Commit ·
21c19c5
1
Parent(s): 025b533
Epoch 0
Browse files
logs/train_unet/events.out.tfevents.1693332835.fccf3d03d68e.78669.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df9a29ac70289db9dc1dc62a230ac097ebd47902a83fca5558d9c204fd9a7304
|
| 3 |
+
size 43155
|
model_index.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"UNet2DModel"
|
| 15 |
],
|
| 16 |
"vqvae": [
|
| 17 |
-
|
| 18 |
-
|
| 19 |
]
|
| 20 |
}
|
|
|
|
| 14 |
"UNet2DModel"
|
| 15 |
],
|
| 16 |
"vqvae": [
|
| 17 |
+
"diffusers",
|
| 18 |
+
"AutoencoderKL"
|
| 19 |
]
|
| 20 |
}
|
unet/config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DModel",
|
| 3 |
"_diffusers_version": "0.20.1",
|
| 4 |
-
"_name_or_path": "/root/.cache/huggingface/hub/models--sebascorreia--imagenet_encoding_audiodiffusion/snapshots/076c3f502b0a18694e30e72d9b5714b4980d62a5/unet",
|
| 5 |
"act_fn": "silu",
|
| 6 |
"add_attention": true,
|
| 7 |
"attention_head_dim": 8,
|
|
@@ -36,8 +35,8 @@
|
|
| 36 |
"out_channels": 1,
|
| 37 |
"resnet_time_scale_shift": "default",
|
| 38 |
"sample_size": [
|
| 39 |
-
|
| 40 |
-
|
| 41 |
],
|
| 42 |
"time_embedding_type": "positional",
|
| 43 |
"up_block_types": [
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DModel",
|
| 3 |
"_diffusers_version": "0.20.1",
|
|
|
|
| 4 |
"act_fn": "silu",
|
| 5 |
"add_attention": true,
|
| 6 |
"attention_head_dim": 8,
|
|
|
|
| 35 |
"out_channels": 1,
|
| 36 |
"resnet_time_scale_shift": "default",
|
| 37 |
"sample_size": [
|
| 38 |
+
32,
|
| 39 |
+
32
|
| 40 |
],
|
| 41 |
"time_embedding_type": "positional",
|
| 42 |
"up_block_types": [
|
unet/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 454722660
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa35f66dd6ddeff28fd12d3a6a71fb62b1aa58f83a0db979cbc0e4c2efecfd01
|
| 3 |
size 454722660
|
vqvae/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.20.1",
|
| 4 |
+
"_name_or_path": "/content/drive/MyDrive/models/autoencoder-kl",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
128,
|
| 8 |
+
256,
|
| 9 |
+
512,
|
| 10 |
+
512
|
| 11 |
+
],
|
| 12 |
+
"down_block_types": [
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D",
|
| 16 |
+
"DownEncoderBlock2D"
|
| 17 |
+
],
|
| 18 |
+
"force_upcast": true,
|
| 19 |
+
"in_channels": 1,
|
| 20 |
+
"latent_channels": 1,
|
| 21 |
+
"layers_per_block": 2,
|
| 22 |
+
"norm_num_groups": 32,
|
| 23 |
+
"out_channels": 1,
|
| 24 |
+
"sample_size": [
|
| 25 |
+
256,
|
| 26 |
+
256
|
| 27 |
+
],
|
| 28 |
+
"scaling_factor": 0.18215,
|
| 29 |
+
"up_block_types": [
|
| 30 |
+
"UpDecoderBlock2D",
|
| 31 |
+
"UpDecoderBlock2D",
|
| 32 |
+
"UpDecoderBlock2D",
|
| 33 |
+
"UpDecoderBlock2D"
|
| 34 |
+
]
|
| 35 |
+
}
|
vqvae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f91c2cb65761ddb494b82b7f6d8dbdf7bf119dbcaf62d1cde798ed83fd8283f
|
| 3 |
+
size 334458580
|