SuperAPI AI Directory

dreamina-canvas-cli-image2image

Design & creation

View repository

Updated 10-15 21:47

About this skill

Jimeng Canvas Image-to-Image and Image Upscaling

When to use

Only handles image-to-image and image upscaling. Input: at least one image reference; local files are first uploaded via resource upload and referenced using node: or res:. When the prompt is not yet determined, hand it to dreamina-prompt-image2image; 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 specification, projectId, and references required by the mode
Side Effects Node writes without --run save drafts; paid execution goes through the public execution operation
Output Handoff The returned nodeId and projectId; after generation, additionally include submitId and the validated resources
Recovery Rules Recovery uses the original submitId; only when explicitly absent + resubmittable should the submission be resumed under the original identity

Workflow

Step 1: Reuse dreamina-canvas-cli 's public invocation contract and the confirmed projectId; when installation or login is missing, hand off to the setup/auth skill by name.

Step 2: Validate the mode parameters from the current model/voice query results and 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 sparsely updated.

dreamina-canvas --format json node create image --project-id <projectId> \
  --prompt "<prompt>" --mode i2i --model <model> --ratio <ratio> --resolution <resolution> --count <count> --ref res:<resourceId>

Step 4: When generation is needed, hand off to dreamina-canvas-cli 's execution operation: 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 off to the same public skill to query recovery and validate the download, 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; do not add --run to draft commands.
  • Do not mix in required fields from other modes; batch limits are queried from the model capabilities.
  • Never persist tokens, cookies or signed URLs; recovery retains only non-sensitive identity.
  • When a companion skill is missing, install:npx skills add full-aigc-skills/dreamina-skills --skill <skill-name>。

Progressive disclosure (read on demand)

  • When per-flag required/value/conflict rules are needed, read Parameter Specification。
  • When selecting a model, aspect ratio, resolution, or duration from the current discovery results, read Model or Voice Selection。
  • For paragraph-level workflows such as batch, asynchronous, multi-project, and iterative, read Common Scenario Combinations。
  • When encountering timeouts, partial success, or recovery scenarios, read Exception Handling。
  • For pre-delivery self-checks, read Acceptance Checklist。
  • For first run, see Success Scenarios; for batch/asynchronous/multi-project/unauthorized-access-refusal/failure-recovery examples, see the examples/ directory.
  • When high-definition upscaling is needed (separate pricing, separate approval), read Image Upscaling。

Validation checklist

  • The input is consistent with i2i mode, and the parameters are discovered in real time.
  • The returned projectId, nodeId, and submitId are handed off correctly, and acceptance must not be treated as completion.
  • The output ends in success; after download, verify the media type, byte count, and SHA-256.

Gotchas

  • Node-generated edits are full replace and must not lose existing references.
  • Login status, billing permission, and generation success are different checks.
  • Generate only the quantity requested by the user, and do not automatically add retries.

Image upscaling is a separately priced operation and uses its own quote and approval token; the token from a normal node confirm cannot be reused. See Image upscaling。

Non-applicability and boundaries

Not applicable to text-to-image or video generation without an image reference. When only uploading assets, use the public resource operation; image upscaling and image-to-image are priced separately and cannot share a single approval.

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.