Z-Image-Turbo-Anime BF16 | Custom Anime CheckpointA custom anime checkpoint built by merging purpose-trained LoRAs directly into the Z-Image-Turbo base model. This approach enhances anime aesthetics while preserving the model's generation speed,My personal settings:<ul><li>Sampler: DPM++ Simple</li><li>Steps: 30</li><li>CFG: 2</li></ul>Feel free to experiment. you can get great results with fewer steps and lighter settings depending on your hardware. Some users may find that 8–12 steps already produce strong outputs, making this model very flexible across different GPU configurations.A LoRA version is also available.nb: My settings were used with the model version.

Z-ImageTurbo Anime V2 BF16

zImageturboAnimeV2_v20Bf16.safetensors

v2,0 bf16

### 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('hezi01001/Z-Image-Turbo-1')
```
Download with Git clone
```
git clone https://www.modelscope.ai/hezi01001/Z-Image-Turbo-1.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: 3c04022d805d3c0cbaac450bc11de1f5e2e47929a58a7c65182a219a5265344f