Hugging Face's logo

JackCrum
/
VideoGen

Diffusers
Safetensors
Model card Files
xet
Community
sugerwh commited on
Commit
26534d6
·
1 Parent(s): c6805d5

Add vA

Browse files
Files changed (8) hide show
  1. vA/checkpoint-6000/transformer/config.json +53 -0
  2. vA/checkpoint-6000/transformer/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  3. vA/checkpoint-6000/transformer/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  4. vA/checkpoint-6000/transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
  5. vA/checkpoint-7500/transformer/config.json +53 -0
  6. vA/checkpoint-7500/transformer/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  7. vA/checkpoint-7500/transformer/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  8. vA/checkpoint-7500/transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
vA/checkpoint-6000/transformer/config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "LFE_depth": 10,
3
+ "LFE_dim_head": 64,
4
+ "LFE_ff_mult": 4,
5
+ "LFE_heads": 12,
6
+ "LFE_id_dim": 1280,
7
+ "LFE_num_heads": 16,
8
+ "LFE_num_id_token": 5,
9
+ "LFE_num_querie": 32,
10
+ "LFE_num_scale": 5,
11
+ "LFE_num_tokens": 32,
12
+ "LFE_output_dim": 2048,
13
+ "LFE_vit_dim": 1024,
14
+ "_class_name": "ConsistentVideoTransformer3DModel",
15
+ "_diffusers_version": "0.33.0.dev0",
16
+ "activation_fn": "gelu-approximate",
17
+ "attention_bias": true,
18
+ "attention_head_dim": 64,
19
+ "calculate_align_loss": "True",
20
+ "cross_attn_dim_head": 128,
21
+ "cross_attn_interval": 2,
22
+ "cross_attn_num_heads": 16,
23
+ "cross_text_interval": 2,
24
+ "dropout": 0.0,
25
+ "flip_sin_to_cos": true,
26
+ "freq_shift": 0,
27
+ "in_channels": 32,
28
+ "is_kps": false,
29
+ "is_textCA": "False",
30
+ "is_train_face": true,
31
+ "is_visionCA": "True",
32
+ "local_face_scale": 1.0,
33
+ "local_text_scale": 0.5,
34
+ "max_text_seq_length": 226,
35
+ "norm_elementwise_affine": true,
36
+ "norm_eps": 1e-05,
37
+ "num_attention_heads": 48,
38
+ "num_layers": 42,
39
+ "out_channels": 16,
40
+ "patch_size": 2,
41
+ "patch_size_t": null,
42
+ "sample_frames": 49,
43
+ "sample_height": 60,
44
+ "sample_width": 90,
45
+ "spatial_interpolation_scale": 1.875,
46
+ "temporal_compression_ratio": 4,
47
+ "temporal_interpolation_scale": 1.0,
48
+ "text_embed_dim": 4096,
49
+ "time_embed_dim": 512,
50
+ "timestep_activation_fn": "silu",
51
+ "use_learned_positional_embeddings": true,
52
+ "use_rotary_positional_embeddings": true
53
+ }
vA/checkpoint-6000/transformer/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbaaca030e4093639d581f1f139b3ea278a50715a2fbec6e80b36d7fa6665c98
3
+ size 9997146608
vA/checkpoint-6000/transformer/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451c8600cc3ba733543ff2dbdc4132bafc3c0fd8a00d3c091433fbc9d7bd9d20
3
+ size 3318463744
vA/checkpoint-6000/transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vA/checkpoint-7500/transformer/config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "LFE_depth": 10,
3
+ "LFE_dim_head": 64,
4
+ "LFE_ff_mult": 4,
5
+ "LFE_heads": 12,
6
+ "LFE_id_dim": 1280,
7
+ "LFE_num_heads": 16,
8
+ "LFE_num_id_token": 5,
9
+ "LFE_num_querie": 32,
10
+ "LFE_num_scale": 5,
11
+ "LFE_num_tokens": 32,
12
+ "LFE_output_dim": 2048,
13
+ "LFE_vit_dim": 1024,
14
+ "_class_name": "ConsistentVideoTransformer3DModel",
15
+ "_diffusers_version": "0.33.0.dev0",
16
+ "activation_fn": "gelu-approximate",
17
+ "attention_bias": true,
18
+ "attention_head_dim": 64,
19
+ "calculate_align_loss": "True",
20
+ "cross_attn_dim_head": 128,
21
+ "cross_attn_interval": 2,
22
+ "cross_attn_num_heads": 16,
23
+ "cross_text_interval": 2,
24
+ "dropout": 0.0,
25
+ "flip_sin_to_cos": true,
26
+ "freq_shift": 0,
27
+ "in_channels": 32,
28
+ "is_kps": false,
29
+ "is_textCA": "False",
30
+ "is_train_face": true,
31
+ "is_visionCA": "True",
32
+ "local_face_scale": 1.0,
33
+ "local_text_scale": 0.5,
34
+ "max_text_seq_length": 226,
35
+ "norm_elementwise_affine": true,
36
+ "norm_eps": 1e-05,
37
+ "num_attention_heads": 48,
38
+ "num_layers": 42,
39
+ "out_channels": 16,
40
+ "patch_size": 2,
41
+ "patch_size_t": null,
42
+ "sample_frames": 49,
43
+ "sample_height": 60,
44
+ "sample_width": 90,
45
+ "spatial_interpolation_scale": 1.875,
46
+ "temporal_compression_ratio": 4,
47
+ "temporal_interpolation_scale": 1.0,
48
+ "text_embed_dim": 4096,
49
+ "time_embed_dim": 512,
50
+ "timestep_activation_fn": "silu",
51
+ "use_learned_positional_embeddings": true,
52
+ "use_rotary_positional_embeddings": true
53
+ }
vA/checkpoint-7500/transformer/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc0f1c95476fc7d7dad2c101fe7e6858dee02e078e61da8a5461ea2e284ebd8
3
+ size 9997146608
vA/checkpoint-7500/transformer/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00439d88562447889e27e09f847aaba0905be31d417b6177b06de8f56ab2bed6
3
+ size 3318463744
vA/checkpoint-7500/transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff