monkseal555 commited on Oct 21, 2024

Commit

75a401d

verified ·

1 Parent(s): 435ab1b

Upload folder using huggingface_hub

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

.gitattributes +8 -0
000000.mp4 +0 -0
000001.mp4 +3 -0
000002.mp4 +0 -0
000003.mp4 +3 -0
000004.mp4 +3 -0
000005.mp4 +3 -0
000006.mp4 +3 -0
000007.mp4 +0 -0
000008.mp4 +3 -0
000009.mp4 +3 -0
000010.mp4 +3 -0
000011.mp4 +0 -0
checkpoint-20000/optimizer.bin +3 -0
checkpoint-20000/random_states_0.pkl +3 -0
checkpoint-20000/scaler.pt +3 -0
checkpoint-20000/scheduler.bin +3 -0
checkpoint-20000/unet/config.json +38 -0
checkpoint-20000/unet/diffusion_pytorch_model.safetensors +3 -0
feature_extractor/preprocessor_config.json +27 -0
image_encoder/config.json +23 -0
image_encoder/model.safetensors +3 -0
model_index.json +25 -0
scheduler/scheduler_config.json +22 -0
unet/config.json +38 -0
unet/diffusion_pytorch_model.safetensors +3 -0
vae/config.json +24 -0
vae/diffusion_pytorch_model.safetensors +3 -0
validation_images/step_10000_val_img_0.gif +0 -0
validation_images/step_1000_val_img_0.gif +0 -0
validation_images/step_10200_val_img_0.gif +0 -0
validation_images/step_10400_val_img_0.gif +0 -0
validation_images/step_10600_val_img_0.gif +0 -0
validation_images/step_10800_val_img_0.gif +0 -0
validation_images/step_11000_val_img_0.gif +0 -0
validation_images/step_11200_val_img_0.gif +0 -0
validation_images/step_11400_val_img_0.gif +0 -0
validation_images/step_11600_val_img_0.gif +0 -0
validation_images/step_11800_val_img_0.gif +0 -0
validation_images/step_12000_val_img_0.gif +0 -0
validation_images/step_1200_val_img_0.gif +0 -0
validation_images/step_12200_val_img_0.gif +0 -0
validation_images/step_12400_val_img_0.gif +0 -0
validation_images/step_12600_val_img_0.gif +0 -0
validation_images/step_12800_val_img_0.gif +0 -0
validation_images/step_13000_val_img_0.gif +0 -0
validation_images/step_13200_val_img_0.gif +0 -0
validation_images/step_13400_val_img_0.gif +0 -0
validation_images/step_13600_val_img_0.gif +0 -0
validation_images/step_13800_val_img_0.gif +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+000001.mp4 filter=lfs diff=lfs merge=lfs -text
+000003.mp4 filter=lfs diff=lfs merge=lfs -text
+000004.mp4 filter=lfs diff=lfs merge=lfs -text
+000005.mp4 filter=lfs diff=lfs merge=lfs -text
+000006.mp4 filter=lfs diff=lfs merge=lfs -text
+000008.mp4 filter=lfs diff=lfs merge=lfs -text
+000009.mp4 filter=lfs diff=lfs merge=lfs -text
+000010.mp4 filter=lfs diff=lfs merge=lfs -text

000000.mp4 ADDED Viewed

Binary file (392 kB). View file

000001.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c425899fb28370e6008f400fdd1d9628cdad21bbe46e8f3df07ee3a5d91b6ef0
+size 1337518

000002.mp4 ADDED Viewed

Binary file (410 kB). View file

000003.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a80e0830bccdd3827499fd61db2fac4eca233bbeaa364c0224cfb82715ccd0
+size 1444170

000004.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e38068594d37127a274b2530046b479ad3a64dcbed68672bae2abc6407e225cd
+size 1322986

000005.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4c573dae93a526febeaee94c0fe08a330b1ceac90b35833829def60c1c0d6a86
+size 2074176

000006.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd43fb464f6f1a80b6880ed4bc31c479a71808fe707f6f86d92fce1dc8c4a49
+size 1355723

000007.mp4 ADDED Viewed

Binary file (396 kB). View file

000008.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:de790df62ef8ddcd9d3d974351b2517c42bd8d382dd47d91a681d0f9befe1042
+size 2024838

000009.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b295e8a0cda2a9bd1c129f0e950fc2dd85711c2fad3b6d28d89f9ea7d9fa246
+size 2039656

000010.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:be76e43d026360dcb2e44288b63d3bae6e623fcd9c247d842314a02f08e767ef
+size 1904477

000011.mp4 ADDED Viewed

Binary file (398 kB). View file

checkpoint-20000/optimizer.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ac858e4d135f528ee3e97dccd4882cf827227d7e513adc65f98e385da6498a
+size 3181312562

checkpoint-20000/random_states_0.pkl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d2204cc8e5a9da2c24a82725381bafc9abc0c5192c64af0cbe2a1f233cb46985
+size 14408

checkpoint-20000/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:893774e51900ebe97139f903f25d8cc0f8e647db85e0307e6b985125b36f7c40
+size 988

checkpoint-20000/scheduler.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:549310c01962ae96454965533cc12e0b805420e3ab1ece6b047afb074fe891bf
+size 1000

checkpoint-20000/unet/config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "_class_name": "UNetSpatioTemporalConditionModel",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
+  "addition_time_embed_dim": 256,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlockSpatioTemporal",
+    "CrossAttnDownBlockSpatioTemporal",
+    "CrossAttnDownBlockSpatioTemporal",
+    "DownBlockSpatioTemporal"
+  ],
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "num_attention_heads": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "num_frames": 25,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 768,
+  "sample_size": 96,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal"
+  ]
+}

checkpoint-20000/unet/diffusion_pytorch_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ff76181b0341451d58979df1b4628d3766e56a4ff5d0dd424b63c9b140e30cea
+size 6098682464

feature_extractor/preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,27 @@

+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

image_encoder/config.json ADDED Viewed

	@@ -0,0 +1,23 @@

+{
+  "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.2"
+}

image_encoder/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ae616c24393dd1854372b0639e5541666f7521cbe219669255e865cb7f89466a
+size 1264217240

model_index.json ADDED Viewed

	@@ -0,0 +1,25 @@

+{
+  "_class_name": "StableVideoDiffusionPipeline",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "unet": [
+    "diffusers",
+    "UNetSpatioTemporalConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLTemporalDecoder"
+  ]
+}

scheduler/scheduler_config.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.30.3",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "final_sigmas_type": "zero",
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": false,
+  "set_alpha_to_one": false,
+  "sigma_max": 700.0,
+  "sigma_min": 0.002,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "timestep_type": "continuous",
+  "trained_betas": null,
+  "use_karras_sigmas": true
+}

unet/config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "_class_name": "UNetSpatioTemporalConditionModel",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
+  "addition_time_embed_dim": 256,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlockSpatioTemporal",
+    "CrossAttnDownBlockSpatioTemporal",
+    "CrossAttnDownBlockSpatioTemporal",
+    "DownBlockSpatioTemporal"
+  ],
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "num_attention_heads": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "num_frames": 25,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 768,
+  "sample_size": 96,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal"
+  ]
+}

unet/diffusion_pytorch_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ff76181b0341451d58979df1b4628d3766e56a4ff5d0dd424b63c9b140e30cea
+size 6098682464

vae/config.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "_class_name": "AutoencoderKLTemporalDecoder",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "out_channels": 3,
+  "sample_size": 768,
+  "scaling_factor": 0.18215
+}