metadata
library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Boogu/Boogu-Image-0.1-Edit/blob/main/README.md
pipeline_tag: image-to-image
base_model: Boogu/Boogu-Image-0.1-Edit
language:
- en
- zh
tags:
- mlx
- safetensors
- apple-silicon
- text-to-image
- image-editing
- diffusion
- omnigen2
- boogu
mlx-community/Boogu-Image-0.1-Edit-bf16
MLX (bf16) conversion of Boogu-Image-0.1-Edit (Apache-2.0)
for Apple Silicon. Instruction-based image editing. OmniGen2-lineage pipeline (DiT + FLUX.1 VAE + FlowMatchEuler).
The Qwen3-VL-8B-Instruct text encoder is stock (bit-identical) — referenced from
mlx-community/Qwen3-VL-8B-Instruct, not re-hosted.
Reference precision (bf16). ~19 GB DiT.
Use
pip install mlx mlx-vlm && git clone https://github.com/xocialize/boogu-image-mlx && cd boogu-image-mlx && pip install -e .
from boogu_image_mlx.pipeline_mlx import BooguImagePipeline
pipe = BooguImagePipeline.from_pretrained("<this repo dir>", "mlx-community/Qwen3-VL-8B-Instruct")
img = # instruction-based image editing (imageEdit)