This is not just a basic Video-to-Video workflow. It features an automated First Frame Pre-Processing Pipeline that performs a head, face, body, and clothing swap on the extracted first frame of your source video before feeding it into the MiniMax H3 Reference-to-Video engine.It allows you to seamlessly transfer motion, performance, and camera movement from a reference video while completely customizing the subject’s identity and outfit!<h2 id="key-features">🔥 Key Features</h2><ul><li>Auto First-Frame Extraction &amp; Swap: Automatically extracts the initial frame of your selected video duration and swaps the head/face/clothing with your uploaded image (<code>Picture 1</code>) using SAM 3.1 &amp; Flux Klein.</li><li>Dual Operating Modes: Easily toggle between full character pre-processing and direct video-to-video style transfer.</li></ul><h2 id="how-to-use">⚙️ How to Use</h2><h3 id="mode-a:-full-face-head-and-clothing-swap-(default)">🟢 Mode A: Full Face, Head &amp; Clothing Swap (Default)</h3><ol><li>Load Video: Upload your reference motion video into <code>LoadVideoUI</code> and adjust the start/end time. (Make sure the subject's face is clearly visible in the first frame of your selection).</li><li>Upload Target Image: Place your desired character/outfit image into <code>Picture 1</code>.</li><li>Switch Node: Set the <code>Image Switch (JPS)</code> node to <code>Select 2</code> (Extracted Frame).</li><li>Run the workflow!</li></ol><h3 id="mode-b:-direct-video-to-video-(no-pre-swap)">🔵 Mode B: Direct Video-to-Video (No Pre-Swap)</h3><ol><li>Upload your reference video into <code>LoadVideoUI</code>.</li><li>Upload your source image into <code>Picture 1</code>.</li><li>Bypass Swap Group: Enable bypass on the <code>FACE CLOTHE SWAP</code> group using the Fast Groups Bypasser.</li><li>Switch Node: Set the <code>Image Switch (JPS)</code> node to <code>Select 1</code> (Picture 1).</li><li>Run the workflow!</li></ol><h3 id="tips-and-troubleshooting">💬 Tips &amp; Troubleshooting</h3><ul><li>Face Visibility: The pre-processing pipeline targets frame #1 of your selected video range. Always ensure the face is visible at the very start frame for optimal SAM 3.1 segmentation.</li><li>Do not use acceleration. You get bad results.</li><li>Custom Prompts: You can adjust the <code>Prompt</code> node to fine-tune the retention vs. replacement ratios if needed.</li></ul>

Files with SHA256: e74218e3cbe0de1c402011cec0a4dd1fc1e9fccd6ff674d8f82a57fd1333394a