Instructions to use linoyts/Qwen-Image-2.1-DMD2-2steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use linoyts/Qwen-Image-2.1-DMD2-2steps with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # 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("linoyts/Qwen-Image-2.1-DMD2-2steps") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Add Qwen-Image-2.1 official space vs 2-step LoRA comparison (t2i + i2i)
#1
by linoyts HF Staff - opened
Comparison grids: the official Qwen-Image-2.1 Space (its defaults) vs this 2-step DMD2 LoRA, on the demo's text-to-image and image-editing examples.
Prompt extension could matter here.