About

4bit qunatized weights for the FLUX.1-Krea-dev model compatible with MFLUX.

Weights are 9.61 GB in size and requires MFLUX v.0.10.0 or later to run. For more information, visit https://github.com/filipstrand/mflux

Upgrade

To upgrade to the latest MFLUX v.0.10.0, run:

uv tool install --upgrade mflux

Example

Once installed, the following command will download these 4bit weights and generate an image:

mflux-generate \
    --model filipstrand/FLUX.1-Krea-dev-mflux-4bit \
    --base-model krea-dev \
    --prompt "A photo of a dog" \
    --steps 25 \
    --seed 2674888

image/jpeg

License

This model inherits the license of the original FLUX.1-dev model. Please refer to the original model repository for licensing information.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for filipstrand/FLUX.1-Krea-dev-mflux-4bit

Finetuned
(6)
this model