About this skill

Problem

Image-to-image editing is not “regenerating a new image”; it is a constrained transformation of a reference image. A prompt like “change the background to a beach” can cause the model to alter the person, outfit, pose, or composition. The skill makes the prompt explicit about what to keep, what to change, and how the new and old elements should blend.

How It Works

Classify the edit: style transfer, background replacement, detail enhancement, color tuning, element editing, season/time change, restoration, creative transformation, outfit change, or multi-reference composition.
Load templates and vocabulary: read references/usecase-library.md, references/word-library.md, and the matching examples/... file.
Build a structured prompt: organize it as KEEP list, CHANGE instruction, NEW description, Coordination, and Quality.
Validate before output: confirm the keep list is explicit, the change is specific, blending and color coordination are included, aspect ratio is sensible, and the model is Dreamina 4.0+.

Limits

This skill is for Dreamina 4.0+ image-to-image prompting, not text-to-image, CLI execution, or video prompts.
It cannot perform true local editing such as “only the left corner”; complex edges, hair, fur, or transparent objects may blend into the new background.
Multi-reference prompts need a clear role for each image, otherwise results become unpredictable.

Screenshots

Use Cases

Generate a Dreamina 4.0 image-to-image prompt that keeps the product and pose while replacing an e-commerce hero image background.
Turn an old portrait into a clean restoration while preserving facial features, hair, and pose in the prompt.
Write a multi-reference outfit-change prompt where image one keeps the person and image two guides clothing material.
Convert a realistic illustration to cyberpunk style while keeping the character silhouette and composition unchanged.

Best For

E-commerce visual operators who need to replace hero-image backgrounds while keeping products and models unchanged.
Product designers restoring old photos who need prompts that preserve facial features, hair, and pose.
Character illustrators who need to migrate the same character across styles without changing composition.
Art directors combining multiple references who need clear roles for subject, background, and clothing images.

Related Skills

AI Daily Self-Review System

@user_fe828a0e/self-reivew-pro

Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.

AI Agent 2026.08.30 ↓ 1.6K

Permanent Memory Auto-Archiving System

@user_6bedba2d/ybdsjy

Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.

AI Agent 2026.08.30 ↓ 1.2K

Grill Me Plus

@user_c31fa39f/grill-me-plus

Run a grilling session to interact with or test AI agents.

AI Agent 2026.08.30 ↓ 3.5K

Prompt Alchemist

@user_83d7fe7a/prompt-alchemist

A systematic prompt optimization skill that refines prompts using a four-step distillation framework (diagnose, structure, think, compress) and methodologies from four prompting masters.

AI Agent 2026.08.30 ↓ 3.8K

Dreamina Image-to-Image Prompt Precision