Guizmus commited on
Commit
48e007f
1 Parent(s): d858350

Upload 15 files

Browse files
README.md CHANGED
@@ -1,3 +1,138 @@
1
  ---
 
 
2
  license: creativeml-openrail-m
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: creativeml-openrail-m
5
+ thumbnail: "https://huggingface.co/Guizmus/SDArt_Catstravaganza/resolve/main/showcase.jpg"
6
+ tags:
7
+ - stable-diffusion
8
+ - text-to-image
9
+ - image-to-image
10
  ---
11
+ # PoW : CATSTRAVAGANZA !
12
+
13
+ ![Showcase](https://huggingface.co/Guizmus/SDArt_Catstravaganza/resolve/main/showcase.jpg)
14
+
15
+ ## Theme
16
+
17
+
18
+ > Orb-like eyes, mischief, and surprise
19
+ > Cat paws tip-a-tap at your side
20
+ > With their fanged teeth and coy mystique
21
+ > They gaze up at you ever so sweet
22
+ > Won’t you give them a treat?
23
+
24
+ This POW’s all about our favorite feline friends wherein we are absolutely not biased. Be as creative as you can!
25
+
26
+ Whether it be a cat made of cotton candy, a grumpy cat made of storm clouds, or just your regular degular tabby cat. Bring them all here and may the best cat reign supreme!
27
+
28
+ “It’s raining cats and cats out here!”
29
+
30
+ * Join us for a cat-stravaganza of fun
31
+ * Cute and cuddly - show us your paw-sitively purrfect creations!
32
+ * Whisk-er away your doubts and unleash your cat-titude
33
+ * Wander into the canvas alongside your meow-gnificant feline friends!
34
+
35
+ ## Model description
36
+
37
+ This is a model related to the "Picture of the Week" contest on Stable Diffusion discord.
38
+
39
+ I try to make a model out of all the submission for people to continue enjoy the theme after the even, and see a little of their designs in other people's creations. The main token just changed to "SDArt", usually staying the same week to week. I balance the learning on the low side, so that it doesn't just replicate creations.
40
+
41
+ The total dataset is made of 61 pictures. It was trained on [Stable diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5). I used [EveryDream](https://github.com/victorchall/EveryDream2trainer) to do the training, 100 total repeat per picture. The pictures were tagged using the token "SDArt", and an arbitrary token I choose for each submission. The dataset is provided below, as well as a list of usernames and their corresponding token.
42
+
43
+ The recommended sampling is UniPC on 15 steps, CFGS 5 .
44
+
45
+ ## Trained tokens
46
+
47
+ * SDArt
48
+ * **User** => **Token**
49
+ * Aiska#5641 => dyce
50
+ * Akumetsu971#9982 => ohwx
51
+ * alex1729#4669 => bnp
52
+ * andrekerygma#4898 => tobi
53
+ * balrogdx#7106 => keel
54
+ * BeardedWhale#3993 => conv
55
+ * beta_caojin#9338 => cov
56
+ * bitspirit3#1653 => aten
57
+ * Brett#2283 => stg
58
+ * bWm_nubby#6416 => fcu
59
+ * csunberry#0594 => nwsl
60
+ * Dexyel#9083 => cous
61
+ * Dreamck#2108 => gare
62
+ * Dries#2321 => mth
63
+ * dunkeroni#4269 => nrf
64
+ * DylanWalker#9705 => elio
65
+ * Eface#8250 => gani
66
+ * Eppinette-Chi#6220 => pfa
67
+ * espasmo#9486 => kprc
68
+ * Guizmus#9881 => kuro
69
+ * Havok#2933 => ndi
70
+ * Horvallis#7915 => asot
71
+ * Jeremy#6194 => sill
72
+ * joachim#4676 => coyi
73
+ * Junglerally#3955 => bsp
74
+ * katmoget#4491 => psst
75
+ * Kaz#5485 => sqm
76
+ * King Pendragon#3589 => irgc
77
+ * Kingpin#2557 => buka
78
+ * Lenny_dV#6843 => lili
79
+ * Lord Parfington#0012 => hns
80
+ * marjan2k#5277 => cq
81
+ * MooDFooD#6245 => bdg
82
+ * mr.katkot#5949 => scd
83
+ * Munkyfoot#7944 => byes
84
+ * NorTroll#1798 => dany
85
+ * Omnia#2931 => yler
86
+ * Onusai#6441 => aroa
87
+ * owleye#1290 => avel
88
+ * Phaff#1970 => vaw
89
+ * piscabo#8649 => zaki
90
+ * qushkitti#0978 => muna
91
+ * Redinhead#3342 => ewe
92
+ * ResidentChiefNZ#6989 => guin
93
+ * Sam#8080 => erra
94
+ * SirVeggie#0230 => urd
95
+ * Smol Sus#0909 => nasi
96
+ * sometimes#8916 => vini
97
+ * SpaceCypher#6900 => fbs
98
+ * tazi#2574 => crit
99
+ * Trash--Panda#6213 => doa
100
+ * ulla_diffusion#0451 => mlas
101
+ * UniversityEuphoric#3284 => ylor
102
+ * uwyne#1111 => isch
103
+ * vcm07#7281 => phol
104
+ * VereVolf#5658 => vedi
105
+ * Vil#0404 => dds
106
+ * Wipeout#0031 => acu
107
+ * wpatzz#5836 => pte
108
+ * xThIsIsBoToXx#8765 => oxi
109
+ * yamination#7634 => bsgo
110
+
111
+ ## Download links
112
+
113
+ [SafeTensors](https://huggingface.co/Guizmus/SDArt_Catstravaganza/resolve/main/SDArt-Catstravaganza.safetensors)
114
+
115
+ [CKPT](https://huggingface.co/Guizmus/SDArt_Catstravaganza/resolve/main/SDArt-Catstravaganza.ckpt)
116
+
117
+ [Dataset](https://huggingface.co/Guizmus/SDArt_Catstravaganza/resolve/main/dataset.zip)
118
+
119
+ ## 🧨 Diffusers
120
+
121
+ This model can be used just like any other Stable Diffusion model. For more information,
122
+ please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
123
+
124
+ You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
125
+
126
+ ```python
127
+ from diffusers import StableDiffusionPipeline
128
+ import torch
129
+
130
+ model_id = "Guizmus/SDArt_Catstravaganza"
131
+ pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
132
+ pipe = pipe.to("cuda")
133
+
134
+ prompt = "SDArt dyce"
135
+ image = pipe(prompt).images[0]
136
+
137
+ image.save("./SDArt.png")
138
+ ```
SDArt_catstravaganza.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af4fc3f55a7d32fab870ade39cbc1968c77bc6813fa8fbcb437ad24ef6b6098
3
+ size 2132856622
dataset.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3ce847951d5d0e3b7ac235543475ad318520541709ff9c2c1aa954f71e54e7
3
+ size 57236722
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.13.0",
4
+ "feature_extractor": [
5
+ null,
6
+ null
7
+ ],
8
+ "requires_safety_checker": null,
9
+ "safety_checker": [
10
+ null,
11
+ null
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "DDPMScheduler"
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMScheduler",
3
+ "_diffusers_version": "0.13.0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
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
+ "variance_type": "fixed_small"
16
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
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": "4.25.1",
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:c3e3ed691b4a373924e3caf02a5a960b2f0dd855f05b99add977f1f693e184ba
3
+ size 492308087
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
23
+ "pad_token": "<|endoftext|>",
24
+ "special_tokens_map_file": "./special_tokens_map.json",
25
+ "tokenizer_class": "CLIPTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "use_fast": false
35
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.13.0",
4
+ "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
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
+ "dual_cross_attention": false,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 4,
29
+ "layers_per_block": 2,
30
+ "mid_block_scale_factor": 1,
31
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
32
+ "norm_eps": 1e-05,
33
+ "norm_num_groups": 32,
34
+ "num_class_embeds": null,
35
+ "only_cross_attention": false,
36
+ "out_channels": 4,
37
+ "projection_class_embeddings_input_dim": null,
38
+ "resnet_time_scale_shift": "default",
39
+ "sample_size": 64,
40
+ "time_cond_proj_dim": null,
41
+ "time_embedding_type": "positional",
42
+ "timestep_post_act": null,
43
+ "up_block_types": [
44
+ "UpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D",
47
+ "CrossAttnUpBlock2D"
48
+ ],
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d7da30a574dcff216c42527b1c80af73fad0e92ed2e2afb5c6fe5c84ed1c5e
3
+ size 3438364325
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.13.0",
4
+ "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
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
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb128b1f37e0c381c440128b217d29613b3e08b9e4ea7f20466424145ba538b0
3
+ size 167402961