--- name: netsi-style-like-dream-palaces description: >- Generate a finished image from an attached photograph, a described scene, or a context that needs illustration. Apply a precise ornamental dream-adventure drawing style: delicate pen contours, expressive figures, flat luminous print colors, theatrical perspective and rhythmic ornament. Preserve recognizable people and source-image content. Offer up to three relevant optional style adjustments and generate a labeled comparison grid when requested. Use for dreamlike vintage comic illustrations, ornamental pen drawings, or /netsi-style-like-dream-palaces. Image generation is required; a prompt alone is not the deliverable. metadata: version: "1.0.0" teaser: "You recognize the face, the smile, the place. So why does the picture suddenly feel like a doorway into a dream? A fine pen line changes the shapes; luminous print colors and carefully staged depth change how you read them. Give this skill a photo, a scene or an idea, and get a finished illustration with a distinct ornamental dream-adventure character. Keep it grounded, or let the scenery bend a little." tags: - image-generation - illustration - style-transfer - creativity - design --- # Dream Palaces Turn a familiar subject into a finely drawn, richly colored dream-adventure illustration. A supplied face stays recognizable; a described scene stays yours; a context becomes a visual idea you can actually use. Deliver the image itself. ## Required capabilities and resources - Use an image-generation/editing tool. For a photograph, use an actual image edit with the photograph attached as the edit target. Do not reconstruct it from a description alone. - Use **netsi-prompt-generator** for the internal image prompt. If it is installed, read its instructions. Otherwise read the bundled, complete copy at `references/prompt-generator.md` and apply that skill's workflow to the prompt subtask. - Read `references/style-profile.md` before composing the prompt, and `references/tweaks.md` when adjustments or a comparison are relevant. - Inspect the bundled generated examples in `https://assets.netsi.dk/skills/netsi-style-like-dream-palaces/images/` as anonymous visual calibration, especially `https://assets.netsi.dk/skills/netsi-style-like-dream-palaces/images/04-night-train.png` for space and color and `https://assets.netsi.dk/skills/netsi-style-like-dream-palaces/images/02-car.png` for figure drawing. When the image tool supports multiple references, supply the input photograph as the **edit target** and a relevant bundled illustration as the **style reference only**. In a new scene, the bundled illustrations are style references only. Never copy their subject, composition, identity or labels into the user's result. Do not redistribute historical research scans. - The prompt generator's output contract applies internally: its English prompt goes to the image tool. The parent skill's user-facing deliverable remains the finished image. - If image generation is unavailable, say that clearly in the user's language. Do not label an English prompt or a mockup as a generated image. Never silently substitute a different provider or paid API. ## Recognize one of three inputs **A — Image.** Inspect the photograph. Record the person or subject, face proportions, age, expression, pose, hands, clothing, recognizable accessories, objects, framing and meaningful setting. Preserve these unless the user explicitly asks to change them. Retain the input aspect ratio by default. A style reference is a different role from the edit target; do not swap them. **B — Scene.** Extract who or what is present, actions, setting, composition and any explicit constraints. Keep the scene's content. If no aspect ratio is supplied, use 16:9 for a scene; follow a stated medium such as a square social post instead when provided. **C — Context.** Extract the message, audience, mood and destination from the supplied text or conversation. Choose a concrete, original visual metaphor. Do not invent facts, numbers, quotations or branding. Make the message understandable without text by default. Ask only if materially different interpretations prevent a useful result. Use the requested destination's aspect ratio, otherwise 16:9. If inputs are combined, infer their roles: for example, an image is the subject and a paragraph supplies the illustration's message. Ask one focused question only when the roles conflict. ## Optional adjustments: zero to three The canonical controls are **Ornament**, **Palette**, and **Dream logic**. Values and defaults live in the tweaks reference. Never weaken the identity of this style by changing its core linework to a generic filter or another medium. If the request is clear, apply the explicit values or defaults and generate immediately. Do not require a questionnaire. If the user asks to explore, requests a materially ambiguous adjustment, or a meaningful unresolved choice would change the result, use an **AskUserQuestion** interaction: the environment's interactive question tool, or the same concise question in chat when no such tool is available. Offer at most three relevant tweak controls. Ask one focused question at a time, explain its visual effect in plain language, place the recommended/default answer first, and allow a custom answer and discussion. Where tool schemas add free text automatically, do not duplicate it with a fake option. Infer answers already supplied. Do not mistake silence for consent to a material change. If the user simply wants the default image, no question is needed. Translate questions, explanations and choices into the user's language. Canonical parameter values stay English in prompts and grid labels. Natural-language requests such as "lidt færre detaljer" may be mapped directly to a suitable value without asking again. Respect a scene's stated lighting: a night scene can imply Palette = Twilight even without an explicit parameter name. Stated content takes precedence over a style default. ## Generate, inspect, deliver 1. Inspect the input and identify its type and invariants. 2. Load the detailed style profile. Resolve any relevant optional adjustments. 3. Apply **netsi-prompt-generator** to form one self-contained internal prompt with role, task, context/constraints and output format. Explicitly set **the entire image-tool prompt to English**, regardless of the dialogue language. Preserve requested in-image text verbatim in its requested language; this is the only language exception inside the English instructions. 4. Include the profile's core traits, their priorities, selected tweak values and the input's exact preservation constraints. Use descriptive traits only. Do not mention artist names, named fictional characters, existing works, signatures or imitation slogans. 5. Generate or edit the actual image. For a local edit target, inspect it before editing and pass the file through the image tool's supported reference mechanism. 6. Inspect the result: recognize the subject; check face, expression and hand gesture; check scene content; check delicate linework, flat bounded colors, stage-like depth and ornament rhythm; check any requested lettering. The style must influence the drawing, not merely tint the photograph or decorate its border. 7. If a material defect exists, make a focused revision and inspect again. Keep a consistent target identity and do not silently alter the scene to make the drawing easier. 8. Deliver the finished image, with at most a short useful caption in the user's language. Keep the internal prompt hidden unless the user explicitly asks for it. Save final project-bound assets in that project's folder; do not overwrite the source photograph. For ordinary portraits, a quiet setting is acceptable. Never add an unrelated palace just because the skill is called Dream Palaces. Apply the same draftsmanship to people, water, car seats and nature. The surreal setting transformation is an explicit adjustment, not an automatic rewrite of the input. ## Comparison grids When requested, create one **16:9 image with 4 columns × 3 rows** (12 image cells). Use the same subject, identity, pose, objects and crop in every cell. Reserve a legible label strip under each image, inside the overall canvas. Labels contain the exact English parameter names and values, never artist names. Use the schedule in `references/tweaks.md`: it includes the default and varies Ornament and Palette while keeping Dream logic grounded. A matrix may explore Dream logic instead if requested, but must state the exact changed values. Generate the artwork with the image tool. Use supported layout/text composition tools to assemble a precise grid if available; do not use code to imitate the illustration or recolor a photograph as a substitute. A single image-tool call may render the complete labeled grid. Verify 12 cells, order, visible differences, literal labels and a 16:9 canvas (allow one pixel of integer raster rounding) before delivering. Regenerate if lettering or structure is wrong. Do not claim pixel-identical identity or perfectly isolated experimental control: image generation can vary details. Aim for faithful, visually comparable variations and disclose a material limitation if it remains. ## Start with an example - Attach a photograph: "Apply this style. Keep the face, pose and surroundings recognizable." - Describe a scene: "A night train crosses a narrow bridge between two immense ornamental towers. One traveler watches from a window." - Supply context: "Illustrate how curiosity helps adults learn, for a workshop opening slide. No text in the image." - Explore adjustments: "Show my attached lakeside portrait in a 4 × 3 comparison grid with English tweak labels." See `EXAMPLES.md` for actual generated outputs, source photos and the comparison grid.