jimchoi commited on
Commit
45565c5
·
verified ·
1 Parent(s): d5eeb34

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +6 -26
README.md CHANGED
@@ -12,27 +12,7 @@ tags:
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: 'your prompt to validate on'
22
- parameters:
23
- negative_prompt: 'blurry, cropped, ugly'
24
- output:
25
- url: ./assets/image_1_0.png
26
- - text: 'another prompt to validate on'
27
- parameters:
28
- negative_prompt: 'blurry, cropped, ugly'
29
- output:
30
- url: ./assets/image_2_0.png
31
- - text: 'A photo-realistic image of a cat girl'
32
- parameters:
33
- negative_prompt: 'blurry, cropped, ugly'
34
- output:
35
- url: ./assets/image_3_0.png
36
  ---
37
 
38
  # simpletuner-lora
@@ -42,7 +22,7 @@ This is a LyCORIS adapter derived from [stabilityai/stable-diffusion-3-medium-di
42
 
43
  The main validation prompt used during training was:
44
  ```
45
- A photo-realistic image of a cat girl
46
  ```
47
 
48
 
@@ -57,7 +37,7 @@ A photo-realistic image of a cat girl
57
 
58
  Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
59
 
60
- You can find some example images in the following gallery:
61
 
62
 
63
  <Gallery />
@@ -69,7 +49,7 @@ You may reuse the base model text encoder for inference.
69
  ## Training settings
70
 
71
  - Training epochs: 1
72
- - Training steps: 1000
73
  - Learning rate: 0.0001
74
  - Learning rate schedule: polynomial
75
  - Warmup steps: 100
@@ -115,7 +95,7 @@ You may reuse the base model text encoder for inference.
115
  ### wikiart_sargent
116
  - Repeats: 0
117
  - Total number of images: 920
118
- - Total number of aspect buckets: 8
119
  - Resolution: 1.048576 megapixels
120
  - Cropped: False
121
  - Crop style: None
@@ -156,7 +136,7 @@ lora_scale = 1.0
156
  wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
157
  wrapper.merge_to()
158
 
159
- prompt = "A photo-realistic image of a cat girl"
160
  negative_prompt = 'blurry, cropped, ugly'
161
 
162
  ## Optional: quantise the model to save on vram.
 
12
  - template:sd-lora
13
  - lycoris
14
  inference: true
15
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  ---
17
 
18
  # simpletuner-lora
 
22
 
23
  The main validation prompt used during training was:
24
  ```
25
+ Sun Wukong, the Monkey King from 'Black Myth: Wukong', clad in battle-damaged golden armor, wearing a phoenix-feathered purple golden crown. His eyes gleam with an indomitable spirit of battle. He wields the Ruyi Jingu Bang, its golden body shimmering with light, standing amidst an ancient battlefield shrouded in demonic fog, surrounded by shattered battle flags and scattered weapons. Wukong's fur billows in the wild wind of the battlefield, his muscular physique clearly defined, showcasing his unparalleled strength and agility.
26
  ```
27
 
28
 
 
37
 
38
  Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
39
 
40
+
41
 
42
 
43
  <Gallery />
 
49
  ## Training settings
50
 
51
  - Training epochs: 1
52
+ - Training steps: 1200
53
  - Learning rate: 0.0001
54
  - Learning rate schedule: polynomial
55
  - Warmup steps: 100
 
95
  ### wikiart_sargent
96
  - Repeats: 0
97
  - Total number of images: 920
98
+ - Total number of aspect buckets: 6
99
  - Resolution: 1.048576 megapixels
100
  - Cropped: False
101
  - Crop style: None
 
136
  wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
137
  wrapper.merge_to()
138
 
139
+ prompt = "Sun Wukong, the Monkey King from 'Black Myth: Wukong', clad in battle-damaged golden armor, wearing a phoenix-feathered purple golden crown. His eyes gleam with an indomitable spirit of battle. He wields the Ruyi Jingu Bang, its golden body shimmering with light, standing amidst an ancient battlefield shrouded in demonic fog, surrounded by shattered battle flags and scattered weapons. Wukong's fur billows in the wild wind of the battlefield, his muscular physique clearly defined, showcasing his unparalleled strength and agility."
140
  negative_prompt = 'blurry, cropped, ugly'
141
 
142
  ## Optional: quantise the model to save on vram.