---
title: Boogu-Image-0.1-Edit-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Boogu-Image-0.1-Edit-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Boogu-Image-0.1-Edit-8bit.md"
repository: mlx-community/Boogu-Image-0.1-Edit-8bit
last_updated: 2026-10-30
license: apache-2.0
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - Boogu/Boogu-Image-0.1-Edit
base_model_relation: finetune
parameters: 4.0B
tensor_type:
  - F32
  - BF16
  - U32
library_name:
  - mlx
  - lora
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 4
stars: 0
tags:
  - mlx
  - safetensors
  - apple-silicon
  - text-to-image
  - image-editing
  - diffusion
  - omnigen2
  - boogu
---

# Boogu-Image-0.1-Edit-8bit

> Boogu-Image-0.1-Edit-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Boogu-Image-0.1-Edit-8bit

mlx-community/Boogu-Image-0.1-Edit-8bit 是 ModelScope 魔搭社区上的 4.0B 参数image-to-image模型，采用 apache-2.0 许可，基于 Boogu/Boogu-Image-0.1-Edit 构建。

- **Repository**: mlx-community/Boogu-Image-0.1-Edit-8bit
- **License**: apache-2.0
- **Tasks**: image-to-image
- **Parameters**: 4.0B
- **Base model**: Boogu/Boogu-Image-0.1-Edit
- **Tags**: mlx, safetensors, apple-silicon, text-to-image, image-editing, diffusion, omnigen2, boogu
- **Downloads**: 4
- **Stars**: 0
- **Last updated**: 2026-10-30

Source: https://www.modelscope.cn/models/mlx-community/Boogu-Image-0.1-Edit-8bit

---

# mlx-community/Boogu-Image-0.1-Edit-8bit

MLX (int8) conversion of **[Boogu-Image-0.1-Edit](https://huggingface.co/Boogu/Boogu-Image-0.1-Edit)** (Apache-2.0)
for Apple Silicon: instruction-based image editing. OmniGen2-lineage pipeline (DiT + FLUX.1 VAE + FlowMatchEuler scheduler).
The **Qwen3-VL-8B-Instruct** text encoder is the stock model (bit-identical) — referenced from
[`Qwen/Qwen3-VL-8B-Instruct`](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct), not re-hosted.

**int8** (group_size=32, attn+FFN Linears; embeds, time, norm_out and AdaLN kept bf16), the same layout as
[Turbo-8bit](https://huggingface.co/mlx-community/Boogu-Image-0.1-Turbo-8bit). Quantized from the
[bf16 tier](https://huggingface.co/mlx-community/Boogu-Image-0.1-Edit-bf16); per-pass DiT cosine vs bf16 **0.999848**.
~12.5 GB DiT. Quant auto-detected via `transformer/quant_config.json`.

**Memory** (M5 Max, process phys_footprint, Swift package): 12.9 GB resident; peak ~31.7 GB at 1024²
(the Qwen3-VL conditioner is loaded per request and evicted before the denoise).

## Use — Swift (MLXEngine)

[`boogu-image-swift`](https://github.com/xocialize/boogu-image-swift) ≥ 0.5.0:
`BooguImageConfiguration.edit(quant: .int8)` materializes this repo and the conditioner into the engine's store.

## Use — Python

```bash
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
from PIL import Image
pipe = BooguImagePipeline.from_pretrained("<this repo dir>", "Qwen/Qwen3-VL-8B-Instruct")
img = pipe.generate_edit(Image.open("in.png"), "make it a snowy winter evening", steps=50, text_guidance=4.0)
```

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