<h1 id="refcontrol-flux.2-klein-9b-reference-pose-lora">RefControl FLUX.2 Klein 9B – Reference Pose LoRA</h1><h2 id="short-description">📝 Short description</h2>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: <code>apply pose from image 1 with reference from image 2</code><hr /><h2 id="examples">📊 Examples</h2>Each preview is a single combined image from ComfyUI: Pose → Reference → Result (left to right).Pose → Reference → Result<img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a%20(1).png" width="960" /><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a%20(2).png" width="960" /><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a%20(3).png" width="960" /><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a%20(4).png" width="960" /><img src="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora/resolve/main/images/a%20(5).png" width="960" /><span style="background-color:rgb(255, 255, 255);color:oklch(0.446 0.03 256.802);font-family:&quot;Source Sans Pro&quot;, ui-sans-serif, system-ui, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;, &quot;Noto Color Emoji&quot;;font-size:16.8px">---<h2 id="extended-description">📖 Extended description</h2>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.<hr /><h2 id="how-to-use">⚙️ How to use</h2><ol><li>Use the first image as the pose control map (skeleton / keypoints).</li><li>Use the second image as the reference (character, person, or object).</li><li>Add the trigger phrase <code>apply pose from image 1 with reference from image 2</code> in your prompt.</li><li>Adjust LoRA weight (recommended 0.8–1.0) depending on how strongly you want to preserve identity.</li></ol><h2 id="comfyui-requirenments">ComfyUI requirenments</h2>Pose extraction in the included workflow uses DWPose (via <a target="_blank" rel="ugc" href="https://github.com/Fannovel16/comfyui_controlnet_aux">comfyui_controlnet_aux</a>):<a target="_blank" rel="ugc" href="https://github.com/Fannovel16/comfyui_controlnet_aux">https://github.com/Fannovel16/comfyui_controlnet_aux</a><h3 id="base-model">Base model</h3>Trained on and recommended with <code>black-forest-labs/FLUX.2-klein-base-9B</code>. The undistilled Base variant is intended for LoRA training and custom pipelines (~50 inference steps, <code>guidance_scale</code> ~4.0).The LoRA also works with the 4-step distilled <code>black-forest-labs/FLUX.2-klein-9B</code> for faster inference (~4 steps, <code>guidance_scale</code> ~1.0), but quality may be slightly lower — especially for identity and pose fidelity — compared to the Base model.<h3 id="example-prompt">✅ Example prompt</h3><pre><code>apply pose from image 1 with reference from image 2
</code></pre><hr /><h2 id="what-it-does">🎯 What it does</h2><ul><li>Preserves character or object identity across generations.</li><li>Adapts the subject to a new pose or action defined by the skeleton map.</li><li>Works best when the pose map has similar proportions and scale to the reference.</li></ul><hr /><h2 id="tips">⚡ Tips</h2><ul><li>Best results when the pose map is not drastically different in body scale or framing from the reference.</li><li>Combine with text prompts to refine background, lighting, or mood.</li><li>Can be combined with other RefControl LoRAs (depth, lineart, canny) on compatible pipelines for multi-constraint generation.</li><li>DWPose skeleton maps on a black background work well as control input.</li></ul><hr /><h2 id="use-cases">📌 Use cases</h2><ul><li>Character posing for illustrations, comics, or storyboards.</li><li>Consistent character design across different poses.</li><li>Re-posing stylized characters while keeping their identity.</li><li>Creating animation keyframes from static references.</li></ul><hr /><h2 id="files">📦 Files</h2><ul><li>Weights: <code>refcontrol_v2_poses.safetensors</code></li><li>ComfyUI workflow: <code>refcontrol_pose_flux_klein_9b.json</code></li><li>Repo: <a target="_blank" rel="ugc" href="https://huggingface.co/thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora">thedeoxen/refcontrol-FLUX.2-klein-9B-reference-pose-lora</a></li></ul>

Files with SHA256: a22ec6a5406ccdb7a247684a40f96b52a83520efa00ebe56528cf54d0e5d473b