---
license: apache-2.0
base_model:
- black-forest-labs/FLUX.2-klein-base-4B
pipeline_tag: image-to-image
tags:
- flux
- flux2
- klein
- depth
- controlnet
- refcontrol
- img2img
- image
- editing
- lora
library_name: diffusers
---
# RefControl FLUX.2 Klein 4B - Reference Depth LoRA
## 📝 Short description
A LoRA for **FLUX.2 Klein 4B Base** 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:** `refcontrol`
---
## 📊 Examples
---
## 📖 Extended description
This LoRA was primarily trained on **humans**, but it also works with **objects** and stylized characters.
Its main purpose is to **preserve identity** - facial features, clothing, style, or object characteristics - from the reference image, while adapting the subject to the **pose and composition** defined by the depth map.
Part of the **RefControl** family: reference + control fusion for consistent, controllable generation on **FLUX.2 Klein 4B Base**.
---
## ⚙️ How to use
1. Use first image as depth reference, second image input.
2. Add the trigger word **`refcontrol`** in your prompt.
3. Adjust LoRA weight (recommended **0.8-1.0**) depending on how strongly you want to preserve identity.
## ComfyUI requirenments
For extracting depth you need to install nodes with depth estimation in workflow used:
https://github.com/Fannovel16/comfyui_controlnet_aux
### Base model
Use with [`black-forest-labs/FLUX.2-klein-base-4B`](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B).
The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps, `guidance_scale` ~4.0).
### ✅ Example prompt
```text
refcontrol
```
---
## 🎯 What it does
- Preserves **character or object identity** across generations.
- Embeds the subject into a **new pose or scene** defined by the depth map.
- Works best when the depth map has **similar proportions and scale** to the reference.
---
## ⚡ Tips
- Best results when the depth map is not drastically different in object scale from the reference.
- Combine with **text prompts** to refine background, lighting, or mood.
- Can be combined with other **RefControl** LoRAs (pose, lineart, canny) on compatible pipelines for multi-constraint generation.
---
## 📌 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.
---
## 📦 Files
- **Weights:** [`flux2_klein_4b_refcontrol_depth.safetensors`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-4B-reference-depth-lora/blob/main/flux2_klein_4b_refcontrol_depth.safetensors)
- **ComfyUI workflow:** [`image_flux2_klein_image_edit_4b_refcontrol_depth.json`](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-4B-reference-depth-lora/blob/main/image_flux2_klein_image_edit_4b_refcontrol_depth.json)
- **Repo:** [thedeoxen/refcontrol-FLUX.2-klein-4B-reference-depth-lora](https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-4B-reference-depth-lora)
