Upload unet/config.json with huggingface_hub
Browse files- unet/config.json +41 -0
unet/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet3DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.26.1",
|
| 4 |
+
"_name_or_path": "damo-vilab/text-to-video-ms-1.7b",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"attention_head_dim": 64,
|
| 7 |
+
"block_out_channels": [
|
| 8 |
+
320,
|
| 9 |
+
640,
|
| 10 |
+
1280,
|
| 11 |
+
1280
|
| 12 |
+
],
|
| 13 |
+
"concat": false,
|
| 14 |
+
"cross_attention_dim": 1024,
|
| 15 |
+
"down_block_types": [
|
| 16 |
+
"CrossAttnDownBlock3D",
|
| 17 |
+
"CrossAttnDownBlock3D",
|
| 18 |
+
"CrossAttnDownBlock3D",
|
| 19 |
+
"DownBlock3D"
|
| 20 |
+
],
|
| 21 |
+
"downsample_padding": 1,
|
| 22 |
+
"in_channels": 4,
|
| 23 |
+
"layers_per_block": 2,
|
| 24 |
+
"merging_mode": "attention_cross_attention",
|
| 25 |
+
"mid_block_scale_factor": 1,
|
| 26 |
+
"norm_eps": 1e-05,
|
| 27 |
+
"norm_num_groups": 32,
|
| 28 |
+
"out_channels": 4,
|
| 29 |
+
"sample_size": 32,
|
| 30 |
+
"up_block_types": [
|
| 31 |
+
"UpBlock3D",
|
| 32 |
+
"CrossAttnUpBlock3D",
|
| 33 |
+
"CrossAttnUpBlock3D",
|
| 34 |
+
"CrossAttnUpBlock3D"
|
| 35 |
+
],
|
| 36 |
+
"use_channel_expansion": false,
|
| 37 |
+
"use_fps_conditioning": false,
|
| 38 |
+
"use_image_embedding": true,
|
| 39 |
+
"use_image_tokens": true,
|
| 40 |
+
"use_repeat_context_img": true
|
| 41 |
+
}
|