dreamina-opencli-image2video

dreamina-opencli-image2video — Dreamina image-to-video (opencli / regular member)

Aimed atno dreamina CLI regular members. Only allowed opencli jimeng subcommands,forbidden dreamina image2video、frames2video、multiframe2video、multimodal2video and dreamina-cli-image2video。

Incremental motion prompt provided by dreamina-prompt-image2video provided;image-to-video / first-last frame / storyboard / omni-referencegenerated on the Dreamina web page after the user selects the mode and uploads materials.

opencli commands

Subcommand	Purpose
generate-image2video <prompt> --image <path>	single reference image + motion prompt (type=video）
history	verify after task completion
new / workspaces	session management

First-last frame, multi-storyboard, and multimodal still require manually selecting the mode on the web page; opencli no --first/--last route.

Web page mode aligned with prompt skill

User input	Web page side (user operation)	prompt skill key points
Single image	image-to-video, upload 1	only write motion increment
First and last 2	first-last frame / transition	describe transition process
Multiple storyboards	multi-frame / storyboard	narrative + transitions
Image + audio/video	omni-reference / multimodal	composition relationship description

Routing atweb pagecompleted; the agent uses the prompt skill to assist with copy and uses opencli for sessions and acceptance.

Core flow

1. PROMPT  → dreamina-prompt-image2video
2. SESSION → 可选 opencli jimeng new --type=video
3. GEN     → opencli jimeng generate-image2video "<motion prompt>" --image ./frame.png --wait 180
4. VERIFY  → opencli jimeng history --limit N --type=video（视频可长达十余分钟，分轮查询）

Allowed opencli examples

opencli jimeng generate-image2video "镜头缓慢推进，发丝随风飘动" --image ./portrait.jpg --wait 180
opencli jimeng history --limit 10 --type=video

Prohibitions

• Must not call any dreamina video subcommand or query_result polling.
• Must not fabricate opencli image-to-video parameters.
• Must not guide the installation of dreamina.

Division of labor with dreamina-canvas-cli-ref2video

Users who have installed dreamina-canvas CLI use dreamina-canvas-cli-ref2video for mode selection and routing (old dreamina image2video stopped maintenance in 2026-11, do not route to it anymore); users of this skillmust notswitch to it.

Agent specifications

• prompt only describesthe part that moves, and does not repeat static content of the image.
• Round-by-round history acceptance, shell infinite loops are prohibited.
• Single-image image-to-video uses generate-image2video --image; complex modes still guide the user to operate on the web page.

Gotchas

1. First-last frame / storyboard / multimodal must be manual on the web page, and opencli parameters must not be fabricated.
2. Video takes a long time, default --wait=120, image-to-video recommended 180+.
3. Regular member queueing and credits are subject to the web page.

When to use (when to use)

When the user needs to execute generation or write operations after explicit input, budget, and delivery constraints Load this skill when. First extract the goal, inputs, constraints, delivery format, and acceptance criteria from the request; the description summary is: Use when the user is a standard (non-VIP) Jimeng member without the dreamina CLI and needs image-to-video on jimeng.jianying.com. opencli jimeng has no image2video, frames2video, or multimodal subcommands. Pair with dreamina-prompt-image2video for incremental motion prompts, manual mode selection on the Jimeng web UI, and opencli history for verification. Never invoke dreamina or jimeng-cli execution skills.

Rules

• Read before write: first confirm the current state and real 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, explicitly mark them as NOT_VERIFIED。
• Idempotency first: retain request identifiers and stage state; when results are unclear, query first rather than retrying blindly.
• 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 inputs, model/tool capabilities, output paths, budget caps, 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 be changed, the success criteria, and the safe exit method after failure.

Step 4: Execute actions

Execute once approved and record the request identifier; for ambiguous results, query first rather than resubmitting; retain an associable state 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 user intent, and no adjacent task was misrouted to this skill.
• Inputs, target objects, versions, and output locations 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.
• 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 actionable 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 indicated.
2. Retrying on error: a timeout or lost response may already have produced remote state; query first before deciding whether to retry.
3. Implicit scope expansion: bulk, full-scale, publish, overwrite, and paid actions are not a natural extension 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 features, publishing, coverage, uploading, or external writes must use the explicit authorization of the current task; do not automatically expand the number of times and 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 input/output, state, 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 run, privilege escalation refusal, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。