Upload 7 files
Browse files
VQGAN_autoencoder.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:930e9865584beae2405d29bc06a05db3bb6a5b34eedd40a7db29b9156ed7d098
|
| 3 |
+
size 2607657443
|
zs2_576w/configuration.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
zs2_576w/open_clip_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7737c257bec4a587785ae6b9bf52cc0c16f041ef776df6bb60928615059a2878
|
| 3 |
+
size 1972448549
|
zs2_576w/text2video_pytorch_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6040b6383685912fa5d3aeb1e84d6efe1d11f4de773c23f3f2a5e97c12ab6b7
|
| 3 |
+
size 2822972283
|
zs2_XL/configuration.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
zs2_XL/open_clip_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b25d2b2605ea43e0447eb84b8b08ba027855569f74391ecc9a3abf283f045441
|
| 3 |
+
size 1972448549
|
zs2_XL/text2video_pytorch_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18dd886130ca1d7228900ac703e88f96f358f040cd56f5392f1d8d7b174ec750
|
| 3 |
+
size 2822972283
|