---
title: refcontrol-FLUX.2-klein-9B-reference-pose-lora
canonical_url: "https://www.modelscope.cn/models/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora"
md_url: "https://www.modelscope.cn/models/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora.md"
repository: thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora
last_updated: 2026-06-26
license: apache-2.0
pipeline_tag: image-to-image
tasks:
- image-to-image
base_model:
- black-forest-labs/FLUX.2-klein-base-9B
base_model_relation: adapter
parameters: 82.8M
tensor_type:
- BF16
library_name:
- lora
- safetensors
- pytorch
frameworks:
- pytorch
supports_inference: img2img
downloads: 129
stars: 2
tags:
- flux
- flux2
- klein
- pose
- openpose
- controlnet
- refcontrol
- img2img
- image
- editing
- lora
---
# refcontrol-FLUX.2-klein-9B-reference-pose-lora
> refcontrol-FLUX.2-klein-9B-reference-pose-lora - thedeoxen 在 ModelScope 开源的模型。RefControl FLUX.2 Klein 9B – Reference Pose LoRA
thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora 是 ModelScope 魔搭社区上的 82.8M 参数image-to-image模型，采用 apache-2.0 许可，基于 black-forest-labs/FLUX.2-klein-base-9B 构建，并支持在线推理（img2img）。
- **Repository**: thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora
- **License**: apache-2.0
- **Tasks**: image-to-image
- **Parameters**: 82.8M
- **Base model**: black-forest-labs/FLUX.2-klein-base-9B
- **Online inference**: img2img
- **Tags**: flux, flux2, klein, pose, openpose, controlnet, refcontrol, img2img, image, editing, lora
- **Downloads**: 129
- **Stars**: 2
- **Last updated**: 2026-06-26
Source: https://www.modelscope.cn/models/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora
---
# RefControl FLUX.2 Klein 9B – Reference Pose LoRA
## 📝 Short description
A LoRA for **FLUX.2 Klein 9B Base** that fuses a **reference image** (identity) with a **pose control map** (skeleton / keypoints).
It preserves **identity and style** from the reference while following the **body pose and structure** from the pose map.
**Trigger phrase:** `apply pose from image 1 with reference from image 2`
---
## 📊 Examples
Each preview is a **single combined image** from ComfyUI: **Pose → Reference → Result** (left to right).
| Pose → Reference → Result |
.png) |
.png) |
.png) |
.png) |
.png) |
---
## 📖 Extended description
This LoRA was primarily trained on **humans**, but it also works with **stylized characters** and some objects.
Its main purpose is to **preserve identity** — facial features, hairstyle, clothing, or object details — from the reference image, while adapting the subject to the **pose and skeleton structure** defined by the control map.
**FLUX.2 Klein 9B Base** already handles reference + pose transfer reasonably well with the right prompt alone. This LoRA builds on that capability — it improves consistency and **better preserves character identity and pose fidelity** than the base model without LoRA.
Part of the **RefControl** family: reference + control fusion for consistent, controllable generation on **FLUX.2 Klein 9B Base**.
---
## ⚙️ How to use
1. Use the **first image** as the **pose control map** (skeleton / keypoints).
2. Use the **second image** as the **reference** (character, person, or object).
3. Add the trigger phrase **`apply pose from image 1 with reference from image 2`** in your prompt.
4. Adjust LoRA weight (recommended **0.8–1.0**) depending on how strongly you want to preserve identity.
## ComfyUI requirenments
Pose extraction in the included workflow uses **DWPose** (via [comfyui_controlnet_aux](https://github.com/Fannovel16/comfyui_controlnet_aux)):
https://github.com/Fannovel16/comfyui_controlnet_aux
### Base model
Trained on and recommended with [`black-forest-labs/FLUX.2-klein-base-9B`](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B).
The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps, `guidance_scale` ~4.0).
The LoRA also works with the **4-step distilled** [`black-forest-labs/FLUX.2-klein-9B`](https://huggingface.co/black-forest-labs/FLUX.2-klein-9B) for faster inference (~4 steps, `guidance_scale` ~1.0), but **quality may be slightly lower** — especially for identity and pose fidelity — compared to the Base model.
### ✅ Example prompt
```
apply pose from image 1 with reference from image 2
```
---
## 🎯 What it does
- Preserves **character or object identity** across generations.
- Adapts the subject to a **new pose or action** defined by the skeleton map.
- Works best when the pose map has **similar proportions and scale** to the reference.
---
## ⚡ Tips
- Best results when the pose map is not drastically different in body scale or framing from the reference.
- Combine with **text prompts** to refine background, lighting, or mood.
- **DWPose** skeleton maps on a **black background** work well as control input.
---
## 📌 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.
---
## 📦 Files
- **Weights:** [`refcontrol_v2_poses.safetensors`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/blob/main/refcontrol_v2_poses.safetensors)
- **ComfyUI workflow:** [`refcontrol_pose_flux_klein_9b.json`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/blob/main/refcontrol_pose_flux_klein_9b.json)
- **Repo:** [thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora)