dreamina-opencli-text2image

dreamina-opencli-text2image — Jimeng text-to-image (opencli / standard member)

Forusers without the dreamina CLI / premium membershipwho can only useJimeng web standard membershipcapabilities. This skillonly allowscalling the opencli jimeng subcommand,forbidscalling dreamina or dreamina-cli-* execution-type skills.

Prompts are produced by dreamina-prompt-text2image ; this skill is only responsible for opencli execution and session management.

opencli jimeng command list

Subcommand	Purpose	Key parameters / output
generate <prompt>	Text-to-image	--model、--wait、--workspace; list status、media_type、media_count、media_urls
generate-image2image <prompt>	Image-to-image	required --images(comma-separated paths, up to 10 images)
history	Recent works	--limit、--workspace、--type; list history_id、media_type、media_url etc.
new	Create workspace	--type; list workspace_id、workspace_url、type
workspaces	Workspace list	list workspace_id、name、is_pinned、updated_at
user_credit	Credit balance	list balance、vip_credit、gift_credit、purchase_credit
user_subscription	Membership info	list cur_vip_level、subscribe_type、end_time etc.
user_assets	Asset library tabs	--tab、--wait; list tab、item_count、request_url

General options (for each subcommand):-f/--format(table, plain, json, etc.),-v/--verbose. Strategy: Cookie + Browser, domain jimeng.jianying.com。

Prerequisites

1. Installed opencli, and opencli jimeng -h can list the above four subcommands.
2. Chrome is already logged in to Jimeng, and Browser Bridge is installed (consistent with the opencli documentation).
3. Before execution, use opencli jimeng history --limit 1 or open Jimeng in the browser to confirm you are not logged out.

Core workflow

1. PROMPT → dreamina-prompt-text2image 定稿并获用户确认
2. GEN    → opencli jimeng generate "<prompt>" [--model ...] [--wait ...]
3. CHECK  → 解析 status；timeout 时加大 --wait 或 history 对照
4. ORG    → 可选 new / workspaces 管理会话

generate usage

opencli jimeng generate "一只在星空下的猫"
opencli jimeng generate "赛博朋克城市夜景" --model high_aes_general_v50 --wait 60
opencli jimeng generate "水墨山水" --format json

Parameter	Description
prompt	Positional parameter, required
--model	Default high_aes_general_v50; optional high_aes_general_v42（4.6）、high_aes_general_v40（4.0）
--wait	Seconds to wait for image generation, default 40

status is success when it takes links from media_urls ;timeout when it adds --wait or checks history；failed when it prompts to check login, credits (user_credit) or web compliance pop-ups.

Auxiliary commands

opencli jimeng history --limit 10
opencli jimeng new
opencli jimeng workspaces

Division of labor with dreamina-canvas-cli-text2image

User condition	Skill used
Standard member only / no dreamina CLI	This skill(opencli only)
dreamina-canvas CLI installed	dreamina-canvas-cli-text2image(old dreamina text2image maintenance stopped in 2026-11, do not route there anymore)

Agent specifications

• Must not suggest installing dreamina or executing dreamina text2image。
• Must not use a shell while true infinite loop; waiting is done by generate --wait inside the browser.
• Must not rewrite the prompt within this skill.

Gotchas

1. generate fixedly opens the type=image text-to-image page; does not include image-to-image or video parameters.
2. --model to opencli jimeng generate -h shall prevail; if the webpage has not switched models, the actual option on the page shall prevail.
3. Chinese prompts usually work better.
4. history 's status is completed / pending, which is different from generate 's success / timeout field; do not mix them up.

When to use

Load this skill when the user needs to perform generation or write operations after clarifying inputs, budget, and delivery constraints . First extract the goal, inputs, constraints, delivery format, and acceptance criteria from the request; the description summary is: Use when the user cannot use the dreamina CLI (standard non-VIP member) and must automate 即梦 text-to-image through opencli Browser Bridge on jimeng.jianying.com. Covers generate, history, new, workspaces, user_credit, user_assets, user_subscription. Does not use the dreamina CLI. Pair with dreamina-prompt-text2image for prompts..

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 outputs are missing, explicitly mark them as NOT_VERIFIED。
• Idempotency first: retain request identifiers and phase state; when results are unclear, query first and do not blindly retry.
• 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 key condition is unknown, stop at the read-only stage.

Step 3: Form a plan

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

Step 4: Execute actions

Execute per approval and record request identifiers; for ambiguous results, query first instead of 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 adjacent tasks were not misrouted to this skill.
• Inputs, target objects, versions, and output locations are all clear, and no required values were replaced with guesses.
• All write, payment, publish, or irreversible actions are within the scope authorized by the user.
• 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: A document or prompt is not equal to actual execution; the actual execution level must be stated.
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: Batch, full, 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. Evidence is stale: caches, old screenshots, and historical tests cannot prove the current environment; refresh key evidence before delivery.

Non-applicability and boundaries

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

Progressive disclosure

• When it is necessary to determine inputs/outputs, states, and authorization points, read references/workflow-contract.md。
• When self-check 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, refusal of privilege escalation, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。