Instructions to use Wuli-art/Qwen-Image-2512-Turbo-LoRA-2-Steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wuli-art/Qwen-Image-2512-Turbo-LoRA-2-Steps 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-2512", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Wuli-art/Qwen-Image-2512-Turbo-LoRA-2-Steps") 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
support for other qwen models
Very good acceleration lora model. Will there be support for other Qwen series models in the future, such as Qwen Image, Qwen Image Edit?
Thanks for the suggestion! Support for other models is on our radar, but there’s no confirmed timeline yet. Stay tuned. 😉
We have had a discussion, and we will release 4 step turbo LoRA for Qwen Image Edit 2511 soon :-)
Hello guys, thanks for releasing the 2-step LoRA, and for all your hard work.
Any update for Owen Image Edit 2511? Or has it been cancelled? I've been waiting for it for a while now and would like to know the status, if possible. Thanks again.
Hello guys, thanks for releasing the 2-step LoRA, and for all your hard work.
Any update for Owen Image Edit 2511? Or has it been cancelled? I've been waiting for it for a while now and would like to know the status, if possible. Thanks again.
Sorry for the late reply. Over the past few months, we have been training Qwen-Image-2, which is not open-sourced yet but is available on our website. Because of that, Qwen-Image-Edit-2511 has been delayed.
I’m currently training a Qwen-Image-Edit-2511 version, and hopefully it can be finished in about two weeks. Thanks for your patience!
Okay, I'm looking forward to it.
we have been training Qwen-Image-2, which is not open-sourced yet
Does that mean they have confirmed about open-sourcing it?
Okay, I'm looking forward to it.
we have been training Qwen-Image-2, which is not open-sourced yet
Does that mean they have confirmed about open-sourcing it?
No. It depends on the Qwen team.