Downloads · 30 days
90
73% of all-time downloads
mflux-community/fibo-edit-mflux-q5
fibo-edit-mflux-q5 is a image-to-image model from mflux-community. Use it when you need one image transformed into another. It is set up for mflux. The card lists the license as other.
This is a Q5 MFlux version of Fibo-Edit.
Downloads · 30 days
90
73% of all-time downloads
All-time downloads
124
Public
Repo size
9.2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors9.2 GB · 100%
From the Hugging Face model README
This is a Q5 MFlux version of Fibo-Edit.
MFlux runs the latest state-of-the-art generative image models locally on your Mac in native MLX. MFlux is open source and free.
[!NOTE] Community conversion by MFlux-Community -- not an official release from the original model's authors. The original model's license applies unchanged, see License.
| QUANT | GB | Repo |
|---|---|---|
| BF16 | 24.1 | mflux-community/fibo-edit-mflux-bf16 |
| Q8 | 13.5 | mflux-community/fibo-edit-mflux-q8 |
| Q6 | 10.6 | mflux-community/fibo-edit-mflux-q6 |
| Q5 | 9.2 | this repo |
| Q4 | 7.8 | mflux-community/fibo-edit-mflux-q4 |
| Q3 | 6.4 | mflux-community/fibo-edit-mflux-q3 |
Converted with MFlux 0.22.0 on 2026-10-09.
Standard MFlux quantization uses MLX affine quantization (5-bit) across the text encoder, transformer and VAE. The quantization level is stored in the weights, so no --quantize flag is needed.
Install MFlux
uv tool install --upgrade mflux
Edit an image using Fibo-Edit Q5:
mflux-generate-fibo-edit \
--model mflux-community/fibo-edit-mflux-q5 \
--base-model fibo-edit \
--image-path input.png \
--prompt "A puffin standing on a cliff" \
--width 1024 \
--height 1024 \
--seed 42 \
--output image.png
The weights are downloaded from this repo on first use. To keep a local copy instead:
hf download mflux-community/fibo-edit-mflux-q5 --local-dir ./fibo-edit-mflux-q5
then pass --model ./fibo-edit-mflux-q5.
This repo inherits the license of the original model: bria-fibo-edit. See the original model card for the full terms and any usage restrictions. The weights here were modified from the original release only by conversion to MLX and quantization.