feishen29 commited on
Commit
5a7a7f0
1 Parent(s): 5354120

Upload 9 files

Browse files
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DEISMultistepScheduler",
3
+ "_diffusers_version": "0.16.1",
4
+ "algorithm_type": "deis",
5
+ "beta_end": 0.012,
6
+ "beta_schedule": "scaled_linear",
7
+ "beta_start": 0.00085,
8
+ "clip_sample": false,
9
+ "clip_sample_range": 1.0,
10
+ "dynamic_thresholding_ratio": 0.995,
11
+ "lower_order_final": true,
12
+ "num_train_timesteps": 1000,
13
+ "prediction_type": "epsilon",
14
+ "sample_max_value": 1.0,
15
+ "set_alpha_to_one": false,
16
+ "solver_order": 2,
17
+ "solver_type": "logrho",
18
+ "steps_offset": 1,
19
+ "thresholding": false,
20
+ "trained_betas": null
21
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee67788c3c9a6f5d73de077b644f1d4317258b55fbcc372dc385e8e5587c1cc
3
+ size 492265880
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": "<|endoftext|>",
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
 
unet/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.16.1",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "attention_head_dim": 8,
8
+ "block_out_channels": [
9
+ 320,
10
+ 640,
11
+ 1280,
12
+ 1280
13
+ ],
14
+ "center_input_sample": false,
15
+ "class_embed_type": null,
16
+ "class_embeddings_concat": false,
17
+ "conv_in_kernel": 3,
18
+ "conv_out_kernel": 3,
19
+ "cross_attention_dim": 768,
20
+ "cross_attention_norm": null,
21
+ "down_block_types": [
22
+ "CrossAttnDownBlock2D",
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "DownBlock2D"
26
+ ],
27
+ "downsample_padding": 1,
28
+ "dual_cross_attention": false,
29
+ "encoder_hid_dim": null,
30
+ "flip_sin_to_cos": true,
31
+ "freq_shift": 0,
32
+ "in_channels": 4,
33
+ "layers_per_block": 2,
34
+ "mid_block_only_cross_attention": null,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": null,
43
+ "resnet_out_scale_factor": 1.0,
44
+ "resnet_skip_time_act": false,
45
+ "resnet_time_scale_shift": "default",
46
+ "sample_size": 64,
47
+ "time_cond_proj_dim": null,
48
+ "time_embedding_act_fn": null,
49
+ "time_embedding_dim": null,
50
+ "time_embedding_type": "positional",
51
+ "timestep_post_act": null,
52
+ "up_block_types": [
53
+ "UpBlock2D",
54
+ "CrossAttnUpBlock2D",
55
+ "CrossAttnUpBlock2D",
56
+ "CrossAttnUpBlock2D"
57
+ ],
58
+ "upcast_attention": false,
59
+ "use_linear_projection": false
60
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75956623c8f95b40e62b3ee45f5dcba8e353b53c33c6765e517c5a8bb3dfbfe
3
+ size 3438167536