add SD subcomponent config
Browse files- text_encoder/config.json +23 -0
- unet/config.json +30 -0
- vae_decoder/config.json +23 -0
- vae_encoder/config.json +23 -0
text_encoder/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPTextModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "quick_gelu",
|
| 10 |
+
"hidden_size": 32,
|
| 11 |
+
"initializer_factor": 1.0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 37,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 77,
|
| 16 |
+
"model_type": "clip_text_model",
|
| 17 |
+
"num_attention_heads": 4,
|
| 18 |
+
"num_hidden_layers": 5,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.22.2",
|
| 22 |
+
"vocab_size": 1000
|
| 23 |
+
}
|
unet/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.7.0.dev0",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"attention_head_dim": 8,
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
32,
|
| 8 |
+
64
|
| 9 |
+
],
|
| 10 |
+
"center_input_sample": false,
|
| 11 |
+
"cross_attention_dim": 32,
|
| 12 |
+
"down_block_types": [
|
| 13 |
+
"DownBlock2D",
|
| 14 |
+
"CrossAttnDownBlock2D"
|
| 15 |
+
],
|
| 16 |
+
"downsample_padding": 1,
|
| 17 |
+
"flip_sin_to_cos": true,
|
| 18 |
+
"freq_shift": 0,
|
| 19 |
+
"in_channels": 4,
|
| 20 |
+
"layers_per_block": 2,
|
| 21 |
+
"mid_block_scale_factor": 1,
|
| 22 |
+
"norm_eps": 1e-05,
|
| 23 |
+
"norm_num_groups": 32,
|
| 24 |
+
"out_channels": 4,
|
| 25 |
+
"sample_size": 32,
|
| 26 |
+
"up_block_types": [
|
| 27 |
+
"CrossAttnUpBlock2D",
|
| 28 |
+
"UpBlock2D"
|
| 29 |
+
]
|
| 30 |
+
}
|
vae_decoder/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.7.0.dev0",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
32,
|
| 7 |
+
64
|
| 8 |
+
],
|
| 9 |
+
"down_block_types": [
|
| 10 |
+
"DownEncoderBlock2D",
|
| 11 |
+
"DownEncoderBlock2D"
|
| 12 |
+
],
|
| 13 |
+
"in_channels": 3,
|
| 14 |
+
"latent_channels": 4,
|
| 15 |
+
"layers_per_block": 1,
|
| 16 |
+
"norm_num_groups": 32,
|
| 17 |
+
"out_channels": 3,
|
| 18 |
+
"sample_size": 128,
|
| 19 |
+
"up_block_types": [
|
| 20 |
+
"UpDecoderBlock2D",
|
| 21 |
+
"UpDecoderBlock2D"
|
| 22 |
+
]
|
| 23 |
+
}
|
vae_encoder/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.7.0.dev0",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
32,
|
| 7 |
+
64
|
| 8 |
+
],
|
| 9 |
+
"down_block_types": [
|
| 10 |
+
"DownEncoderBlock2D",
|
| 11 |
+
"DownEncoderBlock2D"
|
| 12 |
+
],
|
| 13 |
+
"in_channels": 3,
|
| 14 |
+
"latent_channels": 4,
|
| 15 |
+
"layers_per_block": 1,
|
| 16 |
+
"norm_num_groups": 32,
|
| 17 |
+
"out_channels": 3,
|
| 18 |
+
"sample_size": 128,
|
| 19 |
+
"up_block_types": [
|
| 20 |
+
"UpDecoderBlock2D",
|
| 21 |
+
"UpDecoderBlock2D"
|
| 22 |
+
]
|
| 23 |
+
}
|