megemini commited on
Commit
705a714
1 Parent(s): ef25cae

submit best ckpt

Browse files
.gitattributes CHANGED
@@ -32,3 +32,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ safety_checker/model_state.pdparams filter=lfs diff=lfs merge=lfs -text
36
+ unet/model_state.pdparams filter=lfs diff=lfs merge=lfs -text
37
+ vae/model_state.pdparams filter=lfs diff=lfs merge=lfs -text
38
+ text_encoder/model_state.pdparams filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,17 @@
 
1
  ---
2
- license: mit
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
1
+
2
  ---
3
+ license: creativeml-openrail-m
4
+ base_model: shanshui_gen_style
5
+ instance_prompt: A fantasy landscape in <shanshui-gen-style>
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-ppdiffusers
9
+ - text-to-image
10
+ - ppdiffusers
11
+ - lora
12
+ inference: false
13
  ---
14
+
15
+ # LoRA DreamBooth - megemini/shanshui_gen_style
16
+ 本仓库的 LoRA 权重是基于 shanshui_gen_style 训练而来的,我们采用[DreamBooth](https://dreambooth.github.io/)的技术并使用 A fantasy landscape in <shanshui-gen-style> 文本进行了训练。 下面是在训练过程中生成的一些图片。
17
+
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPFeatureExtractor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
learned_embeds-steps-1000.pdparams ADDED
Binary file (3.31 kB). View file
 
learned_embeds-steps-500.pdparams ADDED
Binary file (3.31 kB). View file
 
learned_embeds.pdparams ADDED
Binary file (3.31 kB). View file
 
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.14.1",
4
+ "_ppdiffusers_version": "0.14.1",
5
+ "feature_extractor": [
6
+ "paddlenlp.transformers",
7
+ "CLIPFeatureExtractor"
8
+ ],
9
+ "requires_safety_checker": true,
10
+ "safety_checker": [
11
+ "stable_diffusion",
12
+ "StableDiffusionSafetyChecker"
13
+ ],
14
+ "scheduler": [
15
+ "ppdiffusers",
16
+ "PNDMScheduler"
17
+ ],
18
+ "text_encoder": [
19
+ "paddlenlp.transformers",
20
+ "CLIPTextModel"
21
+ ],
22
+ "tokenizer": [
23
+ "paddlenlp.transformers",
24
+ "CLIPTokenizer"
25
+ ],
26
+ "unet": [
27
+ "ppdiffusers",
28
+ "UNet2DConditionModel"
29
+ ],
30
+ "vae": [
31
+ "ppdiffusers",
32
+ "AutoencoderKL"
33
+ ]
34
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "StableDiffusionSafetyChecker"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dropout": 0.0,
7
+ "dtype": "float32",
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 1024,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 24,
19
+ "paddlenlp_version": null,
20
+ "patch_size": 14,
21
+ "projection_dim": 768,
22
+ "return_dict": true
23
+ }
safety_checker/model_state.pdparams ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382cfd4b5993998b4db3695832e7f1412083e09c69a9f2bed8b49e885e1c1a79
3
+ size 1215975220
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.14.1",
4
+ "_ppdiffusers_version": "0.14.1",
5
+ "beta_end": 0.012,
6
+ "beta_schedule": "scaled_linear",
7
+ "beta_start": 0.00085,
8
+ "clip_sample": false,
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "epsilon",
11
+ "set_alpha_to_one": false,
12
+ "skip_prk_steps": true,
13
+ "steps_offset": 1,
14
+ "trained_betas": null
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "quick_gelu",
12
+ "hidden_size": 768,
13
+ "initializer_factor": 1.0,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 77,
18
+ "model_type": "clip_text_model",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "paddlenlp_version": null,
23
+ "projection_dim": 512,
24
+ "return_dict": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.21.0.dev0",
27
+ "vocab_size": 49409
28
+ }
text_encoder/model_state.pdparams ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c409e72c273f043fcebac9eb23f6862824c265236982103b58a65cd4e579564
3
+ size 492267458
tokenizer/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<shanshui-gen-style>": 49408}
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 @@
 
 
1
+ {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "max_len": 77, "bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>", "tokenizer_class": "CLIPTokenizer", "special_tokens_map_file": "/home/aistudio/.paddlenlp/models/runwayml/stable-diffusion-v1-5/tokenizer/special_tokens_map.json"}
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_paddle_version": "0.5.0",
4
+ "_diffusers_version": "0.14.1",
5
+ "_name_or_path": "/home/aistudio/.cache/paddlenlp/ppdiffusers/runwayml/stable-diffusion-v1-5/unet",
6
+ "_ppdiffusers_version": "0.14.1",
7
+ "act_fn": "silu",
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "conv_in_kernel": 3,
18
+ "conv_out_kernel": 3,
19
+ "cross_attention_dim": 768,
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
+ "projection_class_embeddings_input_dim": null,
40
+ "resnet_pre_temb_non_linearity": false,
41
+ "resnet_time_scale_shift": "default",
42
+ "sample_size": 64,
43
+ "time_cond_proj_dim": null,
44
+ "time_embedding_type": "positional",
45
+ "timestep_post_act": null,
46
+ "up_block_types": [
47
+ "UpBlock2D",
48
+ "CrossAttnUpBlock2D",
49
+ "CrossAttnUpBlock2D",
50
+ "CrossAttnUpBlock2D"
51
+ ],
52
+ "upcast_attention": false,
53
+ "use_linear_projection": false
54
+ }
unet/model_state.pdparams ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2862ec9c1fc724c42742640e8a61b7302d40fdd7a2ff198d21620ace9033db
3
+ size 3438162185
vae/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_paddle_version": "0.5.0",
4
+ "_diffusers_version": "0.14.1",
5
+ "_name_or_path": "/home/aistudio/.cache/paddlenlp/ppdiffusers/runwayml/stable-diffusion-v1-5/vae",
6
+ "_ppdiffusers_version": "0.14.1",
7
+ "act_fn": "silu",
8
+ "block_out_channels": [
9
+ 128,
10
+ 256,
11
+ 512,
12
+ 512
13
+ ],
14
+ "down_block_out_channels": null,
15
+ "down_block_types": [
16
+ "DownEncoderBlock2D",
17
+ "DownEncoderBlock2D",
18
+ "DownEncoderBlock2D",
19
+ "DownEncoderBlock2D"
20
+ ],
21
+ "in_channels": 3,
22
+ "latent_channels": 4,
23
+ "layers_per_block": 2,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "sample_size": 512,
27
+ "scaling_factor": 0.18215,
28
+ "up_block_out_channels": null,
29
+ "up_block_types": [
30
+ "UpDecoderBlock2D",
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D"
34
+ ]
35
+ }
vae/model_state.pdparams ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e107b8b4bb25b32688e72196b43749a4c29484565e3eb606101c1146e3bca675
3
+ size 334641708