Skip to main content
POST
/
api
/
v3
/
alibaba
/
wan-2.5-fast
/
text-to-video
wan-2.5-fast (text to video)
curl --request POST \
  --url https://api.example.com/api/v3/alibaba/wan-2.5-fast/text-to-video
Generate videos from text prompts using Qwen’s wan-2.5-fast model with GPTProto format API. 
curl --location 'https://gptproto.com/api/v3/alibaba/wan-2.5-fast/text-to-video' \
--header 'Authorization: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "prompt": "a cat",
    "negative_prompt": "",
    "audio": "",
    "size": "1280*720",
    "duration": "5",
    "enable_prompt_expansion": "false",
    "seed": -1
}'

​
Response

{
  "task_id": "abc123def456",
  "status": "processing",
  "message": "Video generation task submitted successfully"
}

​
Parameters

ParameterTypeRequiredDefaultDescription
promptstring✅ Yes-Text description for the video generation, describing the desired scene, actions, and style
negative_promptstring❌ No""Negative prompt to specify what should not appear in the generated video. Leave empty if not needed
audiostring❌ No""URL of the audio file to be added to the generated video. Leave empty for no audio
sizestring❌ No"1280*720"Video resolution/size. Format: width*height (e.g., 1280*720, 1920*1080)
durationstring❌ No"5"Duration of the generated video in seconds
enable_prompt_expansionstring❌ No"false"Enable automatic prompt expansion and optimization. Set to "true" or "false"
seedinteger❌ No-1Random seed for generation reproducibility. Set to -1 for random generation