Hugging Face's logo

enryu43
/
anifusion_sd_unet_768

Diffusers
LDMTextToImagePipeline
Model card Files Community
enryu43 commited on
Commit
45c9d10
•
1 Parent(s): c1a2eb2

Initial commit

Browse files
Files changed (13) hide show
  1. bert/config.json +26 -0
  2. bert/pytorch_model.bin +3 -0
  3. model_index.json +24 -0
  4. original_ckpt.bin +3 -0
  5. scheduler/scheduler_config.json +14 -0
  6. tokenizer/special_tokens_map.json +7 -0
  7. tokenizer/tokenizer.json +0 -0
  8. tokenizer/tokenizer_config.json +14 -0
  9. tokenizer/vocab.txt +0 -0
  10. unet/config.json +49 -0
  11. unet/diffusion_pytorch_model.bin +3 -0
  12. vqvae/config.json +29 -0
  13. vqvae/diffusion_pytorch_model.bin +3 -0
bert/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "LDMBertModel"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "classifier_dropout": 0.0,
9
+ "d_model": 1024,
10
+ "dropout": 0.1,
11
+ "encoder_attention_heads": 8,
12
+ "encoder_ffn_dim": 4096,
13
+ "encoder_layerdrop": 0.0,
14
+ "encoder_layers": 12,
15
+ "head_dim": 64,
16
+ "init_std": 0.02,
17
+ "max_position_embeddings": 50,
18
+ "model_type": "ldmbert",
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 0,
21
+ "scale_embedding": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.23.1",
24
+ "use_cache": true,
25
+ "vocab_size": 12221
26
+ }
bert/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15c7f4bd89935cfba25f537d0ca4c6117bd9c5d4ea0adb57b857686c76d36206
3
+ size 604235221
model_index.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LDMTextToImagePipeline",
3
+ "_diffusers_version": "0.11.1",
4
+ "bert": [
5
+ "latent_diffusion",
6
+ "LDMBertModel"
7
+ ],
8
+ "scheduler": [
9
+ "diffusers",
10
+ "PNDMScheduler"
11
+ ],
12
+ "tokenizer": [
13
+ "transformers",
14
+ "BertTokenizerFast"
15
+ ],
16
+ "unet": [
17
+ "diffusers",
18
+ "UNet2DConditionModel"
19
+ ],
20
+ "vqvae": [
21
+ "diffusers",
22
+ "AutoencoderKL"
23
+ ]
24
+ }
original_ckpt.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c179feab60010ae0f789ee9fbaf9454ad1470c4297ecbe3d309dfcf6536402
3
+ size 4402968141
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.11.1",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.11.1",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": [
6
+ 5,
7
+ 10,
8
+ 20,
9
+ 20
10
+ ],
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "cross_attention_dim": 1024,
20
+ "down_block_types": [
21
+ "CrossAttnDownBlock2D",
22
+ "CrossAttnDownBlock2D",
23
+ "CrossAttnDownBlock2D",
24
+ "DownBlock2D"
25
+ ],
26
+ "downsample_padding": 1,
27
+ "dual_cross_attention": false,
28
+ "flip_sin_to_cos": true,
29
+ "freq_shift": 0,
30
+ "in_channels": 4,
31
+ "layers_per_block": 2,
32
+ "mid_block_scale_factor": 1,
33
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
34
+ "norm_eps": 1e-05,
35
+ "norm_num_groups": 32,
36
+ "num_class_embeds": null,
37
+ "only_cross_attention": false,
38
+ "out_channels": 4,
39
+ "resnet_time_scale_shift": "default",
40
+ "sample_size": 64,
41
+ "up_block_types": [
42
+ "UpBlock2D",
43
+ "CrossAttnUpBlock2D",
44
+ "CrossAttnUpBlock2D",
45
+ "CrossAttnUpBlock2D"
46
+ ],
47
+ "upcast_attention": false,
48
+ "use_linear_projection": true
49
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1684c9bdb2d94a17904f0c8e868ae5178622c72b0631e67094d91045753e6447
3
+ size 3463925093
vqvae/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.11.1",
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
+ "norm_num_groups": 32,
21
+ "out_channels": 3,
22
+ "sample_size": 512,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
vqvae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
3
+ size 334711857