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("Danrisi/Lenovo_Qwen")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]P.S: No need to use them. Here is an example of prompting:overexposed indoor scene, raw unedited amateurish candid shot of ...
Also you can control: indoor/outdoor, overexposed/underexposed.
- Downloads last month
- 605
Model tree for Danrisi/Lenovo_Qwen
Base model
Qwen/Qwen-Image