Instructions to use SceneWorks/qwen-image-2-1-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SceneWorks/qwen-image-2-1-mlx with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SceneWorks/qwen-image-2-1-mlx", 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
Commit History
21 days ago
-
Add NOTICE (Qwen Research License §3(c) attribution)
Verified signatureAdds the attribution NOTICE the Qwen RESEARCH LICENSE AGREEMENT §3(c) requires to the q8 and q4 tiers, identical in form to the Qwen-Image-2.1-Turbo tiers (mlx_gen_qwen_image_2_1::convert::attribution_notice). Weights, LICENSE, CHANGES.md and SHA256SUMS are unchanged.ef03535
-
Qwen-Image 2.1 q4 tier (pre-quantized, group 64; derived bundle under the Qwen Research License — see q4/CHANGES.md and q4/SHA256SUMS)
Verified signature1691de0 -
Qwen-Image 2.1 q8 tier (pre-quantized, group 64; derived bundle under the Qwen Research License — see q8/CHANGES.md and q8/SHA256SUMS)
Verified signature2f5ad8b -
initial commit
Verified signature9b92e35