Upload folder using huggingface_hub

hotshot_output/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "HotshotXLPipeline",
+  "_ppdiffusers_version": "0.24.0",
+  "force_zeros_for_empty_prompt": true,
+  "scheduler": [
+    "ppdiffusers",
+    "EulerAncestralDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "ppdiffusers.transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "ppdiffusers.transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "ppdiffusers.transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "ppdiffusers.transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "hotshot_xl",
+    "UNet3DConditionModel"
+  ],
+  "vae": [
+    "ppdiffusers",
+    "AutoencoderKL"
+  ]
+}

hotshot_output/scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "EulerAncestralDiscreteScheduler",
+  "_ppdiffusers_version": "0.24.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

hotshot_output/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "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,
+  "paddle_dtype": "float32",
+  "paddlenlp_version": null,
+  "projection_dim": 768,
+  "return_dict": true,
+  "vocab_size": 49408
+}

hotshot_output/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b781333abf4c85d82bec517cfe11ba3c77a3158d42cab00dbdccea6333339234
+size 492265168

hotshot_output/text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "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,
+  "paddle_dtype": "float32",
+  "paddlenlp_version": null,
+  "projection_dim": 1280,
+  "return_dict": true,
+  "vocab_size": 49408
+}

hotshot_output/text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058b1d6cde79b8c0e731a0fb543c5e6ae4810d9e8ed2b5470092427688d7972d
+size 2778702264

hotshot_output/tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

hotshot_output/tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "max_len": 77, "bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>", "add_prefix_space": false, "added_tokens_decoder": {"49406": {"content": "<|startoftext|>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "49407": {"content": "<|endoftext|>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}}, "clean_up_tokenization_spaces": true, "do_lower_case": true, "model_max_length": 77, "tokenizer_class": "CLIPTokenizer", "special_tokens_map_file": "/tmp/tmpv33_kede/special_tokens_map.json"}

hotshot_output/tokenizer_2/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "!"}

hotshot_output/tokenizer_2/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "max_len": 77, "bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "!", "add_prefix_space": false, "added_tokens_decoder": {"0": {"content": "!", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "49406": {"content": "<|startoftext|>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "49407": {"content": "<|endoftext|>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}}, "clean_up_tokenization_spaces": true, "do_lower_case": true, "model_max_length": 77, "tokenizer_class": "CLIPTokenizer", "special_tokens_map_file": "/tmp/tmpv33_kede/token2/special_tokens_map.json"}

hotshot_output/unet/config.json

@@ -0,0 +1,70 @@
+{
+  "_class_name": "UNet3DConditionModel",
+  "_name_or_path": "/nfs/model/Hotshot-XL/unet",
+  "_ppdiffusers_version": "0.24.0",
+  "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
+}

hotshot_output/unet/diffusion_paddle_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097d4d2a1cf22f1aaa478763bbfe3440b061861a1223d0c9862f2bc218fade88
+size 9997069984

hotshot_output/unet/diffusion_paddle_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2596df4e32e1f1b712ce7b2b9629aa20de686e0ff2c1e77a6f7470e28d6fdeb
+size 1222336504

hotshot_output/vae/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_name_or_path": "/nfs/model/Hotshot-XL/vae",
+  "_ppdiffusers_version": "0.24.0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_out_channels": null,
+  "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_out_channels": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

hotshot_output/vae/diffusion_paddle_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772936a510e6701d5f7cadc81b391debd9a9563bce6ec09a14df843bd19abacc
+size 334643268