Update README.md
Browse files
README.md
CHANGED
|
@@ -152,7 +152,23 @@ grid
|
|
| 152 |
|
| 153 |
Download this script: [SDXL DreamBooth-LoRA_Fine-Tune.ipynb](https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/SDXL_DreamBooth_LoRA_Fine-Tune.ipynb)
|
| 154 |
|
| 155 |
-
You need to create a local folder ```leaf_concept_dir_SDXL``` and add the leaf images (provided in this repository, see subfolder)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
|
| 157 |
The code will automatically download the training script.
|
| 158 |
|
|
@@ -161,14 +177,16 @@ The training script can handle custom prompts associated with each image, which
|
|
| 161 |
For instance, for the images used here, they are:
|
| 162 |
|
| 163 |
```raw
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
|
|
|
|
|
|
| 172 |
```
|
| 173 |
|
| 174 |
Training then proceeds as:
|
|
@@ -222,7 +240,7 @@ with open(f'{instance_data_dir}metadata.jsonl', 'w') as outfile:
|
|
| 222 |
```
|
| 223 |
This produces a JSON file in the ```instance_data_dir``` directory:
|
| 224 |
|
| 225 |
-
```
|
| 226 |
{"file_name": "0.jpeg", "prompt": "<leaf microstructure>, a close up of a green plant with a lot of small holes"}
|
| 227 |
{"file_name": "1.jpeg", "prompt": "<leaf microstructure>, a close up of a leaf with a small insect on it"}
|
| 228 |
{"file_name": "2.jpeg", "prompt": "<leaf microstructure>, a close up of a plant with a lot of green leaves"}
|
|
|
|
| 152 |
|
| 153 |
Download this script: [SDXL DreamBooth-LoRA_Fine-Tune.ipynb](https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/SDXL_DreamBooth_LoRA_Fine-Tune.ipynb)
|
| 154 |
|
| 155 |
+
You need to create a local folder ```leaf_concept_dir_SDXL``` and add the leaf images (provided in this repository, see subfolder), like so:
|
| 156 |
+
|
| 157 |
+
```raw
|
| 158 |
+
mkdir leaf_concept_dir_SDXL
|
| 159 |
+
cd leaf_concept_dir_SDXL
|
| 160 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/0.jpeg
|
| 161 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/1.jpeg
|
| 162 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/2.jpeg
|
| 163 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/3.jpeg
|
| 164 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/87.jpg
|
| 165 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/87.jpg
|
| 166 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/88.jpg
|
| 167 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/90.jpg
|
| 168 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/91.jpg
|
| 169 |
+
wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/94.jpg
|
| 170 |
+
cd ..
|
| 171 |
+
```
|
| 172 |
|
| 173 |
The code will automatically download the training script.
|
| 174 |
|
|
|
|
| 177 |
For instance, for the images used here, they are:
|
| 178 |
|
| 179 |
```raw
|
| 180 |
+
{"file_name": "0.jpeg", "prompt": "<leaf microstructure>, a close up of a green plant with a lot of small holes"}
|
| 181 |
+
{"file_name": "1.jpeg", "prompt": "<leaf microstructure>, a close up of a leaf with a small insect on it"}
|
| 182 |
+
{"file_name": "2.jpeg", "prompt": "<leaf microstructure>, a close up of a plant with a lot of green leaves"}
|
| 183 |
+
{"file_name": "3.jpeg", "prompt": "<leaf microstructure>, a close up of a leaf with a yellow substance in it"}
|
| 184 |
+
{"file_name": "87.jpg", "prompt": "<leaf microstructure>, a close up of a green plant with a yellow light"}
|
| 185 |
+
{"file_name": "88.jpg", "prompt": "<leaf microstructure>, a close up of a green plant with a white center"}
|
| 186 |
+
{"file_name": "90.jpg", "prompt": "<leaf microstructure>, arafed leaf with a white line on the center"}
|
| 187 |
+
{"file_name": "91.jpg", "prompt": "<leaf microstructure>, arafed image of a green leaf with a white spot"}
|
| 188 |
+
{"file_name": "92.jpg", "prompt": "<leaf microstructure>, a close up of a leaf with a yellow light shining through it"}
|
| 189 |
+
{"file_name": "94.jpg", "prompt": "<leaf microstructure>, arafed image of a green plant with a yellow cross"}
|
| 190 |
```
|
| 191 |
|
| 192 |
Training then proceeds as:
|
|
|
|
| 240 |
```
|
| 241 |
This produces a JSON file in the ```instance_data_dir``` directory:
|
| 242 |
|
| 243 |
+
```raw
|
| 244 |
{"file_name": "0.jpeg", "prompt": "<leaf microstructure>, a close up of a green plant with a lot of small holes"}
|
| 245 |
{"file_name": "1.jpeg", "prompt": "<leaf microstructure>, a close up of a leaf with a small insect on it"}
|
| 246 |
{"file_name": "2.jpeg", "prompt": "<leaf microstructure>, a close up of a plant with a lot of green leaves"}
|