Instructions to use lightx2v/Qwen-Image-2.1-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Qwen-Image-2.1-Lightning 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", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lightx2v/Qwen-Image-2.1-Lightning") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Left tilt
#3
by thebaker66 - opened
There's an issue with this lora, the same as one of the previous lora's by another creator. It pushes things to the left in the image.
Are the team aware of this? Is there a solution? It seems to me to be one of the better Turbo LORA's overall, minus this issue.
Thanks.
Well, it also has an issue of being overtrained on girlsgirlsgirls and hallucinating them where there were none. :- )