---
license: apache-2.0
base_model: Tongyi-MAI/Z-Image
base_model_relation: adapter
pipeline_tag: text-to-image
tags: [text-to-image, lora, diffusers, z-image, zimage, stationthis]
instance_prompt: "stationthis"
training_steps: 3000
network_type: lora
library_name: ai-toolkit
widget:
- text: "stationthis, stationthis, low poly playstation screenshot style, A determined young woman with fiery red pigtails tied…"
  output:
    url: samples/sample_000.jpg
- text: "stationthis, stationthis, low poly playstation screenshot style, Under a misty, twilight sky, a male adventurer in blue…"
  output:
    url: samples/sample_001.jpg
- text: "stationthis, stationthis, low poly playstation screenshot style, A stoic, sunglasses-wearing man in a denim jacket stan…"
  output:
    url: samples/sample_002.jpg
- text: "stationthis, stationthis, low poly playstation screenshot style, A stern, determined woman with a black headband and ta…"
  output:
    url: samples/sample_003.jpg
- text: "stationthis"
  output:
    url: samples/sample_004.jpg
- text: "stationthis"
  output:
    url: samples/sample_005.jpg
- text: "stationthis"
  output:
    url: samples/sample_006.jpg
- text: "stationthis"
  output:
    url: samples/sample_007.jpg
---

# impresstation-zimage

zimage LoRA "impresstation-zimage" — trigger "stationthis".

**Trigger word:** `stationthis`

## Sample Outputs

| ![sample](samples/sample_000.jpg) | ![sample](samples/sample_001.jpg) |
|:---:|:---:|
| *stationthis, stationthis, low poly playstation screenshot style, A determined young woman…* | *stationthis, stationthis, low poly playstation screenshot style, Under a misty, twilight…* |
| ![sample](samples/sample_002.jpg) | ![sample](samples/sample_003.jpg) |
|:---:|:---:|
| *stationthis, stationthis, low poly playstation screenshot style, A stoic, sunglasses-wear…* | *stationthis, stationthis, low poly playstation screenshot style, A stern, determined woma…* |
| ![sample](samples/sample_004.jpg) | ![sample](samples/sample_005.jpg) |
|:---:|:---:|
| ![sample](samples/sample_006.jpg) | ![sample](samples/sample_007.jpg) |
|:---:|:---:|

## Usage (Diffusers)

```python
import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "Tongyi-MAI/Z-Image-Turbo", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("ms2stationthis/impresstation-zimage")
image = pipe("stationthis, a character portrait", guidance_scale=4.0, num_inference_steps=25).images[0]
image.save("out.png")
```

## Recommended Settings

| LoRA strength | Guidance | Steps | Resolution |
|---|---|---|---|
| 0.8–1.0 | 4.0 | 25 | 1024×1024 |

## Training Details

- **Base:** Tongyi-MAI/Z-Image
- **Steps:** 3000 · **Network:** LoRA rank 32 / alpha 32
- **Optimizer:** adamw8bit, lr 1e-4 · **Scheduler:** flowmatch
- **Resolution:** 512, 768, 1024 (multi-res bucketed) · **Precision:** bf16 train / fp16 save

## Reproduction

This repo includes the full **`dataset/`** (33 image-caption pairs) and the exact **`config.yaml`** so the LoRA can be retrained as-is.

## About

Trained on [StationThis](https://miladystation2.net) — an AI creative platform powered by $MS2.
Train your own LoRAs via [@stationthisbot](https://t.me/stationthisbot) on Telegram.

<sub>Published via noema.</sub>