thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora
RefControl FLUX.2 Klein 9B โ Reference Pose LoRA
๐ 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
<Gallery />
๐ Examples
Each preview is a single combined image from ComfyUI: Pose โ Reference โ Result (left to right).
<table> <thead> <tr> <th>Pose โ Reference โ Result</th> </tr> </thead> <tbody> <tr> <td><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a (1).png" width="960" /></td> </tr> <tr> <td><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a (2).png" width="960" /></td> </tr> <tr> <td><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a (3).png" width="960" /></td> </tr> <tr> <td><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a (4).png" width="960" /></td> </tr> <tr> <td><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a (5).png" width="960" /></td> </tr> </tbody> </table> ---
๐ 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 โ facial features, hairstyle, clothing, or object details โ 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 โ 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.
โ๏ธ How to use
- Use the first image as the pose control map (skeleton / keypoints).
- Use the second image as the reference (character, person, or object).
- Add the trigger phrase `apply pose from image 1 with reference from image 2` in your prompt.
- Adjust LoRA weight (recommended 0.8โ1.0) 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/comfyuicontrolnetaux
Base model
Trained on and recommended with `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` for faster inference (~4 steps, guidance_scale ~1.0), but quality may be slightly lower โ especially for identity and pose fidelity โ compared to the Base model.
โ Example prompt
apply pose from image 1 with reference from image 2๐ฏ 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.
โก 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.
๐ 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.
๐ฆ Files
- Weights: `refcontrol_v2_poses.safetensors`
- ComfyUI workflow: `refcontrol_pose_flux_klein_9b.json`
- Repo: thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora
