Instructions to use Qwen/Qwen-Image-2.1-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
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] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commercial Use of Qwen-Image-2.1 Outputs β Clear Answer Needed
#11
by VorSar - opened
Could the Qwen team please give a clear and definitive answer on this?
If I run Qwen-Image-2.1 locally on my own hardware (for example via ComfyUI), do not redistribute the model or its weights, and only use the generated images in commercial projects β is this allowed under the current license?
In other words: Can images generated locally with Qwen-Image-2.1 be used commercially β yes or no?
The current license wording and discussions around it leave too much room for conflicting interpretations. A clear answer from the Qwen team would be greatly appreciated.