How to use Qwen/Qwen-Image-2.1-Turbo 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-2.1-Turbo", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
I don't think asking users to re-download the 32GB original weights is a good idea.The LoRA file is just over 1GB?Would you mind sharing how you trained the model?Did you merge open-source LoRA weights, or did you perform full fine-tuning?
· Sign up or log in to comment
