Qwen-Image-mflux-6bit

6-bit quantized weights for the Qwen-Image model compatible with MFLUX.

About

6bit qunatized weights for the Qwen Image model compatible with MFLUX.

Weights are 23.05 GB in size and requires MFLUX v.0.11.0 or later to run. For more information, visit https://github.com/filipstrand/mflux

Installation

To use this model, you need MFLUX installed:

uv tool install --upgrade mflux

Usage

Once installed, generate images with:

mflux-generate-qwen \
  --model filipstrand/Qwen-Image-mflux-6bit \
  --prompt "Close-up portrait of a majestic tiger in its natural habitat, detailed fur texture, piercing eyes, natural forest background, soft natural lighting, wildlife photography, photorealistic, high detail, professional wildlife shot" \
  --negative-prompt "blurry, low quality, distorted, deformed, ugly, bad anatomy, bad proportions, extra limbs, duplicate, watermark, signature, text, letters, cartoon, anime, painting, drawing, illustration, 3d render, cgi, zoo, cage, artificial" \
  --width 1920 \
  --height 816 \
  --steps 30 \
  --seed 42 

Model Details

• Quantization: 6-bit
• Framework: MFLUX
• Compatible with: MFLUX v0.13.0 or later
• Architecture: Qwen-Image

License

This model inherits the license of the original Qwen model. Please refer to the original model repository for detailed licensing information.