SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsdreamina-cli-text2video

dreamina-cli-text2video

Design & creation

View repository

Updated 10-15 21:47

About this skill

Jimeng CLI text-to-video

⚠️ Maintenance discontinuation notice: The legacy Dreamina CLI (dreamina, v1.4.18) will be November 2026 maintenance discontinued starting from. For new tasks, please switch to the Canvas replacement skill dreamina-canvas-cli-text2video(installation:npx skills add full-aigc-skills/dreamina-skills --skill dreamina-canvas-cli-text2video). The content of this skill is retained as a historical contract reference.

Before execution, run dreamina text2video --help. This skill records the v1.4.18 stable workflow; the actual help is always the source of truth for parameters.

When to use and boundary

Used 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 instead dreamina-cli-image2video or the prompt skill.

Collaboration routing:dreamina-prompt-text2video is responsible for video prompts; this Skill is responsible for local dreamina CLI execution; when the user explicitly chooses OpenCLI transport, switch to dreamina-opencli-text2video, do not submit repeatedly.

Must comply

  • Explicitly pass on every submission --video_resolution, the token must be lowercase 480p/720p/1080p/4k。480p only seedance2.5 supports.
  • seedance2.0_vip supports 720p/1080p/4k; other Seedance 2.0 family models only support 720p.
  • seedance2.5: 480p/720p/1080p, duration 4–30 seconds.
  • Discover aspect ratio values from dreamina text2video --help at runtime; v1.4.18 is 1:1, 3:4, 16:9, 4:3, 9:16, 21:9, when omitted --ratio defaults to 16:9.
  • The public text-to-video models are only the Seedance 2.0 family and seedance2.5, do not pass legacy 3.x or Seedance 1.x tokens.
  • Seedance 2.0 family duration 4–15 seconds, default model seedance2.0fast；seedance2.5 duration 4–30 seconds.
  • Explain before submission 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

v1.4.18 Seedance 2.5 long video (4–30 seconds, 480p/720p/1080p):

dreamina text2video \
  --prompt="延时摄影：城市从黎明到夜空的连续变化，云层流动，灯光渐次亮起" \
  --duration=20 \
  --ratio=16:9 \
  --model_version=seedance2.5 \
  --video_resolution=720p \
  --poll=0

Asynchronous closed loop

Step 1: Validate

Run dreamina text2video --help, validate model, duration,--ratio and resolution combination at runtime.

Step 2: Submit

Check credits, explain 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 first.

Gotchas

  1. Missing resolution: must pass every time video_resolution。
  2. token case: use 480p/720p/1080p/4k, not uppercase P.
  3. Model out of bounds: text-to-video does not accept Seedance 1.x or legacy 3.x.
  4. High resolution misuse：seedance2.5 can use 1080p but cannot use 4k; for other models, refer to the current help.
  5. Duration out of bounds: Seedance 2.0 family 4–15 seconds,seedance2.5 4–30 seconds, exceeding will be rejected.
  6. Long task misjudgment: when poll times out and is still querying , continue querying, do not immediately resubmit; long videos especially need longer --poll。

References

When to use

Load this skill when the user needs to execute a generation or write operation after clarifying input, budget, and delivery constraints . First extract the goal, input, constraints, delivery format, and acceptance criteria from the request; the description summary is: Use when the user wants to submit, poll, or troubleshoot Dreamina 即梦 text-to-video tasks through dreamina text2video. Covers CLI v1.4.18 runtime ratio discovery, required video resolution, Seedance model constraints, sessions, and async terminal statuses.。

Rules

  • Read before write: first confirm the current state and actual capabilities, then perform actions that change external state.
  • Least privilege: use only the files, tools, accounts, and network scope required to complete the current step.
  • Evidence first: when run results, resource IDs, versions, hashes, or test output are missing, clearly mark them as NOT_VERIFIED。
  • Idempotency first: retain request identifiers and phase status; when results are unclear, query first rather than blindly retrying.
  • Privacy and security: logs, examples, receipts, and error messages must not contain tokens, cookies, keys, or personally sensitive data.

Workflow

Step 1: Clarify intent

Confirm whether this skill matches the goal; if it is only an adjacent need, hand it off to a more precise skill.

Step 2: Run prechecks

Validate input, model/tool capabilities, output paths, budget ceilings, and approval status; if any key condition is unknown, stop at the read-only stage.

Step 3: Form a plan

List the tools to be invoked, the objects that will change, the success criteria, and the safe exit method after failure.

Step 4: Execute actions

Execute once approved and record the request identifier; query ambiguous results first instead of resubmitting; retain an associable status or receipt for every external call.

Step 5: Verify delivery

Verify artifact existence, format, hash/identifier, cost status, and quality gates, and state facts, inferences, and unverified items separately.

Validation checklist

  • The skill trigger conditions are consistent with the user's intent, and adjacent tasks were not misrouted to this skill.
  • The input, target object, version, and output location are all clear, and no guessed values were used in place of required values.
  • All write, paid, publish, or irreversible actions are within the scope of user authorization.
  • The results have been verified with independent checks; only "command succeeded" or "file exists" does not count as complete acceptance.
  • The output includes actual evidence, failed/skipped items, remaining risks, and executable next steps.

Gotchas

  1. Mistaking the plan for the result: a document or prompt is not equal to actual execution; the actual execution level must be stated.
  2. Incorrect retry: a timeout or lost response may already have produced remote state; query first before deciding whether to retry.
  3. Implicit scope expansion: batch, full-scale, publish, overwrite, and paid operations are not natural extensions of ordinary reads and writes.
  4. Version drift: when referencing external resources, record the version, tag, or commit; do not treat a mutable branch as release evidence.
  5. Stale evidence: caches, old screenshots, and historical tests cannot prove the current environment; refresh key evidence before delivery.

Not Applicable and Boundaries

Paid, publishing, coverage, uploads, or external writes must use the explicit authorization of the current task; do not automatically expand the number of times or the budget. If a request requires a different skill, do not copy its body; hand off by skill name and preserve the current task context.

Progressive disclosure

  • When input/output, state, and authorization points need to be determined, read references/workflow-contract.md。
  • When a pre-delivery self-check is needed, read references/validation-checklist.md。
  • When encountering timeouts, partial success, or recovery scenarios, read references/error-recovery.md。
  • For first run, privilege escalation refusal, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。