Spaces:
Sleeping
Sleeping
Delete pretrained
Browse files- pretrained/Cinemo/model_index.json +0 -32
- pretrained/Cinemo/scheduler/scheduler_config.json +0 -13
- pretrained/Cinemo/text_encoder/config.json +0 -24
- pretrained/Cinemo/text_encoder/pytorch_model.bin +0 -3
- pretrained/Cinemo/tokenizer/merges.txt +0 -0
- pretrained/Cinemo/tokenizer/special_tokens_map.json +0 -24
- pretrained/Cinemo/tokenizer/tokenizer_config.json +0 -34
- pretrained/Cinemo/tokenizer/vocab.json +0 -0
- pretrained/Cinemo/unet/config.json +0 -38
- pretrained/Cinemo/unet/diffusion_pytorch_model.bin +0 -3
- pretrained/Cinemo/vae/config.json +0 -29
- pretrained/Cinemo/vae/diffusion_pytorch_model.bin +0 -3
- pretrained/Cinemo/vae_temporal_decoder/config.json +0 -24
- pretrained/Cinemo/vae_temporal_decoder/diffusion_pytorch_model.safetensors +0 -3
pretrained/Cinemo/model_index.json
DELETED
@@ -1,32 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.2.2",
|
4 |
-
"feature_extractor": [
|
5 |
-
"transformers",
|
6 |
-
"CLIPImageProcessor"
|
7 |
-
],
|
8 |
-
"safety_checker": [
|
9 |
-
"stable_diffusion",
|
10 |
-
"StableDiffusionSafetyChecker"
|
11 |
-
],
|
12 |
-
"scheduler": [
|
13 |
-
"diffusers",
|
14 |
-
"PNDMScheduler"
|
15 |
-
],
|
16 |
-
"text_encoder": [
|
17 |
-
"transformers",
|
18 |
-
"CLIPTextModel"
|
19 |
-
],
|
20 |
-
"tokenizer": [
|
21 |
-
"transformers",
|
22 |
-
"CLIPTokenizer"
|
23 |
-
],
|
24 |
-
"unet": [
|
25 |
-
"diffusers",
|
26 |
-
"UNet2DConditionModel"
|
27 |
-
],
|
28 |
-
"vae": [
|
29 |
-
"diffusers",
|
30 |
-
"AutoencoderKL"
|
31 |
-
]
|
32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/scheduler/scheduler_config.json
DELETED
@@ -1,13 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_class_name": "PNDMScheduler",
|
3 |
-
"_diffusers_version": "0.7.0.dev0",
|
4 |
-
"beta_end": 0.012,
|
5 |
-
"beta_schedule": "scaled_linear",
|
6 |
-
"beta_start": 0.00085,
|
7 |
-
"num_train_timesteps": 1000,
|
8 |
-
"set_alpha_to_one": false,
|
9 |
-
"skip_prk_steps": true,
|
10 |
-
"steps_offset": 1,
|
11 |
-
"trained_betas": null,
|
12 |
-
"clip_sample": false
|
13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/text_encoder/config.json
DELETED
@@ -1,24 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "openai/clip-vit-large-patch14",
|
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": "quick_gelu",
|
11 |
-
"hidden_size": 768,
|
12 |
-
"initializer_factor": 1.0,
|
13 |
-
"initializer_range": 0.02,
|
14 |
-
"intermediate_size": 3072,
|
15 |
-
"layer_norm_eps": 1e-05,
|
16 |
-
"max_position_embeddings": 77,
|
17 |
-
"model_type": "clip_text_model",
|
18 |
-
"num_attention_heads": 12,
|
19 |
-
"num_hidden_layers": 12,
|
20 |
-
"pad_token_id": 1,
|
21 |
-
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.21.0.dev0",
|
23 |
-
"vocab_size": 49408
|
24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/text_encoder/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
|
3 |
-
size 492305335
|
|
|
|
|
|
|
|
pretrained/Cinemo/tokenizer/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
pretrained/Cinemo/tokenizer/special_tokens_map.json
DELETED
@@ -1,24 +0,0 @@
|
|
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": "<|endoftext|>",
|
17 |
-
"unk_token": {
|
18 |
-
"content": "<|endoftext|>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": true,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/tokenizer/tokenizer_config.json
DELETED
@@ -1,34 +0,0 @@
|
|
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 |
-
"name_or_path": "openai/clip-vit-large-patch14",
|
23 |
-
"pad_token": "<|endoftext|>",
|
24 |
-
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
-
"tokenizer_class": "CLIPTokenizer",
|
26 |
-
"unk_token": {
|
27 |
-
"__type": "AddedToken",
|
28 |
-
"content": "<|endoftext|>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": true,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false
|
33 |
-
}
|
34 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/tokenizer/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
pretrained/Cinemo/unet/config.json
DELETED
@@ -1,38 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_class_name": "UNetMidBlock3DCrossAttn",
|
3 |
-
"_diffusers_version": "0.2.2",
|
4 |
-
"act_fn": "silu",
|
5 |
-
"attention_head_dim": 8,
|
6 |
-
"block_out_channels": [
|
7 |
-
320,
|
8 |
-
640,
|
9 |
-
1280,
|
10 |
-
1280
|
11 |
-
],
|
12 |
-
"center_input_sample": false,
|
13 |
-
"cross_attention_dim": 768,
|
14 |
-
"down_block_types": [
|
15 |
-
"CrossAttnDownBlock3D",
|
16 |
-
"CrossAttnDownBlock3D",
|
17 |
-
"CrossAttnDownBlock3D",
|
18 |
-
"DownBlock3D"
|
19 |
-
],
|
20 |
-
"downsample_padding": 1,
|
21 |
-
"flip_sin_to_cos": true,
|
22 |
-
"freq_shift": 0,
|
23 |
-
"in_channels": 4,
|
24 |
-
"layers_per_block": 2,
|
25 |
-
"mid_block_scale_factor": 1,
|
26 |
-
"norm_eps": 1e-05,
|
27 |
-
"norm_num_groups": 32,
|
28 |
-
"out_channels": 4,
|
29 |
-
"sample_size": 64,
|
30 |
-
"up_block_types": [
|
31 |
-
"UpBlock3D",
|
32 |
-
"CrossAttnUpBlock3D",
|
33 |
-
"CrossAttnUpBlock3D",
|
34 |
-
"CrossAttnUpBlock3D"
|
35 |
-
],
|
36 |
-
"addition_embed_type": "motion_ids",
|
37 |
-
"addition_time_embed_dim": 256
|
38 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/unet/diffusion_pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:272cd2f49acd6770a845d2d2f734a8ec2b1d12796f837f47e34b38a2cd5ccb0f
|
3 |
-
size 3644720235
|
|
|
|
|
|
|
|
pretrained/Cinemo/vae/config.json
DELETED
@@ -1,29 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_class_name": "AutoencoderKL",
|
3 |
-
"_diffusers_version": "0.2.2",
|
4 |
-
"act_fn": "silu",
|
5 |
-
"block_out_channels": [
|
6 |
-
128,
|
7 |
-
256,
|
8 |
-
512,
|
9 |
-
512
|
10 |
-
],
|
11 |
-
"down_block_types": [
|
12 |
-
"DownEncoderBlock2D",
|
13 |
-
"DownEncoderBlock2D",
|
14 |
-
"DownEncoderBlock2D",
|
15 |
-
"DownEncoderBlock2D"
|
16 |
-
],
|
17 |
-
"in_channels": 3,
|
18 |
-
"latent_channels": 4,
|
19 |
-
"layers_per_block": 2,
|
20 |
-
"out_channels": 3,
|
21 |
-
"sample_size": 512,
|
22 |
-
"scaling_factor": 0.18215,
|
23 |
-
"up_block_types": [
|
24 |
-
"UpDecoderBlock2D",
|
25 |
-
"UpDecoderBlock2D",
|
26 |
-
"UpDecoderBlock2D",
|
27 |
-
"UpDecoderBlock2D"
|
28 |
-
]
|
29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/vae/diffusion_pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
|
3 |
-
size 334707217
|
|
|
|
|
|
|
|
pretrained/Cinemo/vae_temporal_decoder/config.json
DELETED
@@ -1,24 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_class_name": "AutoencoderKLTemporalDecoder",
|
3 |
-
"_diffusers_version": "0.24.0.dev0",
|
4 |
-
"_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--diffusers--svd-xt/snapshots/9703ded20c957c340781ee710b75660826deb487/vae",
|
5 |
-
"block_out_channels": [
|
6 |
-
128,
|
7 |
-
256,
|
8 |
-
512,
|
9 |
-
512
|
10 |
-
],
|
11 |
-
"down_block_types": [
|
12 |
-
"DownEncoderBlock2D",
|
13 |
-
"DownEncoderBlock2D",
|
14 |
-
"DownEncoderBlock2D",
|
15 |
-
"DownEncoderBlock2D"
|
16 |
-
],
|
17 |
-
"force_upcast": true,
|
18 |
-
"in_channels": 3,
|
19 |
-
"latent_channels": 4,
|
20 |
-
"layers_per_block": 2,
|
21 |
-
"out_channels": 3,
|
22 |
-
"sample_size": 768,
|
23 |
-
"scaling_factor": 0.18215
|
24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pretrained/Cinemo/vae_temporal_decoder/diffusion_pytorch_model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5d92aa595a53d9da9faf594f09910ee869d5d567c8bb0362d5095673c69997d6
|
3 |
-
size 391017740
|
|
|
|
|
|
|
|