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](https://huggingface.co/starsfriday/Qwen-Image-Shentianyongmei-LoRA)
## 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