How to use furaidosu/panorama-qwen-image-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("furaidosu/panorama-qwen-image-lora") prompt = "a mad scientist laboratory interior" image = pipe(prompt).images[0]
This looks really interesting, so thanks for starters. Like the title says, you've got a few versions going that represent (I'm guessing) the number of steps. Is there a sweet spot that works at a strength of 1.0?
· Sign up or log in to comment
