<h2 id="refcontrol-flux-kontext-reference-pose-lora">RefControl Flux Kontext – Reference Pose LoRA</h2><h3 id="short-description">📝 Short description</h3>A LoRA for Flux Kontext Dev that fuses a reference image (left) with a pose control map (right). It preserves identity and style from the reference while following the pose and body structure from the control.Trigger word: <code>refcontrolpose</code>Workflow <a target="_blank" rel="ugc" href="https://civarchive.com/models/1894175?modelVersionId=2144052">https://civarchive.com/models/1894175</a>[Demo Video] <a target="_blank" rel="ugc" href="https://youtu.be/8eTjC7InE44">https://youtu.be/8eTjC7InE44</a>Huging face page: <a target="_blank" rel="ugc" href="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora">https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora</a><h3 id="examples">📊 Examples</h3>InputOupttut<a target="_blank" rel="ugc" href="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/1a.png"><img src="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/1a.png" alt="ref1" /></a><a target="_blank" rel="ugc" href="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/1b.png"><img src="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/1b.png" alt="res1" /></a><a target="_blank" rel="ugc" href="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/3b.png"><img src="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/3b.png" alt="res3" /></a><a target="_blank" rel="ugc" href="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/4a.png"><img src="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/4a.png" alt="ref4" /></a><a target="_blank" rel="ugc" href="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/4b.png"><img src="https://huggingface.co/thedeoxen/refcontrol-flux-kontext-reference-pose-lora/resolve/main/examples/4b.png" alt="res4" /></a><hr /><h3 id="extended-description">📖 Extended description</h3>This LoRA was primarily trained on humans, but it can also be applied to stylized characters and some objects. Its main goal is to transfer identity — facial features, hairstyle, clothing, or object details — from the reference image, while adapting them to the pose and skeleton structure defined by the control map.<hr /><h2 id="how-to-use">⚙️ How to use</h2><ol><li>Concatenate two images side by side:<ul><li>Left: reference image (character, person, or object).</li><li>Right: pose control map (skeleton, keypoints).</li></ul></li><li>Add the trigger word <code>refcontrolpose</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><h3 id="worklow:">Worklow:</h3>For workflow you need to install in ComfyUI:<ul><li><a target="_blank" rel="ugc" href="https://github.com/Fannovel16/comfyui_controlnet_aux">comfyui_controlnet_aux</a></li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-KJNodes">comfyui-kjnodes</a></li></ul><h3 id="example-prompt">✅ Example prompt</h3>refcontrolpose change pose to photo with reference from left side<hr /><h2 id="what-it-does">🎯 What it does</h2><ul><li>Preserves character identity across generations.</li><li>Adapts the subject to a new pose or action.</li><li>Works well for character consistency in sequential generations.</li></ul><hr /><h2 id="tips">⚡ Tips</h2><ul><li>Best results when the pose map has similar proportions to the reference image.</li><li>Combine with text prompts to refine background or mood.</li><li>Can be chained with other RefControl LoRAs (depth, lineart, canny) for multi-constraint generation.</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>

Files with SHA256: e22de9c78edcd026a7c2e31959e73cc286f357cce86f85c441c8ece3bcd98a7f