---
license: apache-2.0
base_model: TurboDiffusion/TurboWan2.1-T2V-14B-720P
tags:
- text-to-video
- diffusion
- video-generation
- turbodiffusion
- wan2.1
pipeline_tag: text-to-video
---

convert TurboWan2.1-T2V-14B-720P(https://modelscope.cn/models/TurboDiffusion/TurboWan2.1-T2V-14B-720P/summary) to TurboWan2.1-T2V-14B-Diffusers
convert script https://github.com/IPostYellow/TurboWan_to_Diffusers/blob/main/convert_turbowan_to_diffusers.py

To use this model in sglang, change dirname `TurboWan2.1-T2V-14B-720P-Diffusers` to `TurboWan2.1-T2V-14B-Diffusers`

bash server:
```bash
sglang serve \
    --model-path  /path/TurboWan2.1-T2V-14B-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 1
```

send request:
```python
import requests
prompt="A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about."
headers = {
    "Content-Type": "application/json",
}
requests.post("http://localhost:3000/v1/videos",headers=headers,json={'prompt': prompt, 'size': '1280x720','num_inference_steps':4,'fps':16,'num_frames':81,'negative_prompt':None,'seed':0,})
```