add dummy

README.md

@@ -1,3 +1,7 @@
 ---
 license: mit
 ---
+
+This is random dummy model for stable video diffusion inspired by the [test script](https://github.com/huggingface/diffusers/blob/main/tests/pipelines/stable_video_diffusion/test_stable_video_diffusion.py) in the diffusers library (script for creating the repo [here](https://github.com/JingyaHuang/neuron-playground/blob/main/stable_diffusion/utils/dummy_sd_video.py)).
+
+This model aims for internal testing, please do not use it in other scenarios.

feature_extractor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 32,
+    "width": 32
+  },
+  "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": 32
+  }
+}

image_encoder/config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 32,
+  "image_size": 32,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_hidden_layers": 5,
+  "patch_size": 1,
+  "projection_dim": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2"
+}

image_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3d19058d12326e930c1086726f37574aa0918081c2fabac94ec922c7dd7765
+size 300409

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "StableVideoDiffusionPipeline",
+  "_diffusers_version": "0.25.0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "unet": [
+    "diffusers",
+    "UNetSpatioTemporalConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLTemporalDecoder"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.25.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": false,
+  "sigma_max": 700.0,
+  "sigma_min": 0.002,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "timestep_type": "continuous",
+  "trained_betas": null,
+  "use_karras_sigmas": true
+}

unet/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "UNetSpatioTemporalConditionModel",
+  "_diffusers_version": "0.25.0",
+  "addition_time_embed_dim": 32,
+  "block_out_channels": [
+    32,
+    64
+  ],
+  "cross_attention_dim": 32,
+  "down_block_types": [
+    "CrossAttnDownBlockSpatioTemporal",
+    "DownBlockSpatioTemporal"
+  ],
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "num_attention_heads": 8,
+  "num_frames": 25,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 96,
+  "sample_size": 32,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlockSpatioTemporal",
+    "CrossAttnUpBlockSpatioTemporal"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b398b486e8695b43daed929a046ee76736b7070f728c7dffe10bd6a5f0fbef4
+size 7439581

vae/config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "AutoencoderKLTemporalDecoder",
+  "_diffusers_version": "0.25.0",
+  "block_out_channels": [
+    32,
+    64
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 1,
+  "out_channels": 3,
+  "sample_size": 32,
+  "scaling_factor": 0.18215
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a798b775cbc6dcd80ebf1a4c320c81bd403523679dbde26a26c7adcd25a03d56
+size 2752239