---
license: other
base_model: "Qwen/Qwen-Image"
tags:
  - qwen_image
  - qwen_image-diffusers
  - text-to-image
  - image-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora

  - template:sd-lora
  - standard
pipeline_tag: text-to-image
inference: true
widget:
- text: 'An domokun in minecraft style.'
  parameters:
    negative_prompt: 'ugly, cropped, blurry, low-quality, mediocre average'
  output:
    url: ./assets/image_0_0.png
---

# simpletuner-example-qwen_image-peft-lora

This is a PEFT LoRA derived from [Qwen/Qwen-Image](https://huggingface.co/Qwen/Qwen-Image).

The main validation prompt used during training was:
```
An domokun in minecraft style.
```


## Validation settings
- CFG: `4.0`
- CFG Rescale: `0.0`
- Steps: `30`
- Sampler: `FlowMatchEulerDiscreteScheduler`
- Seed: `42`
- Resolution: `1024x1024`


Note: The validation settings are not necessarily the same as the [training settings](#training-settings).

You can find some example images in the following gallery:


<Gallery />

The text encoder **was not** trained.
You may reuse the base model text encoder for inference.


## Training settings

- Training epochs: 9
- Training steps: 250
- Learning rate: 0.0001
  - Learning rate schedule: constant_with_warmup
  - Warmup steps: 100
- Max grad value: 0.01
- Effective batch size: 1
  - Micro-batch size: 1
  - Gradient accumulation steps: 1
  - Number of GPUs: 1
- Gradient checkpointing: True
- Prediction type: flow_matching[]
- Optimizer: optimi-lion
- Trainable parameter precision: Pure BF16
- Base model precision: `int8-quanto`
- Caption dropout probability: 0.0%


- LoRA Rank: 8
- LoRA Alpha: 8.0
- LoRA Dropout: 0.1
- LoRA initialisation style: default
- LoRA mode: Standard
    

## Datasets

### dreambooth-1024
- Repeats: 0
- Total number of images: 26
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
- Used for regularisation data: No


## Inference


```python
import torch
from diffusers import DiffusionPipeline

model_id = 'Qwen/Qwen-Image'
adapter_id = 'simpletuner-example-qwen_image-peft-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An domokun in minecraft style."
negative_prompt = 'ugly, cropped, blurry, low-quality, mediocre average'

## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same during inference time.
from optimum.quanto import quantize, freeze, qint8
quantize(pipeline.transformer, weights=qint8)
freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
model_output = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=30,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=1024,
    height=1024,
    guidance_scale=4.0,
).images[0]

model_output.save("output.png", format="PNG")

```