Instructions to use Qwen/Qwen-Image-2512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Qwen/Qwen-Image-2512 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") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Prevent grid artifact?
#10
by stablellama - opened
Generating images with Qwen Image 2512 I can see, especially in the darker places, a repeating, grid like pattern.
E.g. look at this image (prompt: 一杯冒着热气的茶,背景为浅绿色,两侧有叶子装饰,杯上写有中文文字) in the shade on the bottom right:
What is the best way to avoid it? What sampler and which scheduler would prevent it?