valiantcat 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('valiantcat/Qwen-Image-Gufeng-LoRA/qwen_image_gufeng.safetensors', adapter_name="lora")

prompt = '''gfwm, The image presents a character dressed in traditional East Asian attire, possibly inspired by Chinese or Japanese fashion. The outfit is predominantly white with delicate floral embroidery, which adds to the elegance and cultural richness of the ensemble. The use of red accents, such as the sash tied around the waist and the earrings, provides a striking contrast that highlights the beauty of the design. The setting appears to be an outdoor pavilion during autumn, suggested by the vibrant orange-red leaves of the maple tree in the background. This seasonal backdrop not only enhances the visual appeal but also suggests a time of year often associated with change and reflection in many Eastern cultures.
The character's poised demeanor and the careful styling of her hair adorned with intricate accessories convey a sense of grace and sophistication. The lighting in the photograph is soft and warm, contributing to the serene atmosphere and accentuating the textures of the fabric and the natural elements within the scene. Overall, the image captures a moment of tranquility and beauty, blending human artistry with natural splendor.  '''
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