davidrd123 commited on
Commit
2cf01a0
1 Parent(s): 69d9b66

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +190 -0
README.md ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ base_model: "stabilityai/stable-diffusion-xl-base-1.0"
4
+ tags:
5
+ - sdxl
6
+ - sdxl-diffusers
7
+ - text-to-image
8
+ - diffusers
9
+ - simpletuner
10
+ - not-for-all-audiences
11
+ - lora
12
+ - template:sd-lora
13
+ - lycoris
14
+ inference: true
15
+ widget:
16
+ - text: 'unconditional (blank prompt)'
17
+ parameters:
18
+ negative_prompt: 'blurry, cropped, ugly'
19
+ output:
20
+ url: ./assets/image_0_0.png
21
+ - text: 'ggn_style painting of a hipster making a chair'
22
+ parameters:
23
+ negative_prompt: 'blurry, cropped, ugly'
24
+ output:
25
+ url: ./assets/image_1_0.png
26
+ - text: 'ggn_style painting of a hamster'
27
+ parameters:
28
+ negative_prompt: 'blurry, cropped, ugly'
29
+ output:
30
+ url: ./assets/image_2_0.png
31
+ - text: 'in the style of ggn_style, A painting of a woman stands near the water holding an object. Another woman swims in the water. A tree with twisted branches is at the foreground left. Flowers and vegetation are near the lower center. Hills with vegetation are in the background. Text ''Parau na te Varua ino'' at the bottom left and artist''s signature at the lower right.'
32
+ parameters:
33
+ negative_prompt: 'blurry, cropped, ugly'
34
+ output:
35
+ url: ./assets/image_3_0.png
36
+ - text: 'ggn_style, A seated woman with long dark hair is depicted in a front-facing view. She is wearing a dress with a white collar and appears to be in her thirties. Her hands are on her lap. Green leaves and flowers surround her.'
37
+ parameters:
38
+ negative_prompt: 'blurry, cropped, ugly'
39
+ output:
40
+ url: ./assets/image_4_0.png
41
+ - text: 'ggm_style, tropical fruits and flowers, bold outlines, non-naturalistic colors, decorative composition'
42
+ parameters:
43
+ negative_prompt: 'blurry, cropped, ugly'
44
+ output:
45
+ url: ./assets/image_5_0.png
46
+ - text: 'ggn_style, A nude woman sits on a patterned cloth with crossed legs. She holds a small object in her hand. A low table with fruit is in front of her. Pink flowers are in the background, with mountains and palm trees beyond. Text is in the bottom left corner.'
47
+ parameters:
48
+ negative_prompt: 'blurry, cropped, ugly'
49
+ output:
50
+ url: ./assets/image_6_0.png
51
+ ---
52
+
53
+ # paul-gaugin-sdxl-lora-05
54
+
55
+ This is a LyCORIS adapter derived from [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0).
56
+
57
+
58
+ The main validation prompt used during training was:
59
+
60
+
61
+
62
+ ```
63
+ ggn_style, A nude woman sits on a patterned cloth with crossed legs. She holds a small object in her hand. A low table with fruit is in front of her. Pink flowers are in the background, with mountains and palm trees beyond. Text is in the bottom left corner.
64
+ ```
65
+
66
+ ## Validation settings
67
+ - CFG: `4.2`
68
+ - CFG Rescale: `0.0`
69
+ - Steps: `20`
70
+ - Sampler: `None`
71
+ - Seed: `42`
72
+ - Resolution: `1024x1024`
73
+
74
+ Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
75
+
76
+ You can find some example images in the following gallery:
77
+
78
+
79
+ <Gallery />
80
+
81
+ The text encoder **was not** trained.
82
+ You may reuse the base model text encoder for inference.
83
+
84
+
85
+ ## Training settings
86
+
87
+ - Training epochs: 0
88
+ - Training steps: 100
89
+ - Learning rate: 0.0005
90
+ - Effective batch size: 16
91
+ - Micro-batch size: 16
92
+ - Gradient accumulation steps: 1
93
+ - Number of GPUs: 1
94
+ - Prediction type: epsilon
95
+ - Rescaled betas zero SNR: False
96
+ - Optimizer: optimi-lionweight_decay=1e-3
97
+ - Precision: Pure BF16
98
+ - Quantised: Yes: int8-quanto
99
+ - Xformers: Not used
100
+ - LyCORIS Config:
101
+ ```json
102
+ {
103
+ "algo": "lokr",
104
+ "multiplier": 1.0,
105
+ "linear_dim": 10000,
106
+ "linear_alpha": 1,
107
+ "factor": 16,
108
+ "apply_preset": {
109
+ "target_module": [
110
+ "Attention",
111
+ "FeedForward"
112
+ ],
113
+ "module_algo_map": {
114
+ "Attention": {
115
+ "factor": 16
116
+ },
117
+ "FeedForward": {
118
+ "factor": 8
119
+ }
120
+ }
121
+ }
122
+ }
123
+ ```
124
+
125
+ ## Datasets
126
+
127
+ ### paul-gaugin-sdxl-512
128
+ - Repeats: 10
129
+ - Total number of images: 85
130
+ - Total number of aspect buckets: 8
131
+ - Resolution: 0.262144 megapixels
132
+ - Cropped: False
133
+ - Crop style: None
134
+ - Crop aspect: None
135
+ ### paul-gaugin-sdxl-1024
136
+ - Repeats: 10
137
+ - Total number of images: 85
138
+ - Total number of aspect buckets: 17
139
+ - Resolution: 1.048576 megapixels
140
+ - Cropped: False
141
+ - Crop style: None
142
+ - Crop aspect: None
143
+ ### paul-gaugin-sdxl-512-crop
144
+ - Repeats: 10
145
+ - Total number of images: 85
146
+ - Total number of aspect buckets: 1
147
+ - Resolution: 0.262144 megapixels
148
+ - Cropped: True
149
+ - Crop style: random
150
+ - Crop aspect: square
151
+ ### paul-gaugin-sdxl-1024-crop
152
+ - Repeats: 10
153
+ - Total number of images: 85
154
+ - Total number of aspect buckets: 1
155
+ - Resolution: 1.048576 megapixels
156
+ - Cropped: True
157
+ - Crop style: random
158
+ - Crop aspect: square
159
+
160
+
161
+ ## Inference
162
+
163
+
164
+ ```python
165
+ import torch
166
+ from diffusers import DiffusionPipeline
167
+ from lycoris import create_lycoris_from_weights
168
+
169
+ model_id = 'stabilityai/stable-diffusion-xl-base-1.0'
170
+ adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
171
+ lora_scale = 1.0
172
+ wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
173
+ wrapper.merge_to()
174
+
175
+ prompt = "ggn_style, A nude woman sits on a patterned cloth with crossed legs. She holds a small object in her hand. A low table with fruit is in front of her. Pink flowers are in the background, with mountains and palm trees beyond. Text is in the bottom left corner."
176
+ negative_prompt = 'blurry, cropped, ugly'
177
+ pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
178
+ image = pipeline(
179
+ prompt=prompt,
180
+ negative_prompt=negative_prompt,
181
+ num_inference_steps=20,
182
+ generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
183
+ width=1024,
184
+ height=1024,
185
+ guidance_scale=4.2,
186
+ guidance_rescale=0.0,
187
+ ).images[0]
188
+ image.save("output.png", format="PNG")
189
+ ```
190
+