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

Restore original wan222 (base Wan2.2-I2V-A14B, non-xlarge) + keep 145 cap

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

wan222: revert model to base Wan2.2-I2V-A14B + official lightx2v 4-step LoRA

Unify with wan555: identical app.py + release stack + gradio 6.0.1 + WAMU model

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

Upgrade to WAMU_v3 + default 4 steps (faster)

Update app.py

Update requirements.txt (#10)

Update requirements.txt

Update README.md (#8)

Update README.md

Update README.md (#7)

Update app.py

Update requirements.txt

Update app.py

test update rife

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

Update app.py

Update app.py

Update app.py

Update app.py

Update requirements.txt

Create packages.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update README.md

Update app.py

Update app.py

Update app.py

aoti-blocks-load (#23)

PyTorch manual upgrade not needed anymore (#22)

Update app.py

restart with commit

Update optimization_utils.py