wan2.7-i2v
Wan2.7-I2V is a Tusheng video model in the Wanxiang 2.7 video series, which uses images as a starting point to generate dynamic videos. Its core upgrade lies in the comprehensive strengthening of "deductive ability": the emotions of literary dramas are delicate and natural, the action scenes are intense and smooth, and the camera switching is more dramatic and rhythmic, which can achieve stronger performance effects. The model supports first frame and first and last frame control, which can specify the starting and ending pictures of the video. It also supports clip continuation and can generate lip-sync performances synchronously with the audio. The input modes cover images, audio and text, and the output is 720P or 1080P video with a duration of 2 to 15 seconds and a frame rate of 30fps.
- Context
- 0 tokens
- Max output
- 0 tokens
- Input
- llm image video
- Output
- video
Pricing
Price: $0.15 / request
720P image_to_video : $0.09999999999999999 /
1080P image_to_video : $0.15 /
Endpoints
- openai