Update README.md
Browse files
README.md
CHANGED
|
@@ -33,11 +33,11 @@ pip install -U diffusers
|
|
| 33 |
|
| 34 |
These are LoRA adaption weights for the FLUX.1 [dev] model (```black-forest-labs/FLUX.1-dev```). The base model is, and you must first get access to it before loading this LoRA adapter.
|
| 35 |
|
| 36 |
-
This LoRA adapter has rank=64 and alpha=64, trained for
|
| 37 |
|
| 38 |
## Trigger keywords
|
| 39 |
|
| 40 |
-
The model was fine-tuned with a set of ~1,600 images of biological materials, structures, shapes and other images of nature, using the keyword
|
| 41 |
|
| 42 |
You should use \<bioinspired\> to trigger these features during image generation.
|
| 43 |
|
|
@@ -139,6 +139,7 @@ grid
|
|
| 139 |
|
| 140 |
|
| 141 |

|
|
|
|
| 142 |
Image generation - Example #2:
|
| 143 |
|
| 144 |
```python
|
|
@@ -160,6 +161,28 @@ grid
|
|
| 160 |
|
| 161 |

|
| 162 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 163 |
|
| 164 |
```bibtext
|
| 165 |
@article{BioinspiredFluxBuehler2024,
|
|
|
|
| 33 |
|
| 34 |
These are LoRA adaption weights for the FLUX.1 [dev] model (```black-forest-labs/FLUX.1-dev```). The base model is, and you must first get access to it before loading this LoRA adapter.
|
| 35 |
|
| 36 |
+
This LoRA adapter has rank=64 and alpha=64, trained for 16,000 steps. Earlier checkpoints are available in this repository as well (you can load these via the ```adapter``` parameter, see example below).
|
| 37 |
|
| 38 |
## Trigger keywords
|
| 39 |
|
| 40 |
+
The model was fine-tuned with a set of ~1,600 images of biological materials, structures, shapes and other images of nature, using the keyword \<bioinspired\>.
|
| 41 |
|
| 42 |
You should use \<bioinspired\> to trigger these features during image generation.
|
| 43 |
|
|
|
|
| 139 |
|
| 140 |
|
| 141 |

|
| 142 |
+
|
| 143 |
Image generation - Example #2:
|
| 144 |
|
| 145 |
```python
|
|
|
|
| 161 |
|
| 162 |

|
| 163 |
|
| 164 |
+
Image generation - Example #3:
|
| 165 |
+
|
| 166 |
+
```python
|
| 167 |
+
prompt = "An architectural design in the style of <bioinspired>. The structure itself features key design elements as in <bioinspired>."
|
| 168 |
+
num_samples =1
|
| 169 |
+
num_rows =1
|
| 170 |
+
n_steps=50
|
| 171 |
+
guidance_scale=5.
|
| 172 |
+
all_images = []
|
| 173 |
+
for _ in range(num_rows):
|
| 174 |
+
image = pipeline(prompt,num_inference_steps=n_steps,num_images_per_prompt=num_samples,
|
| 175 |
+
guidance_scale=guidance_scale,).images
|
| 176 |
+
|
| 177 |
+
all_images.extend(image)
|
| 178 |
+
|
| 179 |
+
grid = image_grid(all_images, num_rows, num_samples, save_individual_files=True, )
|
| 180 |
+
grid
|
| 181 |
+
```
|
| 182 |
+
|
| 183 |
+

|
| 184 |
+
|
| 185 |
+
|
| 186 |
|
| 187 |
```bibtext
|
| 188 |
@article{BioinspiredFluxBuehler2024,
|