Make identical to wan777: base Wan2.2-I2V-A14B + wan777 code/deps/gradio

Revert model to WAMU-Merge-VisualEffects lightning (user: base+lightx2v anatomy bad)

wan666: revert model to base Wan2.2-I2V-A14B + lightx2v 4-step LoRA

Raise GPU duration cap 140 -> 145 (~290s reported, still under 300 cap)

Cap GPU duration reservation at 140s to clear free-tier per-call limit

Increase BASE_STEP_DURATION 5->15 (reserve enough ZeroGPU time to finish 10s), matching wan222/wan444

Upgrade to WAMU_v3 + default 4 steps (faster)

Update app.py

Update app.py

Update requirements.txt

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Upload 4 files

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

test

Update README.md

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update README.md