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("bunnycore/Qwen-Aesthetic")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Enhancing the aesthetic quality and stylistic range of images generated by the Qwen-Image model. This LoRA attempts to address the base model's inherent lack of aesthetic visual styles.
- Downloads last month
- 111
Model tree for bunnycore/Qwen-Aesthetic
Base model
Qwen/Qwen-Image