Hugging Face's logo

pengxiang
/
trackdiffusion_ytvis

Text-to-Video
Diffusers
Safetensors
Model card Files Community
pixeli commited on
Commit
cd3016a
•
1 Parent(s): c06aa21

First model version

Browse files
Files changed (4) hide show
  1. svd_stage1/unet/config.json +38 -0
  2. svd_stage1/unet/diffusion_pytorch_model.safetensors +3 -0
  3. svd_stage2/unet/config.json +38 -0
  4. svd_stage2/unet/diffusion_pytorch_model.safetensors +3 -0
svd_stage1/unet/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "/18940970966/diffusion_re/NEW_CODE/SVD_Xtend/outputs/checkpoint-191500",
5
+ "addition_time_embed_dim": 256,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "cross_attention_dim": 1024,
13
+ "down_block_types": [
14
+ "CrossAttnDownBlockSpatioTemporal",
15
+ "CrossAttnDownBlockSpatioTemporal",
16
+ "CrossAttnDownBlockSpatioTemporal",
17
+ "DownBlockSpatioTemporal"
18
+ ],
19
+ "in_channels": 8,
20
+ "layers_per_block": 2,
21
+ "num_attention_heads": [
22
+ 5,
23
+ 10,
24
+ 20,
25
+ 20
26
+ ],
27
+ "num_frames": 14,
28
+ "out_channels": 4,
29
+ "projection_class_embeddings_input_dim": 768,
30
+ "sample_size": 96,
31
+ "transformer_layers_per_block": 1,
32
+ "up_block_types": [
33
+ "UpBlockSpatioTemporal",
34
+ "CrossAttnUpBlockSpatioTemporal",
35
+ "CrossAttnUpBlockSpatioTemporal",
36
+ "CrossAttnUpBlockSpatioTemporal"
37
+ ]
38
+ }
svd_stage1/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:326069fe2a0866608fbebd07b5e036acd536b0aaf6b7bd66e089e316c84621fe
3
+ size 6946957672
svd_stage2/unet/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "/18940970966/diffusion_re/NEW_CODE/SVD_Xtend/outputs/checkpoint-87000",
5
+ "addition_time_embed_dim": 256,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "cross_attention_dim": 1024,
13
+ "down_block_types": [
14
+ "CrossAttnDownBlockSpatioTemporal",
15
+ "CrossAttnDownBlockSpatioTemporal",
16
+ "CrossAttnDownBlockSpatioTemporal",
17
+ "DownBlockSpatioTemporal"
18
+ ],
19
+ "in_channels": 8,
20
+ "layers_per_block": 2,
21
+ "num_attention_heads": [
22
+ 5,
23
+ 10,
24
+ 20,
25
+ 20
26
+ ],
27
+ "num_frames": 14,
28
+ "out_channels": 4,
29
+ "projection_class_embeddings_input_dim": 768,
30
+ "sample_size": 96,
31
+ "transformer_layers_per_block": 1,
32
+ "up_block_types": [
33
+ "UpBlockSpatioTemporal",
34
+ "CrossAttnUpBlockSpatioTemporal",
35
+ "CrossAttnUpBlockSpatioTemporal",
36
+ "CrossAttnUpBlockSpatioTemporal"
37
+ ]
38
+ }
svd_stage2/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2ce53b521b01403fdb78b7d9d8b8b5b659827b1bf9ac5a39dcd482bdc767ec
3
+ size 6946957672