starsfriday/Qwen-Image-Shentianyongmei-LoRA

starsfriday Qwen-Image LoRA

Prompt

stym, 一个女人穿着结婚的的汉服，正面对镜头，戴着精美的中式头饰，旁边是结婚的场景

Prompt

stym, The image depicts a person dressed in a school uniform, which is commonly associated with Japanese high schools. The outfit includes a light blue collared shirt and a pleated skirt featuring a blue and white checkered pattern. A prominent burgundy bow tie adds a touch of color to the ensemble. Accessories include colorful beaded bracelets on both wrists, one green and one red, and a small yellow hair accessory in the form of a flower or bow on top of the person's head. The individual is striking a playful pose with their hands making a "rock on" gesture near their face, suggesting a cheerful and youthful demeanor. The background is an indoor setting that appears to be a home environment, with wooden furniture and a door visible behind the person.

Prompt

stym, The image shows a person dressed in an outfit that combines elements of lingerie and cosplay. The top is black with white lace details, featuring a deep neckline and short sleeves adorned with ruffles at the edges. A prominent bow with a jewel center is part of the design, adding a touch of elegance. The bottom garment appears to be a white skirt or shorts with gold accents, suggesting a coordinated ensemble. The individual's pose and expression convey confidence and poise. The background is minimalistic, focusing attention on the attire. This description avoids assumptions about personal identity or context beyond what is visually presented.

Prompt

stym, The image captures a moment of quiet introspection, featuring an individual lying on a bed adorned with a black and white geometric-patterned blanket. The person is dressed in a stylish ensemble that includes a cream-colored top with black trim, suggesting a sense of fashion consciousness. Their hands are clasped together, resting gently on the blanket, which adds to the overall relaxed yet poised atmosphere of the scene. The soft lighting enhances the calmness of the setting, creating a warm and inviting ambiance. This composition could be interpreted as a portrayal of rest or contemplation, with the subject appearing at ease in their environment.

Model Card for Model ID

This is a model for Qwen-Image in Portrait generation, trained on Qwen/Qwen-Image, and it is mainly applicable to generating various photos of Japanese adult actress 深田えいみ.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-Shentianyongmei-LoRA/qwen_image_shentian.safetensors', adapter_name="lora")

prompt = '''stym, The image captures a moment of quiet introspection, featuring an individual lying on a bed adorned with a black and white geometric-patterned blanket. The person is dressed in a stylish ensemble that includes a cream-colored top with black trim, suggesting a sense of fashion consciousness. Their hands are clasped together, resting gently on the blanket, which adds to the overall relaxed yet poised atmosphere of the scene. The soft lighting enhances the calmness of the setting, creating a warm and inviting ambiance. This composition could be interpreted as a portrayal of rest or contemplation, with the subject appearing at ease in their environment. '''
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

stym

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