--- title: Prompting P-Image-Ideogram — P-Image-Ideogram | Runware Docs url: https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting description: "How to prompt P-Image-Ideogram in both modes: natural language for quick exploration and structured JSON for explicit control over layout, colour, and typography." --- P-Image-Ideogram is a Pruna AI text-to-image model built with Ideogram, aimed at brand and design work where the text has to be right and the layout has to land. It takes prompts two ways: **plain natural language** for quick exploration, and a **structured JSON prompt** that places each element and pins its colour. ![A luxury skincare campaign visual: a frosted serum bottle on wet river stones with eucalyptus, its label reading VERDANT, PURE HYDRATION, BOTANICAL FACE SERUM, HYALURONIC ACID + SQUALANE, 30 ML / 1 FL OZ, beside a large PURE HYDRATION headline and a botanical serum subline](https://runware.ai/docs/assets/output-hero.BxO6lLnE_2vobbB.jpg) > **Prompt**: Structured JSON prompt: a luxury botanical-serum campaign visual on wet river stones with eucalyptus and morning mist, a PURE HYDRATION headline and botanical serum subhead in the left negative space, and a full bottle label pinned as separate text elements: VERDANT, PURE HYDRATION, BOTANICAL FACE SERUM, HYALURONIC ACID + SQUALANE, and 30 ML / 1 FL OZ. That hero is a single structured prompt, with the campaign headline and every line of the bottle's label pinned as its own `text` element. That is **the control a structured prompt buys you**. The rest of this guide covers both ways in: natural language for quick exploration, and the structured JSON prompt for exactly that. ### [Request shape](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#request-shape) A generation needs a `positivePrompt`, which is either a plain sentence or a structured JSON object (both modes are covered below). `width` and `height` default to 1024, `seed` is optional, and `settings` holds **the two controls that shape a run**: `enhancePrompt`, which rewrites your prompt before generation, and `thinkingLevel`, which sets how hard the model works. TypeScriptPythoncURLCLIJSON ```typescript import { createClient } from '@runware/sdk' const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY }) await client.connect() const [result] = await client.run({ model: 'prunaai:p-image@ideogram', positivePrompt: 'A minimalist skincare brand poster: a frosted serum bottle on a pale stone against a soft sage backdrop, with a bold headline that reads "PURE HYDRATION". Photoreal editorial photography, generous negative space, no other text.', width: 1600, height: 2400, settings: { enhancePrompt: false, thinkingLevel: 'high' } }) ``` ```python import asyncio import os from runware import Runware async def main(): async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client: results = await client.run({ "model": "prunaai:p-image@ideogram", "positivePrompt": "A minimalist skincare brand poster: a frosted serum bottle on a pale stone against a soft sage backdrop, with a bold headline that reads \"PURE HYDRATION\". Photoreal editorial photography, generous negative space, no other text.", "width": 1600, "height": 2400, "settings": { "enhancePrompt": False, "thinkingLevel": "high" } }) asyncio.run(main()) ``` ```bash curl https://api.runware.ai/v1 \ -H "Authorization: Bearer $RUNWARE_API_KEY" \ -H "Content-Type: application/json" \ -d '[ { "taskType": "imageInference", "taskUUID": "c3d4e5f6-7a8b-4c90-9d1e-2f3a4b5c6d70", "model": "prunaai:p-image@ideogram", "positivePrompt": "A minimalist skincare brand poster: a frosted serum bottle on a pale stone against a soft sage backdrop, with a bold headline that reads \"PURE HYDRATION\". Photoreal editorial photography, generous negative space, no other text.", "width": 1600, "height": 2400, "settings": { "enhancePrompt": false, "thinkingLevel": "high" } } ]' ``` ```bash runware run prunaai:p-image@ideogram \ positivePrompt="A minimalist skincare brand poster: a frosted serum bottle on a pale stone against a soft sage backdrop, with a bold headline that reads \"PURE HYDRATION\". Photoreal editorial photography, generous negative space, no other text." \ width=1600 \ height=2400 \ settings.enhancePrompt=false \ settings.thinkingLevel=high ``` ```json { "taskType": "imageInference", "taskUUID": "c3d4e5f6-7a8b-4c90-9d1e-2f3a4b5c6d70", "model": "prunaai:p-image@ideogram", "positivePrompt": "A minimalist skincare brand poster: a frosted serum bottle on a pale stone against a soft sage backdrop, with a bold headline that reads \"PURE HYDRATION\". Photoreal editorial photography, generous negative space, no other text.", "width": 1600, "height": 2400, "settings": { "enhancePrompt": false, "thinkingLevel": "high" } } ``` Response ```json [ { "taskType": "imageInference", "taskUUID": "c3d4e5f6-7a8b-4c90-9d1e-2f3a4b5c6d70", "imageUUID": "8e1f2a3b-4c5d-4e60-a7b8-9c0d1e2f3a4b", "imageURL": "https://im.runware.ai/image/os/a14d18/ws/2/ii/8e1f2a3b-4c5d-4e60-a7b8-9c0d1e2f3a4b.jpg" } ] ``` `width` and `height` run from 64 to 2560 in steps of 16, bounded by a **4,194,304 pixel budget** (2048 × 2048 square, or any other pair whose area fits). `thinkingLevel` defaults to `high`, which is the right setting for finished work. Drop to `low` or `very low` only for cheap, fast drafts. The examples here set `enhancePrompt` to `false` so the prompt you read is the prompt the model rendered. > [!NOTE] > `thinkingLevel` is a compute dial more than an interpretation switch. On a fully specified prompt the four levels hold the same composition, so a higher level refines detail rather than reading your words differently. Where it shows is on a sparse prompt: the higher the level, the more the model fills in on its own, which is why a specific prompt keeps `high` refining what you asked for instead of inventing around it. ### [Writing a natural-language prompt](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#writing-a-natural-language-prompt) A natural-language prompt is built in layers, each answering a different question about the image: ![A wide billboard mockup of a coral and white running shoe on a charcoal background with a bold RUN LIGHTER headline and a coral underline](https://runware.ai/docs/assets/output-anatomy.Cah8oVOx_Zbm9bF.jpg) > **Prompt**: A wide outdoor billboard mockup for a running shoe brand. A single low-top running shoe in bright coral and white floats slightly left of centre against a deep charcoal background, lit from the right so the sole catches a hard highlight. To the right of the shoe, a bold white headline reads "RUN LIGHTER", with a thin coral underline beneath it. Photoreal product photography, dramatic studio lighting, high contrast, wide horizontal composition, no other text. **[Subject]** A wide outdoor billboard mockup for a running shoe brand, **[Composition and framing]** A single low-top running shoe in bright coral and white floats slightly left of centre against a deep charcoal background, **[Lighting]** lit from the right so the sole catches a hard highlight, **[Text]** To the right of the shoe, a bold white headline reads "RUN LIGHTER", with a thin coral underline beneath it, **[Style]** Photoreal product photography, dramatic studio lighting, high contrast, wide horizontal composition, no other text **Lead with the subject**, then place it, light it, add any copy, and close on the treatment. Quoting the exact text ("RUN LIGHTER") is what gets it rendered as written rather than paraphrased. Natural language is the right mode for exploration, where you want a strong result fast and you are still deciding what the piece even is. ### [Structured prompts](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#structured-prompts) For exact layout and multi-line copy, pass the prompt as a JSON object instead of a sentence. A structured prompt gives you **a slot for every element**, each with its own text, position, and colour, which is what you want for posters, packaging, and any design where the copy has to land in the right place. The structured prompt is an object with three top-level keys: a `high_level_description`, a `style_description` carrying the overall treatment and palette, and a `compositional_deconstruction` that lists the background and an array of elements. ```json { "high_level_description": "A vertical launch poster for a specialty coffee brand", "style_description": { "art_style": "flat editorial brand design, crisp legible type", "color_palette": ["#c1502e", "#f4e9d8", "#3a2417"] }, "compositional_deconstruction": { "background": "solid warm terracotta", "elements": [ { "type": "text", "color_palette": ["#f4e9d8"], "text": "NEW SEASON ROAST", "desc": "large cream headline near the top" }, { "type": "obj", "desc": "a clean flat illustration of a coffee bag in cream and brown" } ] } } ``` Each element is either a `text` or an `obj`, and **the type is a hard dispatch**. A `text` element renders its `text` field literally, so a brand name comes back spelled exactly as you wrote it. An `obj` element paints its `desc` as natural language. The `desc` field is freeform inside both, so the structure is rigid scaffolding around plain-language content slots. Reach for structured prompts when the frame carries **more than one line of text**, when you are building a template where the layout stays fixed and only the copy changes, or when a natural-language prompt keeps drifting off the arrangement you asked for. #### [Colour palettes](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#colour-palettes) **Colours described in words are interpretation.** A `color_palette` array of hex values is direction, a channel the model reads as colours to favour rather than words to read. Both graphics below ask for the same muted scheme, one in prose and one as hex: ![A flat geometric studio graphic in sage, sand, and clay reading STUDIO OPEN HOUSE](https://runware.ai/docs/assets/output-palette-words.DnG0W7MJ_zAbtr.jpg) *Colour described in words* > **Prompt**: A flat social media announcement graphic for a design studio. A bold geometric composition of overlapping circles and rectangles in muted sage green, warm sand, and soft clay, on an off-white background. Centred white type reads "STUDIO OPEN HOUSE". Minimal flat vector design, balanced composition, no other text. ![The same studio graphic with more sharply defined blocks of sage green, clay, sand, and cream](https://runware.ai/docs/assets/output-palette-hex.B5o6tDEv_Z1MxoaL.jpg) *Colour set by hex palette* > **Prompt**: Structured JSON prompt: a STUDIO OPEN HOUSE geometric graphic with an image-level color_palette of #f4f1e8, #9caf88, #d9c3a3, and #c8927a, holding the sage, sand, and clay scheme precisely. The palette works at two scopes. At the image level, `style_description.color_palette` takes **up to 16 hex values** and anchors the whole composition. On a single element, `color_palette` takes **up to 5** and scopes a colour to that element, which is how a brand colour holds on one word without tinting the rest of the frame. Pass the colours that must be exact as hex, and leave the rest to the prose. #### [Bounding boxes](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#bounding-boxes) When an element has to sit in a specific region, add a `bbox` to it. It is four integers in 0 to 1000 normalised coordinates, ordered `[y_min, x_min, y_max, x_max]`, **row first**, and it coexists with `desc` so the box sets the rectangle while the description still carries the treatment: ![A flat sea-green trail map titled CLIFF PATH TRAIL with an 8.4 km loop subtitle, a dashed orange coastal route linking three dots, and START, COVE, and LIGHTHOUSE labels](https://runware.ai/docs/assets/output-bbox.N-VfTghq_ZvmpJi.jpg) > **Prompt**: Structured JSON prompt: a CLIFF PATH TRAIL map card on pale sea-green with a coastline and a dashed orange route, an 8.4 km loop subtitle in the top left, and START, COVE, and LIGHTHOUSE labels placed by bbox. Each label landed in the rectangle its `bbox` declared. **Most layouts do not need boxes**, since positional language in `desc` ("centred along the top", "lower-right corner") carries them. Reach for `bbox` when descriptive placement keeps drifting and an element has to hold a precise spot. > [!WARNING] > Structured prompts use snake\_case keys only: `color_palette`, `compositional_deconstruction`, `high_level_description`. Camel case or hyphens are not read. The model page schema lists every field and its order. ### [Prompt enhancement](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#prompt-enhancement) `enhancePrompt` rewrites your prompt before generation, and it **defaults to on**. On a terse prompt it fills in detail the model then renders: ![A rough juice jar with muddy colours and garbled label text](https://runware.ai/docs/assets/output-enhance-off.1NNBNOVf_Z1fmodw.jpg) *"a juice brand can", enhancement off* > **Prompt**: a juice brand can ![A clean designed aluminium juice can reading FRESH SQUEEZE ORANGE MANGO with an orange illustration](https://runware.ai/docs/assets/output-enhance-on.RHOSEpbj_1O85XJ.jpg) *The same prompt, enhancement on* > **Prompt**: a juice brand can Off, the bare prompt renders as-is, rough and literal. On, it is expanded into a fuller, finished can design. Enhancement is useful for fleshing out a sparse prompt and a liability for control: the rewrite runs before generation and is not itself seeded, so **the same `seed` and prompt produce a different image on every call while enhancement is on**. Turn it off once the composition matters, and a fixed seed then returns the same image every time, which is how you keep a result while you tune the wording around it. ### [Typography in practice](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#typography-in-practice) Text rendering is the reason to reach for this model, and a structured prompt is how you get it reliably. Give **each line its own `text` element** and the model holds copy that most image models turn to mush. The wrapper below is one structured prompt with five text elements: ![A deep-plum chocolate bar wrapper in gold foil type reading COCOA & SALT, DARK 70%, sea salt single estate, with a cacao pod illustration and NET WT 90g](https://runware.ai/docs/assets/output-typography.fodoKZfZ_1MLdNQ.jpg) > **Prompt**: Structured JSON prompt: a matte deep-plum chocolate wrapper with five gold-foil text elements (COCOA & SALT, DARK 70%, sea salt / single estate, a cacao-pod illustration, and NET WT 90g) on a fixed plum-and-gold palette. Every line came back as written, at the weight and place its element assigned. The rule underneath is the same one the whole model runs on: **quote the copy, never describe it**. A string inside a `text` element is rendered literally, so "COCOA & SALT" is pinned, while "a brand name in gold" would hand the wording to the model. A single headline survives that in plain natural language, but the moment a design carries several strings, put each in its own element. ### [Tips](https://runware.ai/docs/models/prunaai-p-image-ideogram/guides/prompting#tips) 1. **Start in natural language.** It is faster for finding a direction, and you can rebuild the winner as a structured prompt once you know what you want. 2. **Switch to structured for templates and exact layouts.** Fixed scaffolding with swappable copy is what structured prompts are for. 3. **Quote every string that matters.** Text inside quotation marks, or inside a `text` element, renders literally. Anything you describe is reinterpreted. 4. **Pass exact colours as hex.** A `color_palette` is direction the model follows. Colour words in prose are only a suggestion. 5. **Reach for `bbox` only when placement drifts.** Positional language handles most layouts, and boxes are the heavier tool for when it does not. 6. **Turn off `enhancePrompt` before you commit.** It helps exploration and breaks reproducibility, so disable it once you need the same prompt to land the same image.