kabachuha commited on
Commit
1f77c41
1 Parent(s): 756498b

Upload 3 files

Browse files
configuration.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ { "framework": "pytorch",
2
+ "task": "text-to-video-synthesis",
3
+ "model": {
4
+ "type": "latent-text-to-video-synthesis",
5
+ "model_args": {
6
+ "ckpt_clip": "open_clip_pytorch_model.bin",
7
+ "ckpt_unet": "text2video_pytorch_model.pth",
8
+ "ckpt_autoencoder": "VQGAN_autoencoder.pth",
9
+ "max_frames": 16,
10
+ "tiny_gpu": 1
11
+ },
12
+ "model_cfg": {
13
+ "unet_in_dim": 4,
14
+ "unet_dim": 320,
15
+ "unet_y_dim": 768,
16
+ "unet_context_dim": 1024,
17
+ "unet_out_dim": 4,
18
+ "unet_dim_mult": [1, 2, 4, 4],
19
+ "unet_num_heads": 8,
20
+ "unet_head_dim": 64,
21
+ "unet_res_blocks": 2,
22
+ "unet_attn_scales": [1, 0.5, 0.25],
23
+ "unet_dropout": 0.1,
24
+ "temporal_attention": "True",
25
+ "num_timesteps": 1000,
26
+ "mean_type": "eps",
27
+ "var_type": "fixed_small",
28
+ "loss_type": "mse"
29
+ }
30
+ },
31
+ "pipeline": {
32
+ "type": "latent-text-to-video-synthesis"
33
+ }
34
+ }
35
+
open_clip_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ca512c4d08a1487097ae60253c9800382a4264a8db7d84c7bf5b2bfac07800
3
+ size 1972390821
text2video_pytorch_model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9c35d05d9fa3b205dd3062b9412a5faadd5298893c70b392e97cb9e9ddf6d0
3
+ size 2822880125