jhj0517 commited on
Commit ·
6a85668
1
Parent(s): b3a815f
fix config files
Browse files
image_encoder/config.json
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/jpinkney/.cache/huggingface/diffusers/models--lambdalabs--sd-image-variations-diffusers/snapshots/ca6f97f838ae1b5bf764f31363a21f388f4d8f3e/image_encoder",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPVisionModelWithProjection"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"hidden_act": "quick_gelu",
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"image_size": 224,
|
| 11 |
+
"initializer_factor": 1.0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"model_type": "clip_vision_model",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_channels": 3,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"patch_size": 14,
|
| 20 |
+
"projection_dim": 768,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.25.1"
|
| 23 |
+
}
|
sd-image-variations-diffusers/unet/config.json
CHANGED
|
@@ -1,3 +1,40 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.9.0",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"attention_head_dim": 8,
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
320,
|
| 8 |
+
640,
|
| 9 |
+
1280,
|
| 10 |
+
1280
|
| 11 |
+
],
|
| 12 |
+
"center_input_sample": false,
|
| 13 |
+
"cross_attention_dim": 768,
|
| 14 |
+
"down_block_types": [
|
| 15 |
+
"CrossAttnDownBlock2D",
|
| 16 |
+
"CrossAttnDownBlock2D",
|
| 17 |
+
"CrossAttnDownBlock2D",
|
| 18 |
+
"DownBlock2D"
|
| 19 |
+
],
|
| 20 |
+
"downsample_padding": 1,
|
| 21 |
+
"dual_cross_attention": false,
|
| 22 |
+
"flip_sin_to_cos": true,
|
| 23 |
+
"freq_shift": 0,
|
| 24 |
+
"in_channels": 4,
|
| 25 |
+
"layers_per_block": 2,
|
| 26 |
+
"mid_block_scale_factor": 1,
|
| 27 |
+
"norm_eps": 1e-05,
|
| 28 |
+
"norm_num_groups": 32,
|
| 29 |
+
"num_class_embeds": null,
|
| 30 |
+
"only_cross_attention": false,
|
| 31 |
+
"out_channels": 4,
|
| 32 |
+
"sample_size": 64,
|
| 33 |
+
"up_block_types": [
|
| 34 |
+
"UpBlock2D",
|
| 35 |
+
"CrossAttnUpBlock2D",
|
| 36 |
+
"CrossAttnUpBlock2D",
|
| 37 |
+
"CrossAttnUpBlock2D"
|
| 38 |
+
],
|
| 39 |
+
"use_linear_projection": false
|
| 40 |
+
}
|
sd-vae-ft-mse/config.json
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.4.2",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
128,
|
| 7 |
+
256,
|
| 8 |
+
512,
|
| 9 |
+
512
|
| 10 |
+
],
|
| 11 |
+
"down_block_types": [
|
| 12 |
+
"DownEncoderBlock2D",
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D"
|
| 16 |
+
],
|
| 17 |
+
"in_channels": 3,
|
| 18 |
+
"latent_channels": 4,
|
| 19 |
+
"layers_per_block": 2,
|
| 20 |
+
"norm_num_groups": 32,
|
| 21 |
+
"out_channels": 3,
|
| 22 |
+
"sample_size": 256,
|
| 23 |
+
"up_block_types": [
|
| 24 |
+
"UpDecoderBlock2D",
|
| 25 |
+
"UpDecoderBlock2D",
|
| 26 |
+
"UpDecoderBlock2D",
|
| 27 |
+
"UpDecoderBlock2D"
|
| 28 |
+
]
|
| 29 |
+
}
|