---
title: Insert-Anything
canonical_url: "https://www.modelscope.cn/models/HuanJue/Insert-Anything"
md_url: "https://www.modelscope.cn/models/HuanJue/Insert-Anything.md"
repository: HuanJue/Insert-Anything
chinese_name: Insert-Anything
last_updated: 2026-08-17
license: "MIT License"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - chuyuxun/flux1.fill.dev
base_model_relation: adapter
parameters: 927.3M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
supports_inference: txt2img
downloads: 24
stars: 0
tags:
  - LoRA
  - text-to-image
---

# Insert-Anything

> Insert-Anything - HuanJue 在 ModelScope 开源的模型。Huggingface 中 Insert-Anything 模型的搬运，可以将参考图像中的物体、人物、服装插入到目标图像的指定区域中。Github 仓库：https://github.com/song-wensong/insert-anything

HuanJue/Insert-Anything 是 ModelScope 魔搭社区上的 927.3M 参数text-to-image-synthesis模型，采用 MIT License 许可，基于 chuyuxun/flux1.fill.dev 构建，并支持在线推理（txt2img）。

- **Repository**: HuanJue/Insert-Anything
- **License**: MIT License
- **Tasks**: text-to-image-synthesis
- **Parameters**: 927.3M
- **Base model**: chuyuxun/flux1.fill.dev
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 24
- **Stars**: 0
- **Last updated**: 2026-08-17

Source: https://www.modelscope.cn/models/HuanJue/Insert-Anything

---

Huggingface 中 Insert-Anything 模型的搬运，可以将参考图像中的物体、人物、服装插入到目标图像的指定区域中。

Github 仓库：https://github.com/song-wensong/insert-anything