README.md

---
base_model: Tongyi-MAI/Z-Image-Turbo
tags:
  - lora
  - text-to-image
  - diffusion
  - z-image-turbo
license: other
---

# sofia-russo — LoRA (Z-Image-Turbo)

LoRA adapter trained for the concept/style **"sofia-russo"**.

## Trigger word
Use this token in your prompt:
- **`sofia-russo`**

> Note: Some workflows/tokenizers may also respond to `sofia russo` (with a space). If the trigger doesn’t “bite”, try both variants.

## Base model
- **Tongyi-MAI/Z-Image-Turbo**

## Files
- `*.safetensors` — LoRA weights
- `config.yaml`, `job_config.json` — training configuration
- (optional) `log.txt` — training log

## How to use

### A) ComfyUI / AUTOMATIC1111
1. Put the `.safetensors` file into your LoRA folder.
2. Prompt example:
   - `sofia-russo, outdoor golden hour portrait, natural warm sunlight, high detail`

(Adjust LoRA strength to taste, e.g. 0.6–1.0.)

### B) Diffusers (generic example)
```python
import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "Tongyi-MAI/Z-Image-Turbo",
    torch_dtype=torch.bfloat16
).to("cuda")

# Replace with your actual filename:
pipe.load_lora_weights("thorjank/<REPO_NAME>", weight_name="<YOUR_LORA_FILENAME>.safetensors")

prompt = "sofia-russo, outdoor golden hour portrait, natural warm sunlight, high detail"
image = pipe(prompt).images[0]
image.save("out.png")