model release
Browse files- gallery_demo.png +3 -0
- model_index.json +41 -0
- scheduler/scheduler_config.json +18 -0
- text_encoder/config.json +30 -0
- text_encoder/embed_tokens_encoder.pt +3 -0
- text_encoder/model.safetensors +3 -0
- text_encoder_2/config.json +24 -0
- text_encoder_2/linear_proj.pth +3 -0
- text_encoder_2/model.safetensors +3 -0
- tokenizer/special_tokens_map.json +15 -0
- tokenizer/tokenizer.json +3 -0
- tokenizer/tokenizer_config.json +21 -0
- tokenizer_2/special_tokens_map.json +15 -0
- tokenizer_2/tokenizer.json +3 -0
- tokenizer_2/tokenizer_config.json +21 -0
- unet/config.json +72 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +14 -0
- vae/movq_model.safetensors +3 -0
gallery_demo.png
ADDED
Git LFS Details
|
model_index.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AniMemoryPipeLine",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
null,
|
6 |
+
null
|
7 |
+
],
|
8 |
+
"force_zeros_for_empty_prompt": true,
|
9 |
+
"image_encoder": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"EulerAncestralDiscreteXPredScheduler"
|
16 |
+
],
|
17 |
+
"text_encoder": [
|
18 |
+
"animemory",
|
19 |
+
"AniMemoryT5"
|
20 |
+
],
|
21 |
+
"text_encoder_2": [
|
22 |
+
"animemory",
|
23 |
+
"AniMemoryAltCLip"
|
24 |
+
],
|
25 |
+
"tokenizer": [
|
26 |
+
"transformers",
|
27 |
+
"XLMRobertaTokenizerFast"
|
28 |
+
],
|
29 |
+
"tokenizer_2": [
|
30 |
+
"transformers",
|
31 |
+
"XLMRobertaTokenizerFast"
|
32 |
+
],
|
33 |
+
"unet": [
|
34 |
+
"diffusers",
|
35 |
+
"UNet2DConditionModel"
|
36 |
+
],
|
37 |
+
"vae": [
|
38 |
+
"animemory",
|
39 |
+
"MoVQ"
|
40 |
+
]
|
41 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "EulerDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.26.0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"interpolation_type": "linear",
|
8 |
+
"num_train_timesteps": 1000,
|
9 |
+
"prediction_type": "sample",
|
10 |
+
"rescale_betas_zero_snr": false,
|
11 |
+
"sigma_max": null,
|
12 |
+
"sigma_min": null,
|
13 |
+
"steps_offset": 0,
|
14 |
+
"timestep_spacing": "linspace",
|
15 |
+
"timestep_type": "discrete",
|
16 |
+
"trained_betas": null,
|
17 |
+
"use_karras_sigmas": false
|
18 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"T5Stack"
|
4 |
+
],
|
5 |
+
"d_ff": 10240,
|
6 |
+
"d_kv": 64,
|
7 |
+
"d_model": 4096,
|
8 |
+
"decoder_start_token_id": 0,
|
9 |
+
"dense_act_fn": "gelu_new",
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": false,
|
15 |
+
"is_gated_act": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
+
"num_decoder_layers": 24,
|
19 |
+
"num_heads": 64,
|
20 |
+
"num_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.30.2",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 32128
|
30 |
+
}
|
text_encoder/embed_tokens_encoder.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bc67fbe6da33fce1aa34c865d3922821712775b0683cb8d1bcba1cc984ef5db
|
3 |
+
size 2048017234
|
text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422de804d9643e4891081fd49012ec7d21a1a779f7c582ed4e77b54d061e65f7
|
3 |
+
size 9261454176
|
text_encoder_2/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"CLIPTextModelWithProjection"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"dropout": 0.0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 1280,
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5120,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 77,
|
16 |
+
"model_type": "clip_text_model",
|
17 |
+
"num_attention_heads": 20,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"projection_dim": 1280,
|
21 |
+
"torch_dtype": "bfloat16",
|
22 |
+
"transformers_version": "4.30.2",
|
23 |
+
"vocab_size": 250002
|
24 |
+
}
|
text_encoder_2/linear_proj.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:723b47687d823e59f7210dfa3536493a09c08c58d8bde2a9c9d9785f4929e89d
|
3 |
+
size 3280439
|
text_encoder_2/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afd0cf9f32ae51da28113679291a983858180d4917e30024ccb5341e53fe02e8
|
3 |
+
size 1902904456
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d63ea22ce2c646e55084ebcef017e8f0e3cc7e02a9ace03ab1339912fe9d8439
|
3 |
+
size 17082729
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 77,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"processor_class": "AltCLIPProcessor",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|
tokenizer_2/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer_2/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d63ea22ce2c646e55084ebcef017e8f0e3cc7e02a9ace03ab1339912fe9d8439
|
3 |
+
size 17082729
|
tokenizer_2/tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 77,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"processor_class": "AltCLIPProcessor",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|
unet/config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.26.0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": "text_time",
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"addition_time_embed_dim": 256,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20
|
12 |
+
],
|
13 |
+
"attention_type": "default",
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"center_input_sample": false,
|
20 |
+
"class_embed_type": null,
|
21 |
+
"class_embeddings_concat": false,
|
22 |
+
"conv_in_kernel": 3,
|
23 |
+
"conv_out_kernel": 3,
|
24 |
+
"cross_attention_dim": 5376,
|
25 |
+
"cross_attention_norm": null,
|
26 |
+
"down_block_types": [
|
27 |
+
"DownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"layers_per_block": 2,
|
40 |
+
"mid_block_only_cross_attention": null,
|
41 |
+
"mid_block_scale_factor": 1,
|
42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
43 |
+
"norm_eps": 1e-05,
|
44 |
+
"norm_num_groups": 32,
|
45 |
+
"num_attention_heads": null,
|
46 |
+
"num_class_embeds": null,
|
47 |
+
"only_cross_attention": false,
|
48 |
+
"out_channels": 4,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_out_scale_factor": 1.0,
|
51 |
+
"resnet_skip_time_act": false,
|
52 |
+
"resnet_time_scale_shift": "default",
|
53 |
+
"reverse_transformer_layers_per_block": null,
|
54 |
+
"sample_size": 128,
|
55 |
+
"time_cond_proj_dim": null,
|
56 |
+
"time_embedding_act_fn": null,
|
57 |
+
"time_embedding_dim": null,
|
58 |
+
"time_embedding_type": "positional",
|
59 |
+
"timestep_post_act": null,
|
60 |
+
"transformer_layers_per_block": [
|
61 |
+
1,
|
62 |
+
2,
|
63 |
+
10
|
64 |
+
],
|
65 |
+
"up_block_types": [
|
66 |
+
"CrossAttnUpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"UpBlock2D"
|
69 |
+
],
|
70 |
+
"upcast_attention": null,
|
71 |
+
"use_linear_projection": true
|
72 |
+
}
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3aa3a5c6465c99dc895dd0bfe58be376b30d2d53eaab6743e29c149a57f4613
|
3 |
+
size 6242710008
|
vae/config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"double_z": false,
|
3 |
+
"z_channels": 4,
|
4 |
+
"resolution": 256,
|
5 |
+
"in_channels": 3,
|
6 |
+
"out_ch": 3,
|
7 |
+
"ch": 256,
|
8 |
+
"ch_mult": [1, 2, 2, 4],
|
9 |
+
"block_out_channels": [256, 512, 512, 1024],
|
10 |
+
"num_res_blocks": 2,
|
11 |
+
"attn_resolutions": [32],
|
12 |
+
"dropout": 0.0,
|
13 |
+
"scaling_factor": 1.0
|
14 |
+
}
|
vae/movq_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a58517ff5693662fd98147b58484dc5d9b879dac5e2a0f21389a6de525b27dfd
|
3 |
+
size 1082461324
|