How to use joyfox/Qwen-Image-Gufeng-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("joyfox/Qwen-Image-Gufeng-LoRA") prompt = "gfwm, The image is a digital illustration that captures the essence of traditional East Asian aesthetics, possibly Chinese or Japanese, given the style of the fan and the hairstyle. The subject's attire and adornments suggest she may be portraying a character from historical or cultural narratives often depicted in literature, film, or art from these regions. The use of vibrant colors and intricate details indicates a high level of craftsmanship and attention to detail, which are hallmarks of such illustrations.To provide a more detailed caption, one could focus on the elements that stand out, such as the rich textures of the fan, the reflective quality of the jewels, and the delicate curls of the hair. It would also be important to note the serene expression on her face, which adds a sense of grace and poise to the overall composition. A well-crafted caption would aim to convey not only the visual aspects but also the cultural significance behind the imagery presented.." image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
