CIVITAI / Workflows

SCAIL-2 Single-Person Biological Long-Video Driving Workflow

Watch the full video first if you want to understand how this SCAIL-2 single-person long-video driving workflow works in practice. The video shows how one reference character can follow a single-person driving video, while the workflow keeps identity, body structure, motion rhythm, silhouette stability, and long-video continuity more consistent. This ComfyUI workflow is designed for SCAIL-2 single-person biological long-video driving. Its main purpose is to animate one reference character by following the motion of one person in a driving video. This is not a local character replacement workflow. It is a skeleton-guided animation route where the reference character follows the full-body movement from the source video while preserving the character’s visual identity. The workflow is built around wan2.1_14B_SCAIL_2_fp8_scaled.safetensors as the main SCAIL-2 model. It also uses WAN VAE, UMT5 XXL WAN text encoding, CLIP Vision identity encoding, SAM3 subject tracking, SCAIL2ColoredMask, WanSCAILToVideo, SamplerCustom, VAEDecode, ForLoop continuation, frame trimming, ColorTransfer, final video combining, and original audio restoration. A multi-LoRA enhancement chain is also included, using modules such as LightX2V, WanAnimate relight, Wan2.2 Lightning I2V, FastWan 480p, Wan21 PusaV1, Wan2.2 Fun InP, and stage-based enhancement LoRAs. The first important rule of the workflow is strict input alignment. Both the reference image and the driving video are aligned to 512×896 before entering SAM3, CLIPVision, and SCAIL. This helps avoid mask mismatch, pose instability, identity drift, and unexpected body deformation caused by inconsistent input dimensions. The second key rule is single-subject tracking. SAM3 is configured with max_objects=1. SCAIL2ColoredMask uses object_indices=0 and sort_by=area. This tells the workflow to focus on one main character, select the dominant subject area, and use that tracked subject as the motion target. This is useful for single-person dance, character animation, creature motion transfer, digital human testing, mascot animation, anime character motion driving, and stylized biological character videos. The workflow uses replacement_mode=false. This means the goal is skeleton-guided driving rather than local replacement. The reference image provides the character identity, the driving video provides the motion structure, and the mask