---
title: FLUX.1-Kontext-dev-reference-depth-fusion-LORA
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/FLUX.1-Kontext-dev-reference-depth-fusion-LORA"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/FLUX.1-Kontext-dev-reference-depth-fusion-LORA.md"
repository: AI-ModelScope/FLUX.1-Kontext-dev-reference-depth-fusion-LORA
last_updated: 2026-06-27
license: apache-2.0
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - black-forest-labs/FLUX.1-Kontext-dev
base_model_relation: adapter
parameters: 171.8M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 141
stars: 2
tags:
  - flux
  - depth
  - controlnet
  - kontext
  - flux-kontext
  - img2img
  - image
  - editing
  - lora
---

# FLUX.1-Kontext-dev-reference-depth-fusion-LORA

> FLUX.1-Kontext-dev-reference-depth-fusion-LORA - AI-ModelScope 在 ModelScope 开源的模型。Depth Reference Fusion LoRA

AI-ModelScope/FLUX.1-Kontext-dev-reference-depth-fusion-LORA 是 ModelScope 魔搭社区上的 171.8M 参数image-to-image模型，采用 apache-2.0 许可，基于 black-forest-labs/FLUX.1-Kontext-dev 构建。

- **Repository**: AI-ModelScope/FLUX.1-Kontext-dev-reference-depth-fusion-LORA
- **License**: apache-2.0
- **Tasks**: image-to-image
- **Parameters**: 171.8M
- **Base model**: black-forest-labs/FLUX.1-Kontext-dev
- **Tags**: flux, depth, controlnet, kontext, flux-kontext, img2img, image, editing, lora
- **Downloads**: 141
- **Stars**: 2
- **Last updated**: 2026-06-27

Source: https://www.modelscope.cn/models/AI-ModelScope/FLUX.1-Kontext-dev-reference-depth-fusion-LORA

---

# Depth Reference Fusion LoRA

## 📝 Short description
A LoRA for **Flux Kontext Dev** that fuses a **reference image (left)** with a **depth map (right)**.  
It preserves **identity and style** from the reference while following the pose and structure from the depth map.  

**Trigger word:** `redepthkontext`

[Demo Video](https://youtu.be/cCwoPOkxq5c?si=T4tr3MWi7EUNJXIW)


![Input](https://huggingface.co/thedeoxen/FLUX.1-Kontext-dev-reference-depth-fusion-LORA/resolve/main/examples/1_a.png)
![Output](https://huggingface.co/thedeoxen/FLUX.1-Kontext-dev-reference-depth-fusion-LORA/resolve/main/examples/1_b.png)

---

### Example 2
![Input](https://huggingface.co/thedeoxen/FLUX.1-Kontext-dev-reference-depth-fusion-LORA/resolve/main/examples/2_a.png)
![Output](https://huggingface.co/thedeoxen/FLUX.1-Kontext-dev-reference-depth-fusion-LORA/resolve/main/examples/2_b.png)

---

### Example 3
![Input](https://huggingface.co/thedeoxen/FLUX.1-Kontext-dev-reference-depth-fusion-LORA/resolve/main/examples/3_a.png)
![Output](https://huggingface.co/thedeoxen/FLUX.1-Kontext-dev-reference-depth-fusion-LORA/resolve/main/examples/3_b.png)

---

## 📖 Extended description
This LoRA was primarily trained on **humans**, but it also works with **objects**.  
Its main purpose is to **preserve identity** — facial features, clothing, or object characteristics — from the reference image, while adapting them to the pose and composition defined by the depth map.

---

## ⚙️ How to use
- Concatenate two images side by side:  
  - **Left:** reference image (person or object)  
  - **Right:** depth map (grayscale or silhouette)  
- Add the trigger word **`redepthkontext`** in your prompt.  

### ✅ Example prompt
redepthkontext change depth map to photo

---

## 🎯 What it does
- Preserves character or object **identity** across generations.  
- Embeds the subject into the new pose/scene defined by the depth map.  
- Works best when the depth map has **similar proportions and sizes** to the reference.  

---

## ⚡ Tips
- Works better if the depth map is not drastically different in object scale.  
- Can be combined with text prompts for additional background/environment control.  

---

## 📌 Use cases
- Human portraits in different poses.  
- Consistent character design across multiple scenes.  
- Object transformations (cars, furniture, props) with depth-guided placement.  
- Storyboarding, comics, or animation frame generation.