pixelass commited on
Commit
3f656c9
0 Parent(s):

initial commit

Browse files
Files changed (2) hide show
  1. .gitattributes +55 -0
  2. README.md +121 -0
.gitattributes ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.lz4 filter=lfs diff=lfs merge=lfs -text
12
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
13
+ *.model filter=lfs diff=lfs merge=lfs -text
14
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
15
+ *.npy filter=lfs diff=lfs merge=lfs -text
16
+ *.npz filter=lfs diff=lfs merge=lfs -text
17
+ *.onnx filter=lfs diff=lfs merge=lfs -text
18
+ *.ot filter=lfs diff=lfs merge=lfs -text
19
+ *.parquet filter=lfs diff=lfs merge=lfs -text
20
+ *.pb filter=lfs diff=lfs merge=lfs -text
21
+ *.pickle filter=lfs diff=lfs merge=lfs -text
22
+ *.pkl filter=lfs diff=lfs merge=lfs -text
23
+ *.pt filter=lfs diff=lfs merge=lfs -text
24
+ *.pth filter=lfs diff=lfs merge=lfs -text
25
+ *.rar filter=lfs diff=lfs merge=lfs -text
26
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
27
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
29
+ *.tar filter=lfs diff=lfs merge=lfs -text
30
+ *.tflite filter=lfs diff=lfs merge=lfs -text
31
+ *.tgz filter=lfs diff=lfs merge=lfs -text
32
+ *.wasm filter=lfs diff=lfs merge=lfs -text
33
+ *.xz filter=lfs diff=lfs merge=lfs -text
34
+ *.zip filter=lfs diff=lfs merge=lfs -text
35
+ *.zst filter=lfs diff=lfs merge=lfs -text
36
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
37
+ # Audio files - uncompressed
38
+ *.pcm filter=lfs diff=lfs merge=lfs -text
39
+ *.sam filter=lfs diff=lfs merge=lfs -text
40
+ *.raw filter=lfs diff=lfs merge=lfs -text
41
+ # Audio files - compressed
42
+ *.aac filter=lfs diff=lfs merge=lfs -text
43
+ *.flac filter=lfs diff=lfs merge=lfs -text
44
+ *.mp3 filter=lfs diff=lfs merge=lfs -text
45
+ *.ogg filter=lfs diff=lfs merge=lfs -text
46
+ *.wav filter=lfs diff=lfs merge=lfs -text
47
+ # Image files - uncompressed
48
+ *.bmp filter=lfs diff=lfs merge=lfs -text
49
+ *.gif filter=lfs diff=lfs merge=lfs -text
50
+ *.png filter=lfs diff=lfs merge=lfs -text
51
+ *.tiff filter=lfs diff=lfs merge=lfs -text
52
+ # Image files - compressed
53
+ *.jpg filter=lfs diff=lfs merge=lfs -text
54
+ *.jpeg filter=lfs diff=lfs merge=lfs -text
55
+ *.webp filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - text-to-image
4
+ - stable-diffusion
5
+ - lora
6
+ - diffusers
7
+ - template:sd-lora
8
+ widget:
9
+ - text: >-
10
+ a used leather dog, made of worn leather, torn edges, weathered, prominent
11
+ stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
12
+ output:
13
+ url: images/00089-3023579477.png
14
+ - text: >-
15
+ a used leather cat, made of worn leather, torn edges, weathered, prominent
16
+ stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
17
+ output:
18
+ url: images/00090-3023579477.png
19
+ - text: >-
20
+ a used leather spider, made of worn leather, torn edges, weathered,
21
+ prominent stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
22
+ output:
23
+ url: images/00091-3023579477.png
24
+ - text: >-
25
+ a used leather dinosaur, made of worn leather, torn edges, weathered,
26
+ prominent stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
27
+ output:
28
+ url: images/00092-3023579477.png
29
+ - text: >-
30
+ a used leather beetle, made of worn leather, torn edges, weathered,
31
+ prominent stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
32
+ output:
33
+ url: images/00093-3023579477.png
34
+ - text: >-
35
+ a used leather grasshopper, made of worn leather, torn edges, weathered,
36
+ prominent stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
37
+ output:
38
+ url: images/00094-3023579477.png
39
+ - text: >-
40
+ a used leather butterfly, made of worn leather, torn edges, weathered,
41
+ prominent stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
42
+ output:
43
+ url: images/00095-3023579477.png
44
+ - text: >-
45
+ a used leather bird, made of worn leather, torn edges, weathered, prominent
46
+ stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
47
+ output:
48
+ url: images/00096-3023579477.png
49
+ - text: >-
50
+ a used leather astronaut, made of worn leather, torn edges, weathered,
51
+ prominent stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
52
+ output:
53
+ url: images/00098-3023579477.png
54
+ - text: >-
55
+ a used leather monkey, made of worn leather, torn edges, weathered,
56
+ prominent stitching, scruffs, scratches <lora:used_leather_sdxl_v1:1>
57
+ output:
58
+ url: images/00099-3023579477.png
59
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
60
+ instance_prompt: used leather
61
+ license: cc-by-nc-4.0
62
+ ---
63
+ # Used LLeather LoRA SDXL
64
+
65
+ <Gallery />
66
+
67
+ ## Model description
68
+
69
+ # Model Card for LoRA on Used Leather Dataset
70
+
71
+ ## Model Overview
72
+
73
+ This model card represents a LoRA (Low-Rank Adaptation) model trained on the Used Leather Dataset, sourced from [Hugging Face Datasets](https:&#x2F;&#x2F;huggingface.co&#x2F;datasets&#x2F;Blib-la&#x2F;used_leather_dataset). The model specializes in generating images of used, worn, and weathered leather textures.
74
+
75
+ ## Training Configuration
76
+
77
+ - **Dataset**: Used Leather Dataset
78
+ - **Epochs**: 17
79
+ - **Number of Images**: 50
80
+ - **Repeats per Image**: 10 (Each image was used 10 times during training)
81
+ - **Optimizer**: DAdaptAdam (An optimizer designed for efficient and effective AI model training)
82
+ - **Precision**: bf16 (Using bf16 precision for training, balancing performance and memory efficiency)
83
+ - **Main Trigger**: The model is fine-tuned to recognize and generate images with the theme &quot;used leather.&quot;
84
+ - **Xformers**: Enabled (Utilizing xformers for efficient transformer models)
85
+ - **Captioning Method**: GPT-Vision (Using GPT-Vision for generating descriptive captions for training images), optimized for token shuffling
86
+ - **Base Model**: Stable Diffusion XL 1.0 (The model is built upon the foundation of Stable Diffusion XL 1.0, known for its robustness in image generation tasks)
87
+
88
+ ## Model Usage
89
+
90
+ This LoRA model is specifically trained to replicate various conditions of leather, such as used, scuffed, scratched, and weathered textures.
91
+
92
+ ## Performance and Limitations
93
+
94
+ - **Performance**: The model demonstrates proficiency in capturing the intricate details and variations in used leather textures.
95
+ - **Limitations**: As the training dataset comprises only 50 images, the model may have limitations in generating certain objects.
96
+
97
+ ## Ethical Considerations
98
+
99
+ - **Intended Use**: This model is intended for non-commercial applications, particularly in design, restoration, and educational fields.
100
+ - **Bias and Fairness**: Users should be aware of the potential biases inherent in the dataset. It reflects the specific types of leather and conditions present in the original images.
101
+
102
+ ## Licensing
103
+
104
+ - **Model License**: The model is available for non-commercial use under the same Creative Commons Attribution-NonCommercial 2.0 Generic (CC BY-NC 2.0) license as the training dataset.
105
+ - **Dataset License**: The Used Leather Dataset is licensed under CC BY-NC 2.0.
106
+
107
+ ## Contributions and Feedback
108
+
109
+ We welcome feedback and contributions to improve the model further. If you have suggestions or would like to contribute to the model&#39;s development, please reach out through the model&#39;s Hugging Face page.
110
+
111
+
112
+ ## Trigger words
113
+
114
+ You should use `used leather` to trigger the image generation.
115
+
116
+
117
+ ## Download model
118
+
119
+ Weights for this model are available in Safetensors format.
120
+
121
+ [Download](/pixelass/used_leather_lora_sdxl/tree/main) them in the Files & versions tab.