SuperAPI AI Directory

dreamina-canvas-cli-text2video

Design & creation

View repository

Updated 10-15 21:47

About this skill

Jimeng Canvas Text-to-Video

When to use

Only handles text-to-video. Input: final prompt, real-time model specs; --duration must be explicit. When the prompt is not yet finalized, hand it to dreamina-prompt-text2video; do not rewrite the final prompt without the user's request.

Sunset notice: this skill replaces the corresponding generation path of the old dreamina CLI.

Operation Contract

Item Standard
Input and Prerequisites User-confirmed prompt, current model specs, projectId, and references required by the mode
Side Effects Node writes without --run save a draft; paid execution goes through the shared execution operations
Output Handoff The returned nodeId and projectId; after generation, also attach the submitId and the validated resources
Recovery Rules Recovery uses the original submitId; only when explicitly absent + resubmittable may it resubmit under the original identity

Workflow

Step 1: Reuse dreamina-canvas-cli shared invocation contract and the confirmed projectId; if installation or login is missing, hand it to the setup/auth skill by name.

Step 2: Validate the mode parameters from the current model/voice query results, read Parameter Specification. Do not apply the old CLI's model_version, resolution_type or poll.

Step 3: Save the draft and record the returned nodeId; when modifying an existing node, first read the current state, fully replace the generation parameters and references, and only metadata is a sparse update.

dreamina-canvas --format json node create video --project-id <projectId> \
  --prompt "<prompt>" --mode t2v --model <model> --ratio <ratio> --resolution <resolution> --duration <seconds>

Step 4: When generation is required, hand it to dreamina-canvas-cli execution operations: node quote → node confirm → node run. Record a stable submitId before submission; the task skill does not approve budgets on its own.

Step 5: Hand it to the same shared skill for query recovery and download validation, and verify the actual artifacts of this mode. On timeout, do not resubmit with a different submitId.

Rules

  • Placeholder parameters must be replaced with values returned by the current CLI or confirmed by the user; draft commands do not include --run.
  • Do not mix in required fields from other modes; query the batch limit from the model capabilities.
  • Never persist tokens, cookies or signed URLs; recovery retains only non-sensitive identity.
  • Install missing companion skills:npx skills add full-aigc-skills/dreamina-skills --skill <skill-name>。

Progressive disclosure (read on demand)

Validation checklist

  • The input is consistent with t2v mode, with parameters discovered in real time.
  • The returned projectId, nodeId and submitId are handed off correctly; acceptance must not be treated as completion.
  • The final state is successful; after download, verify the media type, byte count, and SHA-256.

Gotchas

  • Node generation editing is a full replace; the original references must not be lost.
  • Login status, billing permissions, and generation success are separate checks.
  • Generate only the quantity requested by the user; do not automatically add attempts.

Not applicable and boundaries

Not applicable to videos driven by first and last frames or multimodal assets; use ref2video instead. Full storyboard production is handled by dreamina-video-production; this skill only maintains single-pass t2v mode.

Read only the account and asset information necessary for the current operation; do not store, log, or output access tokens, cookies, or temporary signed links.