saltacc commited on
Commit
5c02aec
1 Parent(s): d3b5218
README.md CHANGED
@@ -1,3 +1,21 @@
1
  ---
2
  license: other
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: other
3
  ---
4
+
5
+ IMPORTANT: this is a BETA MODEL! It is not done!
6
+
7
+ # Release Notes
8
+ https://cafeai.notion.site/WD-1-5-Beta-Release-Notes-967d3a5ece054d07bb02cba02e8199b7
9
+
10
+ # Checkpoints
11
+ Checkpoints are located in the "checkpoints" folder, under the files tab
12
+
13
+ # Aesthetic Embeddings
14
+ I've included a "wdgoodprompt" and "wdbadprompt" embedding in the embeddings folder to help make generation easier. With in progress models, its common to have to use long prompts for good results. Using these embeddings helps alleviate some of that.
15
+
16
+ # Generation
17
+ With Waifu Diffusion 1.5, best results are generated from generating at a resolution of somewhere between 500 and 1000 and then using 2x latent upscale hiresfix
18
+
19
+ ## License
20
+
21
+ WD 1.5 is released under the AGPL v3 ([https://www.gnu.org/licenses/agpl-3.0.en.html](https://www.gnu.org/licenses/agpl-3.0.en.html)) and the CreativeML Open RAIL++-M License ([https://huggingface.co/stabilityai/stable-diffusion-2/raw/main/LICENSE-MODEL](https://huggingface.co/stabilityai/stable-diffusion-2/raw/main/LICENSE-MODEL)), with both licenses being applicable. If any derivative of this model is made, please share your changes accordingly.
checkpoints/wd15-beta1-fp16.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da47dfd5acb2ba0302e67b7688ad0c1d30f6b0b5a66838156a4f8fbd4e1affcb
3
+ size 2580326690
checkpoints/wd15-beta1-fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5a5cf857fc145f37439b6db89245101018c8f538a77d0c30e77f946d35b9cf
3
+ size 2580068692
checkpoints/wd15-beta1-fp16.yaml ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False # we set this to false because this is an inference only config
20
+
21
+ unet_config:
22
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
23
+ params:
24
+ use_checkpoint: True
25
+ use_fp16: True
26
+ image_size: 32 # unused
27
+ in_channels: 4
28
+ out_channels: 4
29
+ model_channels: 320
30
+ attention_resolutions: [ 4, 2, 1 ]
31
+ num_res_blocks: 2
32
+ channel_mult: [ 1, 2, 4, 4 ]
33
+ num_head_channels: 64 # need to fix for flash-attn
34
+ use_spatial_transformer: True
35
+ use_linear_in_transformer: True
36
+ transformer_depth: 1
37
+ context_dim: 1024
38
+ legacy: False
39
+
40
+ first_stage_config:
41
+ target: ldm.models.autoencoder.AutoencoderKL
42
+ params:
43
+ embed_dim: 4
44
+ monitor: val/rec_loss
45
+ ddconfig:
46
+ #attn_type: "vanilla-xformers"
47
+ double_z: true
48
+ z_channels: 4
49
+ resolution: 256
50
+ in_channels: 3
51
+ out_ch: 3
52
+ ch: 128
53
+ ch_mult:
54
+ - 1
55
+ - 2
56
+ - 4
57
+ - 4
58
+ num_res_blocks: 2
59
+ attn_resolutions: []
60
+ dropout: 0.0
61
+ lossconfig:
62
+ target: torch.nn.Identity
63
+
64
+ cond_stage_config:
65
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
66
+ params:
67
+ freeze: True
68
+ layer: "penultimate"
checkpoints/wd15-beta1-fp32.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620db5529f7762dc9b5510faaf2188a326d844d4535bfbfdc3c61992b71a50c2
3
+ size 5160236890
checkpoints/wd15-beta1-fp32.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ea25c308554b99fed79e359f4d70b3b25d6218589ab295b225c2f2bcbb5568
3
+ size 5159974886
checkpoints/wd15-beta1-fp32.yaml ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False # we set this to false because this is an inference only config
20
+
21
+ unet_config:
22
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
23
+ params:
24
+ use_checkpoint: True
25
+ use_fp16: True
26
+ image_size: 32 # unused
27
+ in_channels: 4
28
+ out_channels: 4
29
+ model_channels: 320
30
+ attention_resolutions: [ 4, 2, 1 ]
31
+ num_res_blocks: 2
32
+ channel_mult: [ 1, 2, 4, 4 ]
33
+ num_head_channels: 64 # need to fix for flash-attn
34
+ use_spatial_transformer: True
35
+ use_linear_in_transformer: True
36
+ transformer_depth: 1
37
+ context_dim: 1024
38
+ legacy: False
39
+
40
+ first_stage_config:
41
+ target: ldm.models.autoencoder.AutoencoderKL
42
+ params:
43
+ embed_dim: 4
44
+ monitor: val/rec_loss
45
+ ddconfig:
46
+ #attn_type: "vanilla-xformers"
47
+ double_z: true
48
+ z_channels: 4
49
+ resolution: 256
50
+ in_channels: 3
51
+ out_ch: 3
52
+ ch: 128
53
+ ch_mult:
54
+ - 1
55
+ - 2
56
+ - 4
57
+ - 4
58
+ num_res_blocks: 2
59
+ attn_resolutions: []
60
+ dropout: 0.0
61
+ lossconfig:
62
+ target: torch.nn.Identity
63
+
64
+ cond_stage_config:
65
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
66
+ params:
67
+ freeze: True
68
+ layer: "penultimate"
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
+ }
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.12.1",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "requires_safety_checker": true,
9
+ "safety_checker": [
10
+ "stable_diffusion",
11
+ "StableDiffusionSafetyChecker"
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.12.1",
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": "v_prediction",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/sd-finetune-data/cafe-output/wd-15-official-step-2-2023-02-03-18-08/step_120000",
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": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.26.0",
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:cce6febb0b6d876ee5eb24af35e27e764eb4f9b1d0b7c026c8c3333d4cfc916c
3
+ size 1361597018
unet/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.12.1",
4
+ "_name_or_path": "/mnt/sd-finetune-data/cafe-output/wd-15-official-step-2-2023-02-03-18-08/step_120000",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "cross_attention_dim": 1024,
21
+ "down_block_types": [
22
+ "CrossAttnDownBlock2D",
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "DownBlock2D"
26
+ ],
27
+ "downsample_padding": 1,
28
+ "dual_cross_attention": false,
29
+ "flip_sin_to_cos": true,
30
+ "freq_shift": 0,
31
+ "in_channels": 4,
32
+ "layers_per_block": 2,
33
+ "mid_block_scale_factor": 1,
34
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
35
+ "norm_eps": 1e-05,
36
+ "norm_num_groups": 32,
37
+ "num_class_embeds": null,
38
+ "only_cross_attention": false,
39
+ "out_channels": 4,
40
+ "resnet_time_scale_shift": "default",
41
+ "sample_size": 96,
42
+ "up_block_types": [
43
+ "UpBlock2D",
44
+ "CrossAttnUpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D"
47
+ ],
48
+ "upcast_attention": true,
49
+ "use_linear_projection": true
50
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b6cb73e529ad559d88bd674a187d21bad1679d43a8ba9cff19ed1cc6453856
3
+ size 3463726467
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.12.1",
4
+ "_name_or_path": "/mnt/sd-finetune-data/cafe/cafe-tools/vae-v2/vae-v2",
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
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba2a6f13818912597aabe11b15e3cb20c4b80fbb28c469284687b2c5758d474
3
+ size 334643245