wang1111magic commited on
Commit
7c761a7
1 Parent(s): 4d7c23c

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +118 -0
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ base_model: "black-forest-labs/FLUX.1-dev"
4
+ tags:
5
+ - stable-diffusion
6
+ - stable-diffusion-diffusers
7
+ - text-to-image
8
+ - diffusers
9
+ - simpletuner
10
+ - lora
11
+ - template:sd-lora
12
+ inference: true
13
+ widget:
14
+ - text: 'unconditional (blank prompt)'
15
+ parameters:
16
+ negative_prompt: ''''
17
+ output:
18
+ url: ./assets/image_0_0.png
19
+ - text: 'qxxy style,Your_name,best quality,This is a high-resolution anime still featuring a young male character with black hair wearing a white school uniform with a green and yellow tie. He appears startled or surprised, with his mouth slightly open and a hand to his cheek, as though he has just witnessed something unexpected. The setting seems to be a cafe with a modern, airy interior, as indicated by the wooden trusses on the ceiling and hanging industrial-style lamps. The daylight filters through the windows, creating a bright atmosphere. No other characters are visible, which places the entire focus on the young man''s reaction.,1boy, necktie, male_focus, solo, school_uniform, indoors, striped_necktie, green_necktie, short_sleeves, shirt, upper_body'
20
+ parameters:
21
+ negative_prompt: ''''
22
+ output:
23
+ url: ./assets/image_1_0.png
24
+ ---
25
+
26
+ # 0821flux-Your-name-lora64lora-training
27
+
28
+ This is a LoRA derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev).
29
+
30
+
31
+
32
+ The main validation prompt used during training was:
33
+
34
+
35
+
36
+ ```
37
+ qxxy style,Your_name,best quality,This is a high-resolution anime still featuring a young male character with black hair wearing a white school uniform with a green and yellow tie. He appears startled or surprised, with his mouth slightly open and a hand to his cheek, as though he has just witnessed something unexpected. The setting seems to be a cafe with a modern, airy interior, as indicated by the wooden trusses on the ceiling and hanging industrial-style lamps. The daylight filters through the windows, creating a bright atmosphere. No other characters are visible, which places the entire focus on the young man's reaction.,1boy, necktie, male_focus, solo, school_uniform, indoors, striped_necktie, green_necktie, short_sleeves, shirt, upper_body
38
+ ```
39
+
40
+ ## Validation settings
41
+ - CFG: `3.5`
42
+ - CFG Rescale: `0.0`
43
+ - Steps: `20`
44
+ - Sampler: `None`
45
+ - Seed: `42`
46
+ - Resolution: `1024`
47
+
48
+ Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
49
+
50
+ You can find some example images in the following gallery:
51
+
52
+
53
+ <Gallery />
54
+
55
+ The text encoder **was not** trained.
56
+ You may reuse the base model text encoder for inference.
57
+
58
+
59
+ ## Training settings
60
+
61
+ - Training epochs: 0
62
+ - Training steps: 300
63
+ - Learning rate: 0.0003
64
+ - Effective batch size: 2
65
+ - Micro-batch size: 2
66
+ - Gradient accumulation steps: 1
67
+ - Number of GPUs: 1
68
+ - Prediction type: flow-matching
69
+ - Rescaled betas zero SNR: False
70
+ - Optimizer: adamw_bf16
71
+ - Precision: bf16
72
+ - Quantised: Yes: int8-quanto
73
+ - Xformers: Not used
74
+ - LoRA Rank: 64
75
+ - LoRA Alpha: None
76
+ - LoRA Dropout: 0.1
77
+ - LoRA initialisation style: default
78
+
79
+
80
+ ## Datasets
81
+
82
+ ### qxxy style
83
+ - Repeats: 10
84
+ - Total number of images: 488
85
+ - Total number of aspect buckets: 1
86
+ - Resolution: 1024 px
87
+ - Cropped: True
88
+ - Crop style: center
89
+ - Crop aspect: square
90
+
91
+
92
+ ## Inference
93
+
94
+
95
+ ```python
96
+ import torch
97
+ from diffusers import DiffusionPipeline
98
+
99
+ model_id = 'black-forest-labs/FLUX.1-dev'
100
+ adapter_id = 'wang1111magic/0821flux-Your-name-lora64lora-training'
101
+ pipeline = DiffusionPipeline.from_pretrained(model_id)
102
+ pipeline.load_lora_weights(adapter_id)
103
+
104
+ prompt = "qxxy style,Your_name,best quality,This is a high-resolution anime still featuring a young male character with black hair wearing a white school uniform with a green and yellow tie. He appears startled or surprised, with his mouth slightly open and a hand to his cheek, as though he has just witnessed something unexpected. The setting seems to be a cafe with a modern, airy interior, as indicated by the wooden trusses on the ceiling and hanging industrial-style lamps. The daylight filters through the windows, creating a bright atmosphere. No other characters are visible, which places the entire focus on the young man's reaction.,1boy, necktie, male_focus, solo, school_uniform, indoors, striped_necktie, green_necktie, short_sleeves, shirt, upper_body"
105
+
106
+
107
+ pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
108
+ image = pipeline(
109
+ prompt=prompt,
110
+ num_inference_steps=20,
111
+ generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
112
+ width=1024,
113
+ height=1024,
114
+ guidance_scale=3.5,
115
+ ).images[0]
116
+ image.save("output.png", format="PNG")
117
+ ```
118
+