jimeng-prompt-image2image

jimeng-prompt-image2image is a skill for Claude Code from full-aigc-skills/jimeng-skills. It costs 227 tokens per session (2,490 once invoked), scanned A, original, Apache-2.0.

Prompt-writing guidance for editing an existing image with Jimeng (Dreamina), an image-generation service. It uses a “keep and change” method to state what should remain and what should be transformed.

In plain words
What is it for?
Writing prompts for style changes, background replacement, colour changes, adding or removing elements, and other edits to a reference image in Jimeng 4.0 or later.
Why use it?
It helps prevent an image edit from changing parts the user wanted to preserve. It also distinguishes editing an image from creating one from text alone.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the jimeng-skills plugin — 13 skills shipped together

Good fit Writing prompts for style changes, background replacement, colour changes, adding or removing elements, and other edits to a reference image in Jimeng 4.0 or later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/full-aigc-skills/jimeng-skills/jimeng-prompt-image2image
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add full-aigc-skills/jimeng-skills --skill jimeng-prompt-image2image
Clone the repo
git clone --depth 1 https://github.com/full-aigc-skills/jimeng-skills

Made for: Claude Code.

Or install jimeng-skills, the plugin that ships this one along with the rest of its 13 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for jimeng-prompt-image2image

README.md
[![agentmods](https://agentmods.dev/badge/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-image2image/github.svg)](https://agentmods.dev/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-image2image)
Your own site
<a href="https://agentmods.dev/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-image2image"><img src="https://agentmods.dev/badge/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-image2image/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for jimeng-prompt-image2image

Your own site · 80×15
<a href="https://agentmods.dev/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-image2image"><img src="https://agentmods.dev/badge/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-image2image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00227 $0.02490
Opus 5 $0.00113 $0.01245
Sonnet 5 $0.00045 $0.00498
Haiku 4.5 $0.00023 $0.00249

Measured 12d ago against content hash 759f065aa2b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

jimeng-prompt-image2image scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/jimeng-prompt-image2image/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jimeng-prompt-image2image — 即梦图生图提示词

Craft image-to-image edit prompts for 即梦 Dreamina models 4.0+.

When to use this skill

Use this skill when the user:

  • Provides a reference image and wants to modify it ("把这张图改成...")
  • Asks to change an image's style, background, colors, or details
  • Wants to add or remove elements from an existing image
  • Mentions keywords: 图生图, image2image, 编辑图片, 换背景, 改风格, 修图, 风格迁移, 背景替换
  • Describes a transformation applied TO an existing image (not creating from scratch)

Do NOT use this skill for:

  • Creating images from text only (no reference image) → use jimeng-prompt-text2image
  • CLI execution → use jimeng-cli-image2image
  • Video prompts → use jimeng-prompt-text2video or jimeng-prompt-image2video

Core Methodology

The image-to-image prompt formula is fundamentally different from text-to-image:

[保留什么] + [改变什么] + [新元素/新风格描述] + [光影/色彩协调] + [画质要求]

The Keep/Change Principle: An I2I prompt must explicitly state what to KEEP and what to CHANGE. Failing to specify the "keep" list leads to edit cascading — the model changes elements you never intended to touch.

Key difference from text-to-image

Text-to-Image Image-to-Image
Input Text only Reference image(s) + edit instruction
Core task Create from scratch Transform while preserving
Prompt focus Complete scene description Keep vs. Change separation
Critical component Subject + Scene + Style KEEP list (what stays) + CHANGE list (what transforms)
Reference Optional style reference Required — the source image IS the starting point
Model requirement 3.0+ 4.0+ only

How to use this skill

Step 1: Identify the edit category

Category What User Wants Example File
风格迁移 Change art style while keeping content examples/style-transfer.md
背景替换 Replace background, keep foreground examples/background-replace.md
细节增强 Improve quality, sharpness, texture examples/detail-enhance.md
色彩调整 Change color palette, tone, mood examples/color-adjust.md
元素编辑 Add or remove specific objects/elements examples/element-edit.md
季节/时间 Change season or time of day examples/season-time.md
修复/复原 Restore damaged/old photos examples/restoration.md
创意变形 Whimsical/fantasy transformations examples/creative-transform.md
换装/服装 Change clothing while keeping person examples/outfit-change.md
多图合成 Combine elements from multiple images examples/multi-reference.md

Read the full file on GitHub · 167 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 167 lines · 227 tokens per session scan A 759f065aa2b2

Subscribe to this mod's changes

jimeng-prompt-image2image is a skill published in the GitHub repository full-aigc-skills/jimeng-skills (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 227 tokens to every session and 2,490 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens