c69d24e7c0e79b5c35f9d83497916c006e06e3f5f484eea676ba
+size 1676800476

vae/config.json

@@ -0,0 +1,57 @@
+{
+  "_class_name": "CausalVideoAutoencoder",
+  "dims": 3,
+  "in_channels": 3,
+  "out_channels": 3,
+  "latent_channels": 128,
+  "blocks": [
+    [
+      "res_x",
+      4
+    ],
+    [
+      "compress_all",
+      1
+    ],
+    [
+      "res_x_y",
+      1
+    ],
+    [
+      "res_x",
+      3
+    ],
+    [
+      "compress_all",
+      1
+    ],
+    [
+      "res_x_y",
+      1
+    ],
+    [
+      "res_x",
+      3
+    ],
+    [
+      "compress_all",
+      1
+    ],
+    [
+      "res_x",
+      3
+    ],
+    [
+      "res_x",
+      4
+    ]
+  ],
+  "scaling_factor": 1.0,
+  "norm_layer": "pixel_norm",
+  "patch_size": 4,
+  "latent_log_var": "uniform",
+  "use_quant_conv": false,
+  "causal_decoder": false,
+  "model_name": "Spectro-VAE",
+  "created_by": "SVECTOR"
+}