Hugging Face's logo

monkseal555
/
CIRA

Diffusers
Safetensors
StableVideoDiffusionPipeline
Model card Files Community
monkseal555 commited on
Commit
9ffafaa
•
1 Parent(s): 9137b0a

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. checkpoint-5000/optimizer.bin +3 -0
  2. checkpoint-5000/random_states_0.pkl +3 -0
  3. checkpoint-5000/scaler.pt +3 -0
  4. checkpoint-5000/scheduler.bin +3 -0
  5. checkpoint-5000/unet/config.json +38 -0
  6. checkpoint-5000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. feature_extractor/preprocessor_config.json +44 -0
  8. image_encoder/config.json +23 -0
  9. image_encoder/model.safetensors +3 -0
  10. model_index.json +25 -0
  11. scheduler/scheduler_config.json +21 -0
  12. unet/config.json +38 -0
  13. unet/diffusion_pytorch_model.safetensors +3 -0
  14. vae/config.json +24 -0
  15. vae/diffusion_pytorch_model.safetensors +3 -0
  16. validation_images/step_1000_val_img_0.gif +0 -0
  17. validation_images/step_1200_val_img_0.gif +0 -0
  18. validation_images/step_1400_val_img_0.gif +0 -0
  19. validation_images/step_1600_val_img_0.gif +0 -0
  20. validation_images/step_1800_val_img_0.gif +0 -0
  21. validation_images/step_1_val_img_0.gif +0 -0
  22. validation_images/step_2000_val_img_0.gif +0 -0
  23. validation_images/step_200_val_img_0.gif +0 -0
  24. validation_images/step_2200_val_img_0.gif +0 -0
  25. validation_images/step_2400_val_img_0.gif +0 -0
  26. validation_images/step_2600_val_img_0.gif +0 -0
  27. validation_images/step_2800_val_img_0.gif +0 -0
  28. validation_images/step_3000_val_img_0.gif +0 -0
  29. validation_images/step_3200_val_img_0.gif +0 -0
  30. validation_images/step_3400_val_img_0.gif +0 -0
  31. validation_images/step_3600_val_img_0.gif +0 -0
  32. validation_images/step_3800_val_img_0.gif +0 -0
  33. validation_images/step_4000_val_img_0.gif +0 -0
  34. validation_images/step_400_val_img_0.gif +0 -0
  35. validation_images/step_4200_val_img_0.gif +0 -0
  36. validation_images/step_4400_val_img_0.gif +0 -0
  37. validation_images/step_4600_val_img_0.gif +0 -0
  38. validation_images/step_4800_val_img_0.gif +0 -0
  39. validation_images/step_5000_val_img_0.gif +0 -0
  40. validation_images/step_600_val_img_0.gif +0 -0
  41. validation_images/step_800_val_img_0.gif +0 -0
checkpoint-5000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bd1fdccb41683ae3bb6d8f863c63c5de071ad841d0f2fe6428e054e7edfc3e
3
+ size 3181312125
checkpoint-5000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bf7360141988143757742249fc6b35ebf2cdfeadffca84be86fe9541ebd93e
3
+ size 14727
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:164e4d44ec2f4851507c9a2060d3eb22864f4fa17a9c45ba1630f30ae8afe303
3
+ size 557
checkpoint-5000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992358ea03e461cc1b3a3914f7afd1fa6d34c6ef24790faf89d18f241a7a2981
3
+ size 563
checkpoint-5000/unet/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModel",
3
+ "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
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": 25,
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
+ }
checkpoint-5000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c7639bfe54ad374385c330eb48f9c7fe9bc63919c09ee2f49f3c41e38ec440
3
+ size 6098682464
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_center_crop",
8
+ "crop_size",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_convert_rgb",
15
+ "return_tensors",
16
+ "data_format",
17
+ "input_data_format"
18
+ ],
19
+ "crop_size": {
20
+ "height": 224,
21
+ "width": 224
22
+ },
23
+ "do_center_crop": true,
24
+ "do_convert_rgb": true,
25
+ "do_normalize": true,
26
+ "do_rescale": true,
27
+ "do_resize": true,
28
+ "image_mean": [
29
+ 0.48145466,
30
+ 0.4578275,
31
+ 0.40821073
32
+ ],
33
+ "image_processor_type": "CLIPImageProcessor",
34
+ "image_std": [
35
+ 0.26862954,
36
+ 0.26130258,
37
+ 0.27577711
38
+ ],
39
+ "resample": 3,
40
+ "rescale_factor": 0.00392156862745098,
41
+ "size": {
42
+ "shortest_edge": 224
43
+ }
44
+ }
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1280,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 32,
19
+ "patch_size": 14,
20
+ "projection_dim": 1024,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.39.3"
23
+ }
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae616c24393dd1854372b0639e5541666f7521cbe219669255e865cb7f89466a
3
+ size 1264217240
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableVideoDiffusionPipeline",
3
+ "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ "transformers",
11
+ "CLIPVisionModelWithProjection"
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "EulerDiscreteScheduler"
16
+ ],
17
+ "unet": [
18
+ "diffusers",
19
+ "UNetSpatioTemporalConditionModel"
20
+ ],
21
+ "vae": [
22
+ "diffusers",
23
+ "AutoencoderKLTemporalDecoder"
24
+ ]
25
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerDiscreteScheduler",
3
+ "_diffusers_version": "0.27.2",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "interpolation_type": "linear",
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "v_prediction",
11
+ "rescale_betas_zero_snr": false,
12
+ "set_alpha_to_one": false,
13
+ "sigma_max": 700.0,
14
+ "sigma_min": 0.002,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "timestep_spacing": "leading",
18
+ "timestep_type": "continuous",
19
+ "trained_betas": null,
20
+ "use_karras_sigmas": true
21
+ }
unet/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModel",
3
+ "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
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": 25,
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
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c7639bfe54ad374385c330eb48f9c7fe9bc63919c09ee2f49f3c41e38ec440
3
+ size 6098682464
vae/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLTemporalDecoder",
3
+ "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "DownEncoderBlock2D",
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D"
16
+ ],
17
+ "force_upcast": true,
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "out_channels": 3,
22
+ "sample_size": 768,
23
+ "scaling_factor": 0.18215
24
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af602cd0eb4ad6086ec94fbf1438dfb1be5ec9ac03fd0215640854e90d6463a3
3
+ size 195531910
validation_images/step_1000_val_img_0.gif ADDED
validation_images/step_1200_val_img_0.gif ADDED
validation_images/step_1400_val_img_0.gif ADDED
validation_images/step_1600_val_img_0.gif ADDED
validation_images/step_1800_val_img_0.gif ADDED
validation_images/step_1_val_img_0.gif ADDED
validation_images/step_2000_val_img_0.gif ADDED
validation_images/step_200_val_img_0.gif ADDED
validation_images/step_2200_val_img_0.gif ADDED
validation_images/step_2400_val_img_0.gif ADDED
validation_images/step_2600_val_img_0.gif ADDED
validation_images/step_2800_val_img_0.gif ADDED
validation_images/step_3000_val_img_0.gif ADDED
validation_images/step_3200_val_img_0.gif ADDED
validation_images/step_3400_val_img_0.gif ADDED
validation_images/step_3600_val_img_0.gif ADDED
validation_images/step_3800_val_img_0.gif ADDED
validation_images/step_4000_val_img_0.gif ADDED
validation_images/step_400_val_img_0.gif ADDED
validation_images/step_4200_val_img_0.gif ADDED
validation_images/step_4400_val_img_0.gif ADDED
validation_images/step_4600_val_img_0.gif ADDED
validation_images/step_4800_val_img_0.gif ADDED
validation_images/step_5000_val_img_0.gif ADDED
validation_images/step_600_val_img_0.gif ADDED
validation_images/step_800_val_img_0.gif ADDED