init

.gitattributes

@@ -33,3 +33,7 @@ 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
+encoder_2.tensors filter=lfs diff=lfs merge=lfs -text
+encoder.tensors filter=lfs diff=lfs merge=lfs -text
+unet.tensors filter=lfs diff=lfs merge=lfs -text
+vae.tensors filter=lfs diff=lfs merge=lfs -text

encoder-config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/billzhao/.cache/huggingface/hub/models--hotshotco--Hotshot-XL/snapshots/300d6a691ab6d62e74348f2e0d430e6d82ee2864/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "vocab_size": 49408
+}

encoder.tensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f6bf3869c6f27c0ff925bd46a97da3f01550e9937c47d14aa945d4a4a8124a
+size 246407681

encoder_2-config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/billzhao/.cache/huggingface/hub/models--hotshotco--Hotshot-XL/snapshots/300d6a691ab6d62e74348f2e0d430e6d82ee2864/text_encoder_2",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "vocab_size": 49408
+}

encoder_2.tensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e600e8b604a7fbc2a305f24e7d67209720fb8d99f8f68622e5a28b4a7e84efe0
+size 1389645620

unet-config.json

@@ -0,0 +1,70 @@
+{
+  "_class_name": "UNet3DConditionModel",
+  "_diffusers_version": "0.21.4",
+  "_name_or_path": "/home/billzhao/.cache/huggingface/hub/models--hotshotco--Hotshot-XL/snapshots/300d6a691ab6d62e74348f2e0d430e6d82ee2864/unet",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock3D",
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock3DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D",
+    "UpBlock3D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

unet.tensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c680f0fd6b339c3cb659994940ecfc2493ee6e6ccd1a67631ffac2738d73db04
+size 5610108961

vae-config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.21.4",
+  "_name_or_path": "/home/billzhao/.cache/huggingface/hub/models--hotshotco--Hotshot-XL/snapshots/300d6a691ab6d62e74348f2e0d430e6d82ee2864/vae",
+  "act_fn": "silu",
+  "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,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae.tensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a021db66cd5bb53713fc833484749e22e49833c549d8db2c26f6cb81560e317
+size 167598945