jimeng-opencli-text2video

jimeng-opencli-text2video — Jimeng text-to-video (opencli / regular member)

Forregular members without dreamina CLI . Only the opencli jimeng subcommand is allowed,forbidden dreamina text2video、query_result and jimeng-cli-text2video。

The video prompt is provided by jimeng-prompt-text2video ; execution uses opencli jimeng generate-video（type=video workspace DOM automation).

opencli command

Subcommand	Purpose
`generate-video <prompt>`	Text-to-video (default `--wait=120`）
`generate-image2video <prompt>`	Image-to-video (required `--image` single reference image)
`generate-audio` / `generate-digital-human` / `generate-action-copy`	Voiceover / digital human / motion imitation
`history`	`--type=video` Check works
`new --type=video` / `workspaces`	Session management
`user_credit`	Credit check

Without dreamina's --duration、--model_version=seedance* and other parameters.

Core workflow

1. PROMPT  → jimeng-prompt-text2video
2. SESSION → 可选 opencli jimeng new --type=video
3. GEN     → opencli jimeng generate-video "<prompt>" [--workspace ...] [--wait 180]
4. VERIFY  → opencli jimeng history --limit N --type=video

Allowed opencli examples

opencli jimeng generate-video "镜头缓慢推进，橘猫跳下沙发" --wait=180
opencli jimeng new --type=video
opencli jimeng history --limit 10 --type=video --format json
opencli jimeng user_credit

Prohibitions

Do not use the dreamina CLI to submit or poll video tasks.
Do not use generate（type=image) to impersonate video generation.

Vs. jimeng-cli-text2video

Users who have enabled the dreamina CLI use jimeng-cli-text2video; readers of this skillmust notswitch to dreamina.

Agent specifications

Videos take a long time: multiple history is normal; shell infinite loops are prohibited; the agent should call in rounds history。
Duration should match action complexity (see the prompt skill); the seconds are selected by the user on the web page.
Insufficient credits and compliance blocks are shown on the web page; opencli cannot user_credit query.

Gotchas

history The columns are mainly image-to-video history API fields; video entries are subject to what is actually displayed on the web page; when there are no records, rely on the user's browser state.
Regular members are subject to the web plan and queue, unrelated to the dreamina VIP queue.
First/last frame and multi-storyboard must be operated on the web page; single-image image-to-video uses generate-image2video --image。