strangeman3107 commited on
Commit
11f4d90
0 Parent(s):

initial commit

Browse files
.gitattributes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ text_encoder/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
2
+ unet/diffusion_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
3
+ vae/diffusion_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ 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.
2
+ It was trained at 448x384 resolution.
3
+ The usage is the same as with the original modelscope model.
4
+
5
+ The main difference from version 0.1 is only the resolution.
model_index.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "TextToVideoSDPipeline",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "scheduler": [
5
+ "diffusers",
6
+ "DDIMScheduler"
7
+ ],
8
+ "text_encoder": [
9
+ "transformers",
10
+ "CLIPTextModel"
11
+ ],
12
+ "tokenizer": [
13
+ "transformers",
14
+ "CLIPTokenizer"
15
+ ],
16
+ "unet": [
17
+ "diffusers",
18
+ "UNet3DConditionModel"
19
+ ],
20
+ "vae": [
21
+ "diffusers",
22
+ "AutoencoderKL"
23
+ ]
24
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "epsilon",
12
+ "sample_max_value": 1.0,
13
+ "set_alpha_to_one": false,
14
+ "skip_prk_steps": true,
15
+ "steps_offset": 1,
16
+ "thresholding": false,
17
+ "trained_betas": null
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/model_scope_diffusers/",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.27.3",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c89ba5773b9b5c11b57f676c658047bd2d7c31c207acde13d06d7951101b0b
3
+ size 680904225
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "pad_token": "<|endoftext|>",
23
+ "special_tokens_map_file": "./special_tokens_map.json",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet3DConditionModel",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "_name_or_path": "./models/model_scope_diffusers/",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 64,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "cross_attention_dim": 1024,
14
+ "down_block_types": [
15
+ "CrossAttnDownBlock3D",
16
+ "CrossAttnDownBlock3D",
17
+ "CrossAttnDownBlock3D",
18
+ "DownBlock3D"
19
+ ],
20
+ "downsample_padding": 1,
21
+ "in_channels": 4,
22
+ "layers_per_block": 2,
23
+ "mid_block_scale_factor": 1,
24
+ "norm_eps": 1e-05,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 4,
27
+ "sample_size": 32,
28
+ "up_block_types": [
29
+ "UpBlock3D",
30
+ "CrossAttnUpBlock3D",
31
+ "CrossAttnUpBlock3D",
32
+ "CrossAttnUpBlock3D"
33
+ ]
34
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426c0b7df5e676185cabcc7adf467a46c63bb57029a9e91b98c59af3d032f2b0
3
+ size 2823110385
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "_name_or_path": "./models/model_scope_diffusers/",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 512,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb475c1672d6273bafae618c8de499f383476fc692795c9d0abc97c6b87f1058
3
+ size 167407601