Trained on about 75+ random art images, including anime, digital art, and other styles I found on Pinterest.I recommend setting the strength to 0.5 as increasing it further would give anatomical artifacts.A LoRA strength between 0.1 and 0.5 is a good range. This LoRA also works well as an enhancer for Z images, especially at low strengths.

Z-Image-Art

This one is based on Z image Base, so expect it to work better than all the previous LoRAs.

Z-Aesthetic-2_25.safetensors

v4.0

v5.5

v5.0

v3.0

v2.0

v1.0

### You are viewing the default Readme template as no detailed model-card was provided by the model’s contributors. You can access the model files in the "Files and versions" tab.
#### Model files may be downloaded with ModelScope SDK or through git clone directly.

Download with ModelScope’s Python SDK
```bash
#Install ModelScope
pip install modelscope
```
```python
#Download with ModelScope’s Python SDK
from modelscope import snapshot_download
model_dir = snapshot_download('hopper21/Z-Aesthetic-2')
```
Download with Git clone
```
git clone https://www.modelscope.ai/hopper21/Z-Aesthetic-2.git
```

If you are a contributor to this model, we invite you to promptly update the model card content according to <a href="https://www.modelscope.ai/docs/contribute/model-integration" style="color: lightgrey; text-decoration: underline;">the model contribution documentation</a>.

Files with SHA256: 1dd2cf11d1fefd83ed83e4a709e74d7b21d5e5c9a92ac008b1d8ce7b5b453c50