Upload folder using huggingface_hub

model_index.json

@@ -44,5 +44,13 @@
   "vqvae": [
     "diffusers",
     "AutoencoderKL"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "vocoder": [
+    "transformers",
+    "SpeechT5HifiGan"
   ]
 }

vae/config.json

@@ -0,0 +1,35 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.24.0",
+  "_name_or_path": "models/autoencoder-kl",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 1,
+  "latent_channels": 1,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 1,
+  "sample_size": [
+    256,
+    256
+  ],
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e017384ee9c7e521f67fd22f491b8a26c5a45b6da56e2ac56a7bc1ab7bbd68e3
+size 334458580