starsfriday Qwen-Image LoRA

Model Card for Model ID

This is a model for Qwen-Image in Portrait generation, trained on Qwen/Qwen-Image, and it is mainly used to generate animation pictures of ancient Chinese style.For use in through the following code and ComfyUI,The workflow files are in the folder of this project.

ComfyUI Workflow

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

See the Downloads section above for the modified workflow.

Direct Use

from diffusers import DiffusionPipeline
import torch

model_name = "Qwen/Qwen-Image"

# Load the pipeline
if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype)
pipe = pipe.to(device)

# Load LoRA weights
pipe.load_lora_weights('starsfriday/Qwen-Image-Gufeng-LoRA/qwen_image_gufeng.safetensors', adapter_name="lora")

prompt = '''gfwm, The image presents a digital illustration of a woman dressed in traditional East Asian attire, which suggests that the artwork may be inspired by Chinese or Japanese cultural elements. The use of soft colors and light effects gives the painting a serene and ethereal quality. The background is minimalistic, focusing attention on the subject while still providing context with the presence of foliage. This kind of imagery could be used for various purposes such as book covers, historical fiction media, or even educational materials to depict historical fashion and culture. The detailed rendering of her clothing and accessories indicates a high level of skill in digital artistry, capturing both the elegance of the garments and the gracefulness of the model's pose. '''
negative_prompt =  " "
image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=1024,
    height=1024,
    num_inference_steps=50,
    true_cfg_scale=5,
    generator=torch.Generator(device="cuda").manual_seed(123456)
)
image = image.images[0]

image.save("output.png")

Trigger phrase

gfwm

Download model

Weights for this model are available in Safetensors format.

Download

Training at Chongqing Valiant Cat

This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD(https://vvicat.com/).Business cooperation is welcome