MLX (int4) 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.

int4 (group_size=32, attn+FFN); quant auto-detected via quant_config.json. ~7.9 GB.

Use

pip install mlx mlx-vlm && git clone https://github.com/xocialize/boogu-image-mlx && cd boogu-image-mlx && pip install -e .

python

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)

Code: https://github.com/xocialize/boogu-image-mlx