initial commit

.gitattributes

@@ -0,0 +1,3 @@
+text_encoder/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+unet/diffusion_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+vae/diffusion_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,5 @@
+This is a text2video model for diffusers, fine-tuned with a [modelscope](https://huggingface.co/damo-vilab/text-to-video-ms-1.7b) to have an anime-style appearance.  
+It was trained at 448x384 resolution.  
+The usage is the same as with the original modelscope model.  
+  
+The main difference from version 0.1 is only the resolution.

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "TextToVideoSDPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet3DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.15.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./models/model_scope_diffusers/",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.3",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c89ba5773b9b5c11b57f676c658047bd2d7c31c207acde13d06d7951101b0b
+size 680904225

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "UNet3DConditionModel",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./models/model_scope_diffusers/",
+  "act_fn": "silu",
+  "attention_head_dim": 64,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "DownBlock3D"
+  ],
+  "downsample_padding": 1,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 32,
+  "up_block_types": [
+    "UpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426c0b7df5e676185cabcc7adf467a46c63bb57029a9e91b98c59af3d032f2b0
+size 2823110385

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./models/model_scope_diffusers/",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb475c1672d6273bafae618c8de499f383476fc692795c9d0abc97c6b87f1058
+size 167407601