<h3 id="uaz-452-&quot;bukhanka&quot;-soviet-retro-van-lora">UAZ-452 "Bukhanka" / Soviet Retro Van LoRA</h3>High-quality LoRA trained on clean stock references of the iconic Soviet off-road microbus. Perfect for creating atmospheric retro road trips, rustic landscapes, and cinematic renders.It got its nickname 'Bukhanka' (literally 'The Loaf') because its boxy, rounded shape looks exactly like a traditional Russian brick loaf of bread on wheels<ul><li>Key features: Accurate factory geometry, classic round headlights, signature visor over the windshield, and authentic metal body texture without plastic gloss.</li><li>Tips: Use tags like <code>gray body</code>, <code>olive green body</code>, or <code>white body</code> to control the paint color. Pair with environmental tags (<code>pine forest</code>, <code>dirt road</code>, <code>canyon</code>) for best results.</li><li>Use a trigger if your prompt is poorly written. Vintage van</li></ul>

UAZ-452 Bukhanka (Vintage Van) | MOSS / Krea 2/Qwen 2.1

yazv1Q_.safetensors

v1.0 Qwen 2.1

v1.0 MOSS

v1.0 Krea 2


# 

## Model Introduction

This model is trained using the [Civision/model training](https://modelscope.ai/civision/modelTraining) environment and computing resources provided by ModelScope.

* Model Type: LoRA
* Base Model: [Qwen/Qwen-Image-2.1](https://modelscope.ai/models/Qwen/Qwen-Image-2.1)
* Training Code: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* Data amount：27
* Total training steps：2000
* License: Apache-2.0

## Inference Code

Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio):

```bash
pip install diffsynth
```

Inference:

```python
from diffsynth.pipelines.qwen_image_21 import QwenImage21Pipeline, ModelConfig
import torch

pipe = QwenImage21Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="vae/diffusion_pytorch_model*.safetensors"),
    ],
    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="processor/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="bazya75/yazv1Q", origin_file_pattern="yazv1Q_c1-st2000.safetensors"))

prompt = "a cat"
image = pipe(prompt, seed=0, num_inference_steps=50)
image.save("image.png")
```


Files with SHA256: c1635ef938cc24e562fd93ca7c9934b4759606ee70cdb0dd2a2fceae028a4f3b