SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsdreamina-cli-text2image

dreamina-cli-text2image

Design & creation

View repository

Updated 10-15 21:47

About this skill

Dreamina CLI Text-to-Image

⚠️ Maintenance Discontinuation Notice: The legacy Dreamina CLI (dreamina, v1.4.18) will be discontinued starting November 2026 . For new tasks, please switch to the Canvas replacement skill dreamina-canvas-cli-text2image(installation:npx skills add full-aigc-skills/dreamina-skills --skill dreamina-canvas-cli-text2image). The content of this skill is retained as a historical contract reference.

Before execution, run dreamina text2image -h. 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

For text-to-image tasks that have already entered the CLI execution, polling, or troubleshooting stage. It should not be used for image-to-image, video generation, or pure prompt creation; for these scenarios, load the corresponding dreamina-cli-* or dreamina-prompt-* skill respectively.

Collaboration routing:dreamina-prompt-text2image is responsible for prompt creation; this Skill is responsible for local dreamina CLI execution; when the user explicitly chooses OpenCLI transport, switch to dreamina-opencli-text2image, do not submit two execution chains at the same time.

Must comply

  • Explicitly pass on every submission --resolution_type=1k|2k|4k。
  • --width and --height must appear in pairs, be positive integers, and be mutually exclusive with --ratio .
  • Model token uses 5.0Pro, do not write it as the human-readable name 5.0 Pro。
  • generate_num range is 1–10.
  • Before submission, explain that credits will be consumed; prefer --poll=0 to obtain submit_id。

For the model and resolution matrix, and width/height pixel limits, see dreamina-cli skill's references/dreamina-cli-v1.4.18-contract.md. If not installed, please first npx skills add full-aigc-skills/dreamina-skills --skill dreamina-cli。

Standard Execution

dreamina user_credit
dreamina text2image \
  --prompt="一只橘猫坐在窗边，柔和晨光，浅景深" \
  --ratio=1:1 \
  --model_version=5.0 \
  --resolution_type=2k \
  --poll=0

Omit ratio when using custom dimensions:

dreamina text2image \
  --prompt="竖版产品海报，留出标题区域" \
  --model_version=5.0 \
  --resolution_type=2k \
  --width=1536 \
  --height=2048 \
  --poll=0

Asynchronous Closed Loop

Step 1: Validate

Run dreamina text2image -h, validate the model, resolution, ratio, or custom dimension combination.

Step 2: Submit

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

Step 3: Final State Closed Loop

querying only indicates accepted; continue query_result, until success or fail. On failure, report fail_reason; when a file is needed, add --download_dir=<absolute-path>。

Gotchas

  1. Missing resolution: v1.4.18 will reject requests that do not pass resolution_type .
  2. Width/height conflict: custom width/height cannot appear together with ratio.
  3. Display name mistaken as token：5.0 Pro must be converted to 5.0Pro。
  4. Accepted mistaken as success：querying is not a successful final state.
  5. Credit consumption: before a real submission, the user must be informed that credits will be consumed.

References

When to use

Load this skill when the user needs to execute generation or write operations after clear 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-image tasks through dreamina text2image. Covers CLI v1.4.18 required resolution, custom width/height, Seedream model tokens, batch count, sessions, and async terminal status handling.。

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 outputs are missing, explicitly mark them as NOT_VERIFIED。
  • Idempotency first: retain request identifiers and stage 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: Perform prechecks

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

Step 3: Form a plan

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

Step 4: Execute actions

Execute once per approval and record the request identifier; for ambiguous results, query 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 have not been misrouted to this skill.
  • Inputs, target objects, versions, and output locations are all clear, and no guessed values have been used in place of required values.
  • All write, paid, publish, or irreversible actions are within the scope of user authorization.
  • Results have been verified with independent checks; "command succeeded" or "file exists" alone 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: documentation or prompts are not the same as actual execution; the actual execution level must be stated.
  2. Erroneous 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.

Non-applicability and boundaries

Paid, publish, overwrite, upload, or external write operations must use the explicit authorization of the current task; do not automatically expand the number of times or the budget. If the request requires another skill, do not copy its body text; hand off by skill name and preserve the current task context.

Progressive disclosure

  • When inputs/outputs, status, and authorization points need to be determined, read references/workflow-contract.md。
  • When self-checking before delivery is needed, read references/validation-checklist.md。
  • When encountering timeouts, partial success, or recovery scenarios, read references/error-recovery.md。
  • For first runs, privilege escalation refusal, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。