Hugging Face's logo

haoningwu
/
StoryGen

Diffusers
Model card Files
xet
Community
1
haoningwu commited on
Commit
ecfa719
·
verified ·
1 Parent(s): b4518fd

Upload 22 files

Browse files
Files changed (22) hide show
  1. checkpoint_COCO/text_encoder/config.json +25 -0
  2. checkpoint_COCO/text_encoder/pytorch_model.bin +3 -0
  3. checkpoint_COCO/tokenizer/merges.txt +0 -0
  4. checkpoint_COCO/tokenizer/special_tokens_map.json +24 -0
  5. checkpoint_COCO/tokenizer/tokenizer_config.json +33 -0
  6. checkpoint_COCO/tokenizer/vocab.json +0 -0
  7. checkpoint_COCO/unet/config.json +47 -0
  8. checkpoint_COCO/unet/diffusion_pytorch_model.bin +3 -0
  9. checkpoint_COCO/vae/config.json +31 -0
  10. checkpoint_COCO/vae/diffusion_pytorch_model.bin +3 -0
  11. checkpoint_StorySalon/model_index.json +24 -0
  12. checkpoint_StorySalon/scheduler/scheduler_config.json +14 -0
  13. checkpoint_StorySalon/text_encoder/config.json +25 -0
  14. checkpoint_StorySalon/text_encoder/pytorch_model.bin +3 -0
  15. checkpoint_StorySalon/tokenizer/merges.txt +0 -0
  16. checkpoint_StorySalon/tokenizer/special_tokens_map.json +24 -0
  17. checkpoint_StorySalon/tokenizer/tokenizer_config.json +33 -0
  18. checkpoint_StorySalon/tokenizer/vocab.json +0 -0
  19. checkpoint_StorySalon/unet/config.json +47 -0
  20. checkpoint_StorySalon/unet/diffusion_pytorch_model.bin +3 -0
  21. checkpoint_StorySalon/vae/config.json +31 -0
  22. checkpoint_StorySalon/vae/diffusion_pytorch_model.bin +3 -0
checkpoint_COCO/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/home/haoningwu/Diffusion/StoryTellingP/ckpt/checkpoint_40000",
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": "4.33.3",
24
+ "vocab_size": 49408
25
+ }
checkpoint_COCO/text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1331e0172e49cd7c3c906d6424f264f2c8248b723fbfc502e699ff3bc06257
3
+ size 492307065
checkpoint_COCO/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint_COCO/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
+ }
checkpoint_COCO/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
+ }
checkpoint_COCO/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint_COCO/unet/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.13.1",
4
+ "_name_or_path": "/data/home/haoningwu/Diffusion/StoryTellingP/ckpt/checkpoint_40000",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "conv_in_kernel": 3,
16
+ "conv_out_kernel": 3,
17
+ "cross_attention_dim": 768,
18
+ "down_block_types": [
19
+ "CrossAttnDownBlock2D",
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "DownBlock2D"
23
+ ],
24
+ "downsample_padding": 1,
25
+ "flip_sin_to_cos": true,
26
+ "freq_shift": 0,
27
+ "in_channels": 4,
28
+ "layers_per_block": 2,
29
+ "mid_block_scale_factor": 1,
30
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
31
+ "norm_eps": 1e-05,
32
+ "norm_num_groups": 32,
33
+ "num_class_embeds": null,
34
+ "only_cross_attention": false,
35
+ "out_channels": 4,
36
+ "resnet_time_scale_shift": "default",
37
+ "sample_size": 512,
38
+ "time_embedding_type": "positional",
39
+ "up_block_types": [
40
+ "UpBlock2D",
41
+ "CrossAttnUpBlock2D",
42
+ "CrossAttnUpBlock2D",
43
+ "CrossAttnUpBlock2D"
44
+ ],
45
+ "upcast_attention": false,
46
+ "use_linear_projection": false
47
+ }
checkpoint_COCO/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2304a6282a44fb2e0db68e101a9dae5f0a8e96966810aebafa4ef08ce27c270
3
+ size 3636810629
checkpoint_COCO/vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.13.1",
4
+ "_name_or_path": "/data/home/haoningwu/Diffusion/StoryTellingP/ckpt/checkpoint_40000",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 512,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
checkpoint_COCO/vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f506c519bca6fcb25f695b94364422f7b2f534d52ded3decbcd6674a5101b500
3
+ size 334710673
checkpoint_StorySalon/model_index.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.13.1",
4
+ "scheduler": [
5
+ "diffusers",
6
+ "DDIMScheduler"
7
+ ],
8
+ "text_encoder": [
9
+ "transformers",
10
+ "CLIPTextModel"
11
+ ],
12
+ "tokenizer": [
13
+ "transformers",
14
+ "CLIPTokenizer"
15
+ ],
16
+ "unet": [
17
+ null,
18
+ "UNet2DConditionModel"
19
+ ],
20
+ "vae": [
21
+ "diffusers",
22
+ "AutoencoderKL"
23
+ ]
24
+ }
checkpoint_StorySalon/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.13.1",
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
+ }
checkpoint_StorySalon/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/home/haoningwu/Diffusion/StoryTellingIPS/ckpt2/checkpoint_40000",
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": "4.33.3",
24
+ "vocab_size": 49408
25
+ }
checkpoint_StorySalon/text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d19d629f9de1c788a55030c971b2ba980822b47e1756ecf9c5c318b85f0da8
3
+ size 492307065
checkpoint_StorySalon/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint_StorySalon/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
+ }
checkpoint_StorySalon/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
+ }
checkpoint_StorySalon/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint_StorySalon/unet/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.13.1",
4
+ "_name_or_path": "/data/home/haoningwu/Diffusion/StoryTellingIPS/ckpt2/checkpoint_40000",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "conv_in_kernel": 3,
16
+ "conv_out_kernel": 3,
17
+ "cross_attention_dim": 768,
18
+ "down_block_types": [
19
+ "CrossAttnDownBlock2D",
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "DownBlock2D"
23
+ ],
24
+ "downsample_padding": 1,
25
+ "flip_sin_to_cos": true,
26
+ "freq_shift": 0,
27
+ "in_channels": 4,
28
+ "layers_per_block": 2,
29
+ "mid_block_scale_factor": 1,
30
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
31
+ "norm_eps": 1e-05,
32
+ "norm_num_groups": 32,
33
+ "num_class_embeds": null,
34
+ "only_cross_attention": false,
35
+ "out_channels": 4,
36
+ "resnet_time_scale_shift": "default",
37
+ "sample_size": 512,
38
+ "time_embedding_type": "positional",
39
+ "up_block_types": [
40
+ "UpBlock2D",
41
+ "CrossAttnUpBlock2D",
42
+ "CrossAttnUpBlock2D",
43
+ "CrossAttnUpBlock2D"
44
+ ],
45
+ "upcast_attention": false,
46
+ "use_linear_projection": false
47
+ }
checkpoint_StorySalon/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e16af87f1a8bc0842aeae0720606ae562d559c908b9c9e0aa3fd735e3496ef
3
+ size 3636810629
checkpoint_StorySalon/vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.13.1",
4
+ "_name_or_path": "/data/home/haoningwu/Diffusion/StoryTellingIPS/ckpt2/checkpoint_40000",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 512,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
checkpoint_StorySalon/vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16a79cb6c6127b8965341d585af620c4fd9362c4d33d561213d2bdd2f0727fb
3
+ size 334710673