|
--- |
|
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5 |
|
library_name: diffusers |
|
license: creativeml-openrail-m |
|
inference: true |
|
tags: |
|
- stable-diffusion |
|
- stable-diffusion-diffusers |
|
- text-to-image |
|
- diffusers |
|
- diffusers-training |
|
- lora |
|
datasets: |
|
- gigant/oldbookillustrations |
|
pipeline_tag: text-to-image |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the training script had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# LoRA text2image fine-tuning - Oedon42/oldpainter-lora |
|
These are LoRA adaption weights for stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were fine-tuned on the gigant/oldbookillustrations dataset. You can find some example images in the following. |
|
|
|
|
|
|
|
|
|
## Intended uses & limitations |
|
|
|
#### How to use |
|
|
|
```python |
|
from diffusers import DiffusionPipeline |
|
|
|
pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5") |
|
pipe.load_lora_weights("Oedon42/oldpainter-lora") |
|
|
|
prompt = "1800s, 19th century, antiquity, black & white, Croatia, Europe, ruins" |
|
image = pipe(prompt).images[0] |
|
``` |
|
|
|
## Model Preview |
|
|
|
Here are some preview results of the model: |
|
|
|
<div style="display: flex; flex-wrap: wrap;"> |
|
<div style="flex: 50%; padding: 1px;"> |
|
<img src="./image_0.png" alt="Preview 1" style="width: 90%;"/> |
|
</div> |
|
<div style="flex: 50%; padding: 1px;"> |
|
<img src="./image_1.png" alt="Preview 2" style="width: 90%;"/> |
|
</div> |
|
<div style="flex: 50%; padding: 1px;"> |
|
<img src="./image_2.png" alt="Preview 3" style="width: 90%;"/> |
|
</div> |
|
<div style="flex: 50%; padding: 1px;"> |
|
<img src="./image_3.png" alt="Preview 4" style="width: 90%;"/> |
|
</div> |
|
</div> |
|
|
|
## Training details |
|
|
|
[TODO: describe the data used to train the model] |
