Hugging Face's logo

Efficient-Large-Model
/
SANA-Streaming

Diffusers
Safetensors
Model card Files
xet
 Community
Yuyang-z commited on
Commit
534c946
·
verified ·
1 Parent(s): 9a667c0

Add files using upload-large-folder tool

Browse files
Files changed (7) hide show
  1. .gitattributes +3 -0
  2. dit/sana_streaming_ar.pth +3 -0
  3. ltx2_causal_vae_0516/config.json +82 -0
  4. ltx2_causal_vae_0516/diffusion_pytorch_model.safetensors +3 -0
  5. source/00_local_editing_source.mp4 +3 -0
  6. source/05_background_editing_source.mp4 +3 -0
  7. source/09_style_transfer_source.mp4 +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ source/09_style_transfer_source.mp4 filter=lfs diff=lfs merge=lfs -text
37
+ source/05_background_editing_source.mp4 filter=lfs diff=lfs merge=lfs -text
38
+ source/00_local_editing_source.mp4 filter=lfs diff=lfs merge=lfs -text
dit/sana_streaming_ar.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971839a07e5647875e0d7c79aefbc30d05751f33e62537a24ebff2be5f8fc5fa
3
+ size 4520642011
ltx2_causal_vae_0516/config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLCausalLTX2Video",
3
+ "_diffusers_version": "0.38.0.dev0",
4
+ "block_out_channels": [
5
+ 256,
6
+ 512,
7
+ 1024,
8
+ 2048
9
+ ],
10
+ "decoder_block_out_channels": [
11
+ 256,
12
+ 512,
13
+ 1024
14
+ ],
15
+ "decoder_causal": true,
16
+ "decoder_inject_noise": [
17
+ false,
18
+ false,
19
+ false,
20
+ false
21
+ ],
22
+ "decoder_layers_per_block": [
23
+ 5,
24
+ 5,
25
+ 5,
26
+ 5
27
+ ],
28
+ "decoder_spatial_padding_mode": "reflect",
29
+ "decoder_spatio_temporal_scaling": [
30
+ true,
31
+ true,
32
+ true
33
+ ],
34
+ "decoder_upsample_type": null,
35
+ "down_block_types": [
36
+ "LTX2VideoDownBlock3D",
37
+ "LTX2VideoDownBlock3D",
38
+ "LTX2VideoDownBlock3D",
39
+ "LTX2VideoDownBlock3D"
40
+ ],
41
+ "downsample_type": [
42
+ "spatial",
43
+ "temporal",
44
+ "spatiotemporal",
45
+ "spatiotemporal"
46
+ ],
47
+ "encoder_causal": true,
48
+ "encoder_spatial_padding_mode": "zeros",
49
+ "in_channels": 3,
50
+ "latent_channels": 128,
51
+ "layers_per_block": [
52
+ 4,
53
+ 6,
54
+ 6,
55
+ 2,
56
+ 2
57
+ ],
58
+ "out_channels": 3,
59
+ "patch_size": 4,
60
+ "patch_size_t": 1,
61
+ "resnet_norm_eps": 1e-06,
62
+ "scaling_factor": 1.0,
63
+ "spatial_compression_ratio": 32,
64
+ "spatio_temporal_scaling": [
65
+ true,
66
+ true,
67
+ true,
68
+ true
69
+ ],
70
+ "temporal_compression_ratio": 8,
71
+ "timestep_conditioning": false,
72
+ "upsample_factor": [
73
+ 2,
74
+ 2,
75
+ 2
76
+ ],
77
+ "upsample_residual": [
78
+ true,
79
+ true,
80
+ true
81
+ ]
82
+ }
ltx2_causal_vae_0516/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3694526c1da964fcf1ebccb70edb09895bf9e0a723b3ac48e0b5adf5bf97cc4a
3
+ size 4889942004
source/00_local_editing_source.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d162eaa4ba50c0391bac83bbf4d5a813e32a1c7d49d387b6113dd9bcad96a501
3
+ size 77362502
source/05_background_editing_source.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1accb4e89df91389d74bf31ae1850567c5f6d514c32ca28dbbbc43ee8ca81564
3
+ size 16472896
source/09_style_transfer_source.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34a672a64d8ee9b10b3aea7b38ad7736aca23d87c24d3a4f8dac019a7c9dc08
3
+ size 12262405