dinhvietduy/wan2-2-fp8da-aoti-faster

compile doesn't like resize

attempt resize

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 README.md

Update optimization.py

trying with lora_scale==1

Update app.py

Upload kill_bill.jpeg

Update optimization.py (#4)

Update optimization.py

Update app.py

update aoti compile (#3)

Update optimization.py

move lora loading into optim code to work on CUDA memory (#2)

Update app.py

Update app.py

Update README.md

Update app.py

Upload wan22_input_2.jpg

Update README.md

Update app.py

Update app.py

Update requirements.txt

Update app.py

Update app.py

Update app.py

add dual lora loading (#1)

Update app.py

Update app.py

Update app.py

Update app.py

lora

Revert "ZeroGPUWeights debug"

THE fix

ZeroGPUWeights debug

Revert "ZeroGPUWeights debug"

Oops

ZeroGPUWeights debug

Update optimization.py

Update optimization.py

Update optimization.py

Wan 2.2

Upload wan_i2v_input.JPG