simpletuner-example-qwen_image-peft-lora

simpletuner-example-qwen_image-peft-lora

This is a PEFT LoRA derived from Qwen/Qwen-Image.

The main validation prompt used during training was:

An domokun running through a field with flowers all around him.

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.

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: 218

• Training steps: 1600

• Learning rate: 0.0001

  • Learning rate schedule: constant
  • 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

import torch
from diffusers import DiffusionPipeline

model_id = 'Qwen/Qwen-Image'
adapter_id = 'bghira/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 running through a field with flowers all around him."
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")