<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/2Mo8q4GUtdw" start="0"></iframe></div>☕ One coffee = one happy creator: <a target="_blank" rel="ugc" href="https://buymeacoffee.com/the_frizzy1">https://buymeacoffee.com/the_frizzy1</a><hr />Swap one person in your video for your own character, a person, an animal or a cartoon. Any clip length, the original sound kept, and it opens in App mode. This was my entry for the ComfyUI #OpenSourceHiggsfield challenge, Openjutsu track: OPENjutsu could not turn me into a dog, so I built my own.<h2 id="what-you-need">What you need</h2>✔ Custom nodes — None. Core ComfyUI only. ✔ ComfyUI version — 0.43.1 — the version it was tested on. Older ones may not have Start Loop / End Loop or the SCAIL-2 nodes ✔ VRAM — 12 GB — tested, not estimated ✔ System RAM — 32 GB tested. The README gives no peak figure for this one ✔ Tested on — RTX 3060 12 GB · 32 GB RAM · ComfyUI 0.43.1 (frontend 1.57.4) · Windows 11 ✔ Licence — Workflow MIT · SCAIL-2 MIT · SAM 3.1: see its model page<h2 id="models-to-download">Models to download</h2>Click a file name to download it. Put it in the folder shown, inside <code>ComfyUI/models/</code>. Every file name was read from the workflow <code>.json</code>, and ComfyUI's Missing models window offers them too. 28.6 GB is a lot to ask, so start the downloads before you start reading.Required — 7 files, 28.6 GB. All links checked on 2026-11-03.<h3 id="diffusion_models">diffusion_models/</h3>File: wan2.1_14B_SCAIL_2_int8_convrot.safetensors — 16.65 GB (SCAIL-2 model) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SCAIL-2/resolve/main/diffusion_models/wan2.1_14B_SCAIL_2_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/SCAIL-2/resolve/main/diffusion_models/wan2.1_14B_SCAIL_2_int8_convrot.safetensors</a>Put it here: ComfyUI/models/diffusion_models/<h3 id="loras">loras/</h3>File: wan2.1_SCAIL_2_DPO_lora_bf16.safetensors — 1.23 GB (quality LoRA) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SCAIL-2/resolve/main/loras/wan2.1_SCAIL_2_DPO_lora_bf16.safetensors">https://huggingface.co/Comfy-Org/SCAIL-2/resolve/main/loras/wan2.1_SCAIL_2_DPO_lora_bf16.safetensors</a>Put it here: ComfyUI/models/loras/File: lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors — 0.74 GB (speed LoRA) Download: <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">https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors</a>Put it here: ComfyUI/models/loras/<h3 id="text_encoders">text_encoders/</h3>File: umt5_xxl_fp8_e4m3fn_scaled.safetensors — 6.74 GB (text encoder) Download: <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">https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors</a>Put it here: ComfyUI/models/text_encoders/<h3 id="vae">vae/</h3>File: Wan2_1_VAE_bf16.safetensors — 0.25 GB (VAE) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Wan2_1_VAE_bf16.safetensors">https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Wan2_1_VAE_bf16.safetensors</a>Put it here: ComfyUI/models/vae/<h3 id="clip_vision">clip_vision/</h3>File: clip_vision_h.safetensors — 1.26 GB (character picture) Download: <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">https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors</a>Put it here: ComfyUI/models/clip_vision/<h3 id="checkpoints">checkpoints/</h3>File: sam3.1_multiplex_fp16.safetensors — 1.75 GB (finds the people) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors">https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors</a>Put it here: ComfyUI/models/checkpoints/<h2 id="inputs">Inputs</h2>It opens in App mode. Your video and a character picture, front view and full body if you can. Describe the result in one sentence, e.g. A realistic golden retriever dances in a bright room. Then Who is in the clip, e.g. man in red t-shirt, and What your character is, e.g. dog. Which person: <code>0</code> = the left one, <code>1</code> = the next one, empty = everyone. Seconds: 0 = the whole clip, try 3 s first. The video lands in <code>ComfyUI/output/SCAIL2 swap/</code>.SAM 3.1 finds up to 4 people that match "Who is in the clip" and sorts them left to right. One character per run.<h2 id="how-the-long-clips-work">How the long clips work</h2>SCAIL-2 makes 81 frames at a time. The workflow runs it inside ComfyUI's own Start Loop / End Loop, one segment per round. Every next round starts 76 frames later and gets the last 5 frames of the round before, drops them again and colour-matches to the previous round with reinhard_lab, so a long clip stays one take. The clip is padded to whole segments and cut back at the end.Settings I benchmarked and settled on: int8 model, DPO LoRA 1.0, lightx2v distill LoRA 0.8, 6 steps, CFG 1, shift 5, euler / simple, short side 512.<h2 id="speed-on-my-rtx-3060">Speed on my RTX 3060</h2><ul><li>9.4 s dance clip, whole clip, sound kept — 512x896, 24:09 wall</li></ul>That is 24 minutes for 9.4 seconds, so this is not a fast one. Try 3 s first before you run a whole clip. One run is all the README has: there is no VRAM or RAM column because those were not recorded for it.<h2 id="what-did-not-work">What did not work</h2><ul><li>Two characters in one run: left out on purpose, it was not reliable enough in my tests.</li><li>A face fix pass: same, left out.</li><li>One character per run is the hard limit, even when SAM 3.1 finds four people and swaps them all.</li></ul><h2 id="get-the-workflow">Get the workflow</h2><ul><li>GitHub: <a target="_blank" rel="ugc" href="https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/scail/scail2-character-swap-12gb">https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/scail/scail2-character-swap-12gb</a></li><li>Hugging Face mirror: <a target="_blank" rel="ugc" href="https://huggingface.co/The-frizzy1/The_frizzy1-Workflows/tree/main/workflows/scail/scail2-character-swap-12gb">https://huggingface.co/The-frizzy1/The_frizzy1-Workflows/tree/main/workflows/scail/scail2-character-swap-12gb</a></li></ul>More videos on this stuff: <a target="_blank" rel="ugc" href="https://www.youtube.com/playlist?list=UUGKDBMhTGqvlBZE9cF5d50Q">https://www.youtube.com/playlist?list=UUGKDBMhTGqvlBZE9cF5d50Q</a>

SCAIL-2 Character Swap 12GB — turn anyone in your video into your own character, any clip length, sound kept

v1.1.0. The README does not say what changed from v1.0.0 — see <code>changelog.md</code> in the repo.

Files with SHA256: 7fb4d14a85275be8331b0143ccfad2b90510fa2e6c0d1af5642e4aa3cc0b150d