n01e1se/qwen-image-lora

Qwen-Image with Integrated LoRA

This is a Qwen-Image model with integrated LoRA weights for custom character generation.

Model Details

• Base Model: Qwen/Qwen-Image
• LoRA: Integrated custom LoRA for character generation
• Format: Diffusers
• Precision: bfloat16
• Framework: PyTorch

Usage

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "n01e1se/qwen-image-lora",
    torch_dtype=torch.bfloat16,
)

pipe.enable_sequential_cpu_offload()

image = pipe(
    prompt="ma11en1a elegant woman with voluminous red curls",
    num_inference_steps=50,
    width=1024,
    height=1024,
).images[0]

image.save("output.png")

Example Images

Example 1

Example 2

Example 3

Notes

• The LoRA weights have been merged into the base model weights
• Use CPU offloading for systems with limited GPU memory
• Recommended image size: 1024x1024
• Recommended steps: 50