valhalla commited on
Commit
6613776
1 Parent(s): 7779490

add diffusers weights

Browse files
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--diffusers--svd-xt/snapshots/9703ded20c957c340781ee710b75660826deb487/image_encoder",
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": "4.34.0.dev0"
23
+ }
image_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae616c24393dd1854372b0639e5541666f7521cbe219669255e865cb7f89466a
3
+ size 1264217240
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1e5af7b4042ca30ec29999a4a5cfcac90b7fb610fd05ace834f2dcbb763eab
3
+ size 2528371296
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableVideoDiffusionPipeline",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "diffusers/svd-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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerDiscreteScheduler",
3
+ "_diffusers_version": "0.24.0.dev0",
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
+ "set_alpha_to_one": false,
12
+ "sigma_max": 700.0,
13
+ "sigma_min": 0.002,
14
+ "skip_prk_steps": true,
15
+ "steps_offset": 1,
16
+ "timestep_spacing": "leading",
17
+ "timestep_type": "continuous",
18
+ "trained_betas": null,
19
+ "use_karras_sigmas": true
20
+ }
unet/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--diffusers--svd-xt/snapshots/9703ded20c957c340781ee710b75660826deb487/unet",
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.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbc02e90f37d422f5e3a4aeaee95f6629dc8c45ca211b951626e930daf2bddf
3
+ size 3049435868
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7783d82729af04f26ded4641a5952617fe331fc46add332fb9e47674fecc6ad7
3
+ size 6098682464
vae/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLTemporalDecoder",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--diffusers--svd-xt/snapshots/9703ded20c957c340781ee710b75660826deb487/vae",
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.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af602cd0eb4ad6086ec94fbf1438dfb1be5ec9ac03fd0215640854e90d6463a3
3
+ size 195531910
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d92aa595a53d9da9faf594f09910ee869d5d567c8bb0362d5095673c69997d6
3
+ size 391017740