<h2 id="overview">Overview</h2>Using Wan Animate 2.2, transfer motions from Reference Video to animate the character in Reference Image, or replace the character in Reference Video with the character in Reference Image. Tested with videos up to ~20 seconds long but theoretically should support unlimited length.Still a WIP as there are some rough edges (certain reference videos and images work better than others, character identity drifts the longer a video goes), but releasing it as I don't see other similar workflows available on Civitai yet.<h2 id="key-features">Key Features</h2><ul><li>Using <code>WanVideo Block Swap</code> &amp; <code>WanVideo Animate Embeds</code>, this workflow splits long videos into small "windows" of 81 frames (~5 seconds) so that theoretically unlimited video length can be supported</li><li>Using RIFE VFI, this workflow interpolates the generated frames so that buttery smooth video of 60FPS or more (configurable in workflow) can be generated</li></ul><h2 id="custom-comfyui-nodes">Custom ComfyUI Nodes</h2><ul><li><a target="_blank" rel="ugc" href="https://github.com/Fannovel16/comfyui_controlnet_aux">ControlNet Auxiliary Preprocessors</a></li><li><a target="_blank" rel="ugc" href="https://github.com/pythongosssss/ComfyUI-Custom-Scripts">ComfyUI-Custom-Scripts</a></li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-KJNodes">KJNodes for ComfyUI</a></li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-WanAnimatePreprocess">WanAnimate Preprocessors</a></li><li><a target="_blank" rel="ugc" href="https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite">VideoHelperSuite</a></li><li><a target="_blank" rel="ugc" href="https://github.com/Fannovel16/ComfyUI-Frame-Interpolation">ComfyUI Frame Interpolation (ComfyUI VFI)</a></li></ul><h2 id="model-download-links">Model Download Links</h2><ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.2-Animate-14B-GGUF/tree/main">Wan 2.2 Animate 14B GGUF</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors">LightX2V I2V 14B 480p cfg_step_distill_rank64_bf16</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/LoRAs/Wan22_relight/WanAnimate_relight_lora_fp16.safetensors">WanAnimate Relight LoRA fp16</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors">UMT5 XXL fp8 e4m3fn_scaled</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors">CLIP Vision_H</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors">Wan 2.1 VAE</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Wan-AI/Wan2.2-Animate-14B/blob/main/process_checkpoint/det/yolov10m.onnx">YOLO v10-M</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/JunkyByte/easy_ViTPose/blob/main/onnx/wholebody/vitpose-l-wholebody.onnx">ViTPose-L Wholebody</a></li></ul><h2 id="important-notes">Important Notes</h2>Generating at 480p (480 x 832 pixels), system RAM usage peaks at around 47.8GB and VRAM usage peaks at around 15GB so you would need a system with ≥16GB VRAM, ≥48GB RAM to run this workflow as-is.You might be able to lower the system requirements by tweaking the various settings.

Wan 2.2 Animate for Long Videos (≥30 secs, requires ≥16GB VRAM, ≥48GB RAM)

<ul><li>Updated to use <code>vitpose-h</code> (Huge) + <code>yolov10l</code> (Large) instead of <code>vitpose-l</code> (Large) + <code>yolov10m</code> (Medium) for better pose detection.</li><li>Updated ref_image and ref_video resize methods for better face &amp; pose detection</li></ul>

Files with SHA256: 3f4da2f4905f1710dcdb08a015634223aeadb6a1ae4ea068b41a6433e8d3d2b9