starsfriday Qwen-Image-Edit LoRA

Prompt
turn the image into the oil painting style.

Model Card for Model ID

This is a model for generation of oil painting style, trained on Qwen/Qwen-Image-Edit, and the main purpose is to generate images in an oil painting style. Surprisingly, this oil painting style can bypass the real-person image review process of sora2.For use in ComfyUI.

ComfyUI Workflow

This LoRA works with a modified version of Comfy's Qwen-Image-Edit workflow. The main modification is adding a Qwen-Image-Edit LoRA node connected to the base model.

See the Downloads section above for the modified workflow.

Video Demos

Direct Use

from diffusers import QwenImageEditPipeline
import torch
from PIL import Image

# Load the pipeline
pipeline = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit")
pipeline.to(torch.bfloat16)
pipeline.to("cuda")

# Load trained LoRA weights for in-scene editing
pipeline.load_lora_weights("starsfriday/Qwen-Image-Edit-Skip-Sora",weight_name="qwen_edit_oil-paint.safetensors")

# Load input image
image = Image.open("./result/test.jpg").convert("RGB")

# Define in-scene editing prompt
prompt = "turn the image into the oil painting style. "

# Generate edited image with enhanced scene understanding
inputs = {
    "image": image,
    "prompt": prompt,
    "generator": torch.manual_seed(12345),
    "true_cfg_scale": 4.0,
    "negative_prompt": " ",
    "num_inference_steps": 50,
}

with torch.inference_mode():
    output = pipeline(**inputs)
    output_image = output.images[0]
    output_image.save("restlt.png")