메뉴
SCAIL-2 in-video character replacement on WAN 2.1. WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the tuning/compositing pitfalls
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/artokun/comfyui-mcp --skill wan-scail-replacement명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | wan-scail-replacement |
| description | SCAIL-2 in-video character replacement on WAN 2.1. WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the tuning/compositing pitfalls |
| globs | ["**/*.json"] |
SCAIL-2 (zai-org, on WAN 2.1 14B) replaces the person in a driving video with a
character you supply as a reference image, end-to-end, with no pose maps, and
with multi-character support. It is the successor to WAN Animate / motion
transfer for the "swap the subject, keep the motion" job. The official ComfyUI
template is video_wan21_scail2_character_replacement_int8, built around
WanSCAILToVideo (+ SCAIL2ColoredMask) with a SAM3 mask driving where the
character goes.
This skill documents the non-obvious behaviours that cost a full multi-minute render to discover. It is not a from-scratch graph. Start from the official template and apply the guidance below.
In replacement_mode: true, the reference image's FRAMING controls the output
character's SIZE as well as its appearance. The SAM3 mask controls where the
character is placed; the reference image controls how large.
Measured on a 720x1280 driving clip where the subject occupied ~30% of frame height (subject bbox 363 px):
| Reference framing | Person bbox in output | vs driving subject |
|---|---|---|
| Full-bleed portrait (person ~93% of frame) | 621 px | 1.71x oversized |
| Reframed (person ~34% of frame) |
| 364 px |
| 1.003x — correct |
After reframing, top/bottom registration matched the driving subject within 1 px (the character stands on the same ground plane at the same height). Pose transfer was correct in both cases. Only the scale was wrong, which makes it easy to misread as "the model works" until you A/B against the source.
Guidance: pad or reframe the reference before you render.
Pad/reframe the reference image onto a canvas at the working resolution so the person occupies roughly the same fraction of frame height as the subject in the driving video. A full-bleed portrait reference against a wide-shot driving clip renders the character oversized in proportion to the framing mismatch.
It is a trap because the template's on-canvas notes do not state it, and it does not show up in the popular Civitai motion-transfer workflows. Those run animation mode, where the reference legitimately fills the frame.
Running the lightx2v distill LoRA at 0.8 with ModelSamplingSD3 shift 5 (the
settings the popular Civitai workflow uses) improves colour and detail versus
1.0 / shift 8. It also increases adherence to the driving video enough
that original-subject details bleed onto the replacement character. In one
run the original golfer's neon-yellow shoe appeared on a replacement character
who wears white shoes in the reference (same seed, same reference, only those two
params changed). If you see source details you didn't ask for, raise the LoRA
strength / shift back toward 1.0 / shift 8.
The raw SCAIL-2 output shows a measurable colour error (background ~-5 per channel from the VAE round-trip; the character loses red ~2.4x faster than green, which reads as a slight green cast). It is tempting to composite the generated character back over the original plate through the SAM3 mask to "correct" it. Don't. It measures better but looks worse:
SCAIL-2 resolves colour, edges, grip and occlusion jointly; correcting any one of them in isolation breaks the others. Leave the raw output alone.
The template's int8 build was exercised with:
wan2.1_14B_SCAIL_2_int8_convrot, the SCAIL-2 modelwan2.1_SCAIL_2_DPO_lora_bf16, the DPO LoRAlightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16, the distill LoRA (see tuning note)Wan2_1_VAE_bf16umt5_xxl_fp8_e4m3fn_scaled, the text encoderclip_vision_hsam3.1_multiplex_fp16, the SAM3 mask modelVRAM: ~22.2 GB peak at 576x1024 / 81-frame chunks on a 24 GB card.
wan-t2v-video, wan-flf-video for other WAN 2.x video pipelinesdirector for multi-shot scene direction for video pipelinespacks/ and observed renders; not a vendor prompting guide.