convert TurboWan2.2-I2V-A14B-720P(https://modelscope.cn/models/TurboDiffusion/TurboWan2.2-I2V-A14B-720P/summary) to TurboWan2.2-I2V-A14B-Diffusers convert script https://github.com/IPostYellow/TurboWan_to_Diffusers/blob/main/convert_turbowan_to_diffusers.py
To use in sglang bash server:
sglang serve \
--model-path /home/admin/TurboWan2.2-I2V-A14B-Diffusers \
--dit-cpu-offload false \
--text-encoder-cpu-offload false \
--image-encoder-cpu-offload false \
--vae-cpu-offload false \
--pin-cpu-memory false \
--num-gpus 2 \
--tp-size 2
send request:
import requests
prompt = "POV selfie video, ultra-messy and extremely fast. A white cat in sunglasses stands on a surfboard with a neutral look when the board suddenly whips sideways, throwing cat and camera into the water; the frame dives sharply downward, swallowed by violent bursts of bubbles, spinning turbulence, and smeared water streaks as the camera sinks. Shadows thicken, pressure ripples distort the edges, and loose bubbles rush upward past the lens, showing the camera is still sinking. Then the cat kicks upward with explosive speed, dragging the view through churning bubbles and rapidly brightening water as sunlight floods back in; the camera races upward, water streaming off the lens, and finally breaks the surface in a sudden blast of light and spray, snapping back into a crooked, frantic selfie as the cat resurfaces."
response = requests.post("http://localhost:30000/v1/videos",
files={'prompt': (None,prompt), 'size': (None,'720x1280'),'reference_url':(None,"https://raw.githubusercontent.com/IPostYellow/TurboWan_to_Diffusers/refs/heads/main/input_image/i2v_input_0.jpg"),'num_inference_steps':(None,"4"),'fps':(None,"16"),'num_frames':(None,"81"),'seed':(None,"0")})
print("Status Code:", response.status_code)
print("Response Body:", response.text)