SuperAPI AI Directory

jimeng-cli-text2video

Agents & models

View repository

Updated 10-15 21:47

About this skill

即梦 CLI text-to-video

Before executing, first run dreamina text2video -h. This skill records the v1.4.14 stable workflow; the actual help is always the source of truth for parameters.

When to use and boundary

For CLI text-to-video submission, polling, and troubleshooting without reference media. Should not be used for image-to-video, storyboards, or pure prompt creation; use jimeng-cli-image2video or the prompt skill instead.

Must comply

  • Explicitly pass on every submission --video_resolution, the token must be lowercase 720p、1080p or 4k。
  • seedance2.0_vip supports 720p/1080p/4k; other public models only support 720p.
  • The only public text-to-video models are the Seedance 2.0 family; do not pass old 3.x or Seedance 1.x tokens.
  • duration range is 4–15 seconds, default model seedance2.0fast。
  • Before submission, explain that credits will be consumed; for time-consuming scenarios, prefer asynchronous submission.

Standard execution

dreamina user_credit
dreamina text2video \
  --prompt="镜头缓慢推进,一只橘猫在窗台伸懒腰,晨光穿过窗帘" \
  --duration=5 \
  --ratio=16:9 \
  --model_version=seedance2.0fast \
  --video_resolution=720p \
  --poll=0

VIP high resolution:

dreamina text2video \
  --prompt="航拍海岸线,浪花沿岩石展开,电影感长镜头" \
  --duration=8 \
  --ratio=16:9 \
  --model_version=seedance2.0_vip \
  --video_resolution=1080p \
  --poll=0

Asynchronous closed loop

Step 1: Verify

Run help to validate the model, duration, ratio, and resolution combination.

Step 2: Submit

Check credits, explain the consumption impact, submit asynchronously, and save submit_id。

Step 3: Final-state closed loop

For querying continuously call query_result, until success or fail. On failure, report fail_reason. When encountering AigcComplianceConfirmationRequired , prompt the user to complete authorization on the Web side first.

Gotchas

  1. Missing resolution: must pass every time video_resolution。
  2. token case: use 720p/1080p, not uppercase P.
  3. Model out of bounds: text-to-video does not accept Seedance 1.x or old 3.x.
  4. High-resolution misuse: 1080p/4k only seedance2.0_vip。
  5. Long task misjudgment: if poll times out and it is still querying , continue querying, do not immediately resubmit.

References