README.md

---
library_name: peft
base_model: Tongyi-MAI/Z-Image-Turbo
tags:
- lora
- diffusion
- image-generation
- japan
- photography
- realistic
license: other
datasets:
- ThePioneer/japanese-photos
language:
- en
- fr
pipeline_tag: text-to-image
---

# Japan Realistic LoRA for Z-Image-Turbo

A LoRA adapter trained on realistic Japanese photography to enhance Z-Image-Turbo's ability to generate authentic Japanese scenes, urban landscapes, and cultural elements.

## Model Description

This is a LoRA (Low-Rank Adaptation) adapter trained on the [Tongyi-MAI/Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo) diffusion model. It specializes in generating realistic photographs of Japanese locations, transportation, architecture, and everyday scenes with authentic lighting and composition.

## Training Details

- **Base Model**: Tongyi-MAI/Z-Image-Turbo
- **Training Steps**: 2,000
- **LoRA Rank (r)**: 32
- **LoRA Alpha**: 32
- **Learning Rate**: 0.0001
- **Optimizer**: AdamW 8-bit
- **Batch Size**: 1 (with gradient accumulation of 4)
- **Training Resolution**: 512x512
- **Precision**: bfloat16
- **Noise Scheduler**: FlowMatch
- **Trained Using**: [Ostris AI-Toolkit](https://github.com/ostris/ai-toolkit)

## Usage

### Using with Diffusers

```python
from diffusers import DiffusionPipeline
import torch

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

# Load LoRA adapter
pipe.load_lora_weights("your-username/japan_realistic")

# Generate image
prompt = "Photo of a Shinkansen bullet train stopped at a Japanese station platform, overhead roof structure, yellow tactile paving, natural daylight, ultra realistic."
image = pipe(
    prompt=prompt,
    num_inference_steps=8,
    guidance_scale=1.0,
    width=1024,
    height=1024
).images

image.save("output.png")