elasticBottle commited on
Commit
6d68c20
·
verified ·
1 Parent(s): 2ab74a1

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +193 -0
README.md ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: "black-forest-labs/FLUX.1-dev"
4
+ tags:
5
+ - flux
6
+ - flux-diffusers
7
+ - text-to-image
8
+ - diffusers
9
+ - simpletuner
10
+ - safe-for-work
11
+ - lora
12
+ - template:sd-lora
13
+ - standard
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: 'TIGER_THERMOS_BOTTLE. A breathtaking anime-style portrait of a gray thermos bottle, capturing its essence with vibrant colors and expressive features. There is a black "TIGER" logo at the bottom of the thermos bottle'
22
+ parameters:
23
+ negative_prompt: 'blurry, cropped, ugly'
24
+ output:
25
+ url: ./assets/image_1_0.png
26
+ - text: 'TIGER_THERMOS_BOTTLE. A high-quality, detailed photograph of a gray thermos bottle next to a sous-chef, immersed in the art of culinary creation. There is a black "TIGER" logo at the bottom of the thermos bottle'
27
+ parameters:
28
+ negative_prompt: 'blurry, cropped, ugly'
29
+ output:
30
+ url: ./assets/image_2_0.png
31
+ - text: 'TIGER_THERMOS_BOTTLE. A lifelike and intimate portrait of a blue thermos bottle, showcasing its unique personality and charm. There is a black "TIGER" logo at the bottom of the thermos bottle'
32
+ parameters:
33
+ negative_prompt: 'blurry, cropped, ugly'
34
+ output:
35
+ url: ./assets/image_3_0.png
36
+ - text: 'TIGER_THERMOS_BOTTLE. A cinematic, visually stunning photo ofa gray thermos bottle, emphasizing her dramatic and captivating presence. There is a black "TIGER" logo at the bottom of the thermos bottle'
37
+ parameters:
38
+ negative_prompt: 'blurry, cropped, ugly'
39
+ output:
40
+ url: ./assets/image_4_0.png
41
+ - text: 'TIGER_THERMOS_BOTTLE. An elegant and timeless portrait of a gray thermos bottle, exuding grace and sophistication. There is a black "TIGER" logo at the bottom of the thermos bottle'
42
+ parameters:
43
+ negative_prompt: 'blurry, cropped, ugly'
44
+ output:
45
+ url: ./assets/image_5_0.png
46
+ - text: 'TIGER_THERMOS_BOTTLE. A dynamic and adventurous photo of a gray thermos bottle, captured in an exciting, action-filled moment. There is a black "TIGER" logo at the bottom of the thermos bottle'
47
+ parameters:
48
+ negative_prompt: 'blurry, cropped, ugly'
49
+ output:
50
+ url: ./assets/image_6_0.png
51
+ - text: 'TIGER_THERMOS_BOTTLE. A mysterious and enigmatic portrait of a purple thermos bottle, shrouded in shadows and intrigue. There is a black "TIGER" logo at the bottom of the thermos bottle'
52
+ parameters:
53
+ negative_prompt: 'blurry, cropped, ugly'
54
+ output:
55
+ url: ./assets/image_7_0.png
56
+ - text: 'TIGER_THERMOS_BOTTLE. A vintage-style portrait of a gray thermos bottle, evoking the charm and nostalgia of a bygone era. There is a black "TIGER" logo at the bottom of the thermos bottle'
57
+ parameters:
58
+ negative_prompt: 'blurry, cropped, ugly'
59
+ output:
60
+ url: ./assets/image_8_0.png
61
+ - text: 'TIGER_THERMOS_BOTTLE. An artistic and abstract representation of a yellow thermos bottle, blending creativity with visual storytelling. There is a black "TIGER" logo at the bottom of the thermos bottle'
62
+ parameters:
63
+ negative_prompt: 'blurry, cropped, ugly'
64
+ output:
65
+ url: ./assets/image_9_0.png
66
+ - text: 'TIGER_THERMOS_BOTTLE. A futuristic and cutting-edge portrayal of a pink gray thermos bottle, set against a backdrop of advanced technology. There is a black "TIGER" logo at the bottom of the thermos bottle'
67
+ parameters:
68
+ negative_prompt: 'blurry, cropped, ugly'
69
+ output:
70
+ url: ./assets/image_10_0.png
71
+ - text: 'a beautifully crafted portrait of a woman, highlighting her natural beauty and unique features'
72
+ parameters:
73
+ negative_prompt: 'blurry, cropped, ugly'
74
+ output:
75
+ url: ./assets/image_11_0.png
76
+ - text: 'a powerful and striking portrait of a man, capturing his strength and character'
77
+ parameters:
78
+ negative_prompt: 'blurry, cropped, ugly'
79
+ output:
80
+ url: ./assets/image_12_0.png
81
+ - text: 'a playful and spirited portrait of a boy, capturing youthful energy and innocence'
82
+ parameters:
83
+ negative_prompt: 'blurry, cropped, ugly'
84
+ output:
85
+ url: ./assets/image_13_0.png
86
+ - text: 'a charming and vibrant portrait of a girl, emphasizing her bright personality and joy'
87
+ parameters:
88
+ negative_prompt: 'blurry, cropped, ugly'
89
+ output:
90
+ url: ./assets/image_14_0.png
91
+ - text: 'a heartwarming and cohesive family portrait, showcasing the bonds and connections between loved ones'
92
+ parameters:
93
+ negative_prompt: 'blurry, cropped, ugly'
94
+ output:
95
+ url: ./assets/image_15_0.png
96
+ - text: 'TIGER_THERMOS_BOTTLE. A photo-realistic image of a gray thermos bottle on a while tabletop with mountains in the background. There is a black "TIGER" logo at the bottom of the grey thermos bottle'
97
+ parameters:
98
+ negative_prompt: 'blurry, cropped, ugly'
99
+ output:
100
+ url: ./assets/image_16_0.png
101
+ ---
102
+
103
+ # tiger-thermos-lora
104
+
105
+ This is a standard PEFT LoRA derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev).
106
+
107
+
108
+ The main validation prompt used during training was:
109
+
110
+
111
+
112
+ ```
113
+ TIGER_THERMOS_BOTTLE. A photo-realistic image of a gray thermos bottle on a while tabletop with mountains in the background. There is a black "TIGER" logo at the bottom of the grey thermos bottle
114
+ ```
115
+
116
+ ## Validation settings
117
+ - CFG: `3.5`
118
+ - CFG Rescale: `0.0`
119
+ - Steps: `20`
120
+ - Sampler: `None`
121
+ - Seed: `42`
122
+ - Resolution: `512x512`
123
+
124
+ Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
125
+
126
+ You can find some example images in the following gallery:
127
+
128
+
129
+ <Gallery />
130
+
131
+ The text encoder **was not** trained.
132
+ You may reuse the base model text encoder for inference.
133
+
134
+
135
+ ## Training settings
136
+
137
+ - Training epochs: 83
138
+ - Training steps: 500
139
+ - Learning rate: 0.00012
140
+ - Effective batch size: 2
141
+ - Micro-batch size: 2
142
+ - Gradient accumulation steps: 1
143
+ - Number of GPUs: 1
144
+ - Prediction type: flow-matching
145
+ - Rescaled betas zero SNR: False
146
+ - Optimizer: adamw_bf16
147
+ - Precision: Pure BF16
148
+ - Quantised: No
149
+ - Xformers: Not used
150
+ - LoRA Rank: 4
151
+ - LoRA Alpha: None
152
+ - LoRA Dropout: 0.1
153
+ - LoRA initialisation style: default
154
+
155
+
156
+ ## Datasets
157
+
158
+ ### default_dataset
159
+ - Repeats: 0
160
+ - Total number of images: 12
161
+ - Total number of aspect buckets: 1
162
+ - Resolution: 0.147456 megapixels
163
+ - Cropped: True
164
+ - Crop style: center
165
+ - Crop aspect: square
166
+
167
+
168
+ ## Inference
169
+
170
+
171
+ ```python
172
+ import torch
173
+ from diffusers import DiffusionPipeline
174
+
175
+ model_id = 'black-forest-labs/FLUX.1-dev'
176
+ adapter_id = 'elasticBottle/tiger-thermos-lora'
177
+ pipeline = DiffusionPipeline.from_pretrained(model_id)
178
+ pipeline.load_lora_weights(adapter_id)
179
+
180
+ prompt = "TIGER_THERMOS_BOTTLE. A photo-realistic image of a gray thermos bottle on a while tabletop with mountains in the background. There is a black "TIGER" logo at the bottom of the grey thermos bottle"
181
+
182
+ pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
183
+ image = pipeline(
184
+ prompt=prompt,
185
+ num_inference_steps=20,
186
+ generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
187
+ width=512,
188
+ height=512,
189
+ guidance_scale=3.5,
190
+ ).images[0]
191
+ image.save("output.png", format="PNG")
192
+ ```
193
+