Uploading the light-weight files for the model.

.gitattributes

@@ -33,17 +33,3 @@ 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
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_104857600_157286400 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_0_52428800 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_52428800_104857600 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_314572800_367001600 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_209715200_262144000 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_262144000_314572800 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_419430400_471859200 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_367001600_419430400 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_471859200_524288000 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_576716800_629145600 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_629145600_681574400 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_681574400_734003200 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_734003200_774425808 filter=lfs diff=lfs merge=lfs -text
-diffusion_pytorch_model-00006-of-00006.safetensors.chunk_524288000_576716800 filter=lfs diff=lfs merge=lfs -text

svd/feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "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
+  }
+}

svd/image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--diffusers--svd-test/snapshots/b9d5dcd269e2f7bff9f98a4907b8c69b7acd555d/image_encoder",
+  "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": "4.34.0.dev0"
+}

svd/scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.24.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "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
+}

svd/svd_model_index.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "StableVideoDiffusionPipeline",
+  "_diffusers_version": "0.24.0.dev0",
+  "_name_or_path": "diffusers/svd-test",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "unet": [
+    "diffusers",
+    "UNetSpatioTemporalConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLTemporalDecoder"
+  ]
+}

svd/unet/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "UNetSpatioTemporalConditionModel",
+  "_diffusers_version": "0.24.0.dev0",
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--diffusers--svd-test/snapshots/b9d5dcd269e2f7bff9f98a4907b8c69b7acd555d/unet",
+  "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": 14,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 768,
+  "sample_size": 96,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal"
+  ]
+}

svd/vae/config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "AutoencoderKLTemporalDecoder",
+  "_diffusers_version": "0.24.0.dev0",
+  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--diffusers--svd-test/snapshots/b9d5dcd269e2f7bff9f98a4907b8c69b7acd555d/vae",
+  "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
+}