---
title: refcontrol-flux-kontext-reference-pose-lora
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/refcontrol-flux-kontext-reference-pose-lora"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/refcontrol-flux-kontext-reference-pose-lora.md"
repository: AI-ModelScope/refcontrol-flux-kontext-reference-pose-lora
last_updated: 2026-06-16
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
supports_inference: img2img
downloads: 189
stars: 4
tags:
  - flux
  - kontext
  - img2img
  - controlnet
  - flux-kontext
  - image
  - editing
  - lora
---

# refcontrol-flux-kontext-reference-pose-lora

> refcontrol-flux-kontext-reference-pose-lora - AI-ModelScope 在 ModelScope 开源的模型。license: apache-2.0 basemodel: black-forest-labs/FLUX.1-Kontext-dev pipelinetag: image-to-image ---

AI-ModelScope/refcontrol-flux-kontext-reference-pose-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，并支持在线推理（img2img）。

- **Repository**: AI-ModelScope/refcontrol-flux-kontext-reference-pose-lora
- **License**: apache-2.0
- **Tasks**: image-to-image
- **Parameters**: 171.8M
- **Base model**: black-forest-labs/FLUX.1-Kontext-dev
- **Online inference**: img2img
- **Tags**: flux, kontext, img2img, controlnet, flux-kontext, image, editing, lora
- **Downloads**: 189
- **Stars**: 4
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/models/AI-ModelScope/refcontrol-flux-kontext-reference-pose-lora

---

license: apache-2.0
base_model:
- black-forest-labs/FLUX.1-Kontext-dev
pipeline_tag: image-to-image
---

# RefControl Flux Kontext – Reference Pose LoRA

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

**Trigger word:** `refcontrolpose`
---
[🎥 Demo Video](https://youtu.be/8eTjC7InE44)

---
## 📊 Examples
| Input | Oupttut |
|-----------|--------|
| ![ref1](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/1a.png) | ![res1](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/1b.png) |
| ![ref2](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/2a.png) | ![res2](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/2b.png) |
| ![ref3](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/3a.png) | ![res3](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/3b.png) |
| ![ref4](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/4a.png) | ![res4](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/4b.png) |
| ![ref5](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/5a.png) | ![res5](https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/5b.png) |

---

## 📖 Extended description
This LoRA was primarily trained on **humans**, but it can also be applied to stylized characters and some objects.  
Its main goal is to **transfer identity** — facial features, hairstyle, clothing, or object details — from the **reference image**, while adapting them to the **pose and skeleton structure** defined by the control map.

---

## ⚙️ How to use
1. Concatenate two images side by side:  
   - **Left:** reference image (character, person, or object).  
   - **Right:** pose control map (skeleton, keypoints).  
2. Add the trigger word `refcontrolpose` in your prompt.  
3. Adjust LoRA weight (recommended **0.8–1.0**) depending on how strongly you want to preserve identity.  


### Worklow:
You can find workflow in the workflows folder.

For workflow you need to install in ComfyUI:

- [comfyui_controlnet_aux](https://github.com/Fannovel16/comfyui_controlnet_aux)
- [comfyui-kjnodes](https://github.com/kijai/ComfyUI-KJNodes)


### ✅ Example prompt

refcontrolpose change pose to photo with reference from left side

---

## 🎯 What it does
- Preserves **character identity** across generations.  
- Adapts the subject to a **new pose or action**.  
- Works well for **character consistency** in sequential generations.  

---

## ⚡ Tips
- Best results when the pose map has **similar proportions** to the reference image.  
- Combine with **text prompts** to refine background or mood.  
- Can be chained with other RefControl LoRAs (depth, lineart, canny) for **multi-constraint generation**.  

---

## 📌 Use cases
- Character posing for illustrations, comics, or storyboards.  
- Consistent **character design** across different poses.  
- Re-posing **stylized characters** while keeping their identity.  
- Creating **animation keyframes** from static references.  

---