Billie Eilish LoRA — Z-Image Turbo
A billie lora trained on a single event with various images. Captures likeness, hair, and expression well.
Examples
Training Details
| Field | Value |
|---|---|
| Base model | Tongyi-MAI/Z-Image-Turbo |
| Training tool | ai-toolkit |
| Steps | 3000 |
| Resolution | 1024×1024 |
| Precision | qfloat8 |
| Trigger word | billie eilish |
Usage
Recommended lora strength: 0.8 – 0.9.
Known limitations
Trained on a single event dataset, so background environments may drift toward the training context without explicit prompting. The dataset images are all from a single event, so clothing/background leans heavily towards that one outfit. Prompting for clothing however makes it easy to adjust this. This is my first attempt at training a lora, so expect some jank.
Compatibility
Tested in ComfyUI with Z-Image Turbo.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for emacs01/Billie_Eilish_ZIT
Base model
Tongyi-MAI/Z-Image-Turbo