Switch apply-step from Wan-Animate to Wan2.1-VACE masked inpaint: regenerates ONLY the clothing region, copies face/hair/skin/motion/background from the source at original sharpness. UI: video + prompt -> video. VACE on 'large' (49 frames @6fps, ~265 quota incl remote FireRed) fits a FREE account. Boot probes reference_images + pack size. Removed dead wan_engine helpers; stopped purging the VACE model cache.

Adopt alexnasa/Wan2.2-Animate-ZEROGPU mechanism wholesale: official wan package, GPU pose (torch 2.8/CUDA12 + onnxruntime-gpu), clip slicing. Default mode = Pose Retarget. Root cause of our slowness was CUDA-13 forcing onnxruntime pose onto CPU (1.87s/frame).

Review fixes: guard null xlarge_threshold in probe; derive duration_factor instead of hardcoding 1.5; _HAS_SEG_LEN defaults True (don't brick free on an inspect hiccup); UI/API-guide say 10.0s for free tier

Fix remote FireRed TypeError (send int seed/steps, not float); surface remote error detail; fix video arg format in API guide

Free-tier support: segment_frame_length lever (seg 41/5 steps) so a FREE 300s/day account fits one run (290 quota); make quota_probe a 0-cost info endpoint (was 580 quota, unusable by free accounts)

API: name the status output, rewrite API_GUIDE to match the real 3-input signature

Restore Wan-VACE prompt-based clothing editor (revert Animate swap)

Replace with alexnasa/Wan2.2-Animate-ZEROGPU

Process first 10s consistently + stable /change_clothes API + API guide