Hugging Face's logo

reza-alipour
/
face-muse

Diffusers
Safetensors
AmusedPipeline
Model card Files Community
reza-alipour commited on
Commit
e4f30b8
·
1 Parent(s): 5101cfa

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. text_encoder/config.json +25 -0
  2. text_encoder/pytorch_model.bin +3 -0
  3. tokenizer/merges.txt +0 -0
  4. tokenizer/special_tokens_map.json +24 -0
  5. tokenizer/tokenizer_config.json +33 -0
  6. tokenizer/vocab.json +0 -0
  7. transformer/config.json +27 -0
  8. transformer/diffusion_pytorch_model.safetensors +3 -0
  9. vqvae/config.json +39 -0
  10. vqvae/diffusion_pytorch_model.safetensors +3 -0
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openMUSE/clip-vit-large-patch14-text-enc",
3
+ "architectures": [
4
+ "CLIPTextModelWithProjection"
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
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.33.0",
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:d666716eab583fbf22cf28c3cd2a5a2f6fa46114a43be00bb0a69a0fee6f89b1
3
+ size 494665697
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
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
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
 
transformer/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UVit2DModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "reza-alipour/mb",
5
+ "attention_dropout": 0.0,
6
+ "block_num_heads": 12,
7
+ "block_out_channels": 768,
8
+ "codebook_size": 8192,
9
+ "cond_embed_dim": 768,
10
+ "downsample": true,
11
+ "encoder_hidden_size": 768,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "in_channels": 768,
15
+ "intermediate_size": 2816,
16
+ "layer_norm_eps": 1e-06,
17
+ "ln_elementwise_affine": true,
18
+ "micro_cond_embed_dim": 1280,
19
+ "micro_cond_encode_dim": 256,
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 22,
22
+ "num_res_blocks": 3,
23
+ "sample_size": 16,
24
+ "upsample": true,
25
+ "use_bias": false,
26
+ "vocab_size": 8256
27
+ }
transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03281ab4232f098fda24d5d9a41abfc24e180ca922707293b92dea05b045e727
3
+ size 2433086672
vqvae/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "VQModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "reza-alipour/vq-tokenizer",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 256,
10
+ 512,
11
+ 768
12
+ ],
13
+ "down_block_types": [
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D",
17
+ "DownEncoderBlock2D",
18
+ "DownEncoderBlock2D"
19
+ ],
20
+ "in_channels": 3,
21
+ "latent_channels": 64,
22
+ "layers_per_block": 2,
23
+ "lookup_from_codebook": true,
24
+ "mid_block_add_attention": false,
25
+ "norm_num_groups": 32,
26
+ "norm_type": "group",
27
+ "num_vq_embeddings": 8192,
28
+ "out_channels": 3,
29
+ "sample_size": 32,
30
+ "scaling_factor": 0.18215,
31
+ "up_block_types": [
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D",
35
+ "UpDecoderBlock2D",
36
+ "UpDecoderBlock2D"
37
+ ],
38
+ "vq_embed_dim": null
39
+ }
vqvae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74397c70e364f52785da9d4ea66a24b0643f5681b7782b5f40520aaa603cfe9b
3
+ size 585009980