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
| Reference | Depth | Result |
|---|---|---|
📖 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
- Use first image as depth reference, second image input.
- Add the trigger word
refcontrolin your prompt. - 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.
The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps, guidance_scale ~4.0).
✅ Example prompt
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.