--- title: Prompting — GPT-Image-2.6 Flare | Runware Docs url: https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting description: "How to prompt GPT-Image-2.6 Flare: writing a brief it can plan a layout from, rendering readable text in the scene, and choosing a size from its dimension envelope." --- ### [Introduction](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#introduction) GPT-Image-2.6 Flare is OpenAI's fast model for generating and editing images in interactive work. It takes up to 32,000 characters of `positivePrompt` and **plans the layout before it renders**. A prompt written as a brief, with the subject, where each element sits, how many there are and the exact words in quotes, gives that plan something to follow. ![An off-white knit running sneaker with a sage green heel tab and a gum rubber sole on a pale concrete plinth, a kraft paper price tag reading $129 hanging from its laces, under the headline LOOPWAY RUNNER in white capitals on a sage green backdrop](https://runware.ai/docs/assets/hero.KmFtjLhC_ZcmrUx.jpg) > **Prompt**: An e-commerce product hero for the website of a running shoe brand. A single low-top running sneaker in off-white knit with a sage green heel tab and a gum rubber sole stands in three-quarter view on a pale concrete plinth, centered in the lower half of the frame. A kraft paper price tag hangs from the laces on a cotton string and reads "$129" in black stamped type. Across the upper third, on a soft sage green backdrop, the headline "LOOPWAY RUNNER" is set in large white sans-serif capitals. Soft diffused daylight from the upper left, a gentle shadow falling to the right of the plinth. Straight-on shot at plinth height, 85mm lens. Photoreal studio product photography, no other text. This guide covers the request, writing a brief the model can plan from, counts and positions, readable text, and choosing a size. ### [The request](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#the-request) A call needs only `model` and `positivePrompt`, and **the size is optional too**. **TypeScript**: ```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: 'openai:gpt-image@2.6-flare', positivePrompt: 'An e-commerce product hero for the website of a running shoe brand. A single low-top running sneaker in off-white knit with a sage green heel tab and a gum rubber sole stands in three-quarter view on a pale concrete plinth, centered in the lower half of the frame. A kraft paper price tag hangs from the laces on a cotton string and reads "$129" in black stamped type. Across the upper third, on a soft sage green backdrop, the headline "LOOPWAY RUNNER" is set in large white sans-serif capitals. Soft diffused daylight from the upper left, a gentle shadow falling to the right of the plinth. Straight-on shot at plinth height, 85mm lens. Photoreal studio product photography, no other text.', width: 2048, height: 1152 }) ``` **Python**: ```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": "openai:gpt-image@2.6-flare", "positivePrompt": "An e-commerce product hero for the website of a running shoe brand. A single low-top running sneaker in off-white knit with a sage green heel tab and a gum rubber sole stands in three-quarter view on a pale concrete plinth, centered in the lower half of the frame. A kraft paper price tag hangs from the laces on a cotton string and reads \"$129\" in black stamped type. Across the upper third, on a soft sage green backdrop, the headline \"LOOPWAY RUNNER\" is set in large white sans-serif capitals. Soft diffused daylight from the upper left, a gentle shadow falling to the right of the plinth. Straight-on shot at plinth height, 85mm lens. Photoreal studio product photography, no other text.", "width": 2048, "height": 1152 }) asyncio.run(main()) ``` **cURL**: ```bash curl https://api.runware.ai/v1 \ -H "Authorization: Bearer $RUNWARE_API_KEY" \ -H "Content-Type: application/json" \ -d '[ { "taskType": "imageInference", "taskUUID": "6e1c9a4f-2b87-4d3e-9f05-8a7d3c2b1e64", "model": "openai:gpt-image@2.6-flare", "positivePrompt": "An e-commerce product hero for the website of a running shoe brand. A single low-top running sneaker in off-white knit with a sage green heel tab and a gum rubber sole stands in three-quarter view on a pale concrete plinth, centered in the lower half of the frame. A kraft paper price tag hangs from the laces on a cotton string and reads \"$129\" in black stamped type. Across the upper third, on a soft sage green backdrop, the headline \"LOOPWAY RUNNER\" is set in large white sans-serif capitals. Soft diffused daylight from the upper left, a gentle shadow falling to the right of the plinth. Straight-on shot at plinth height, 85mm lens. Photoreal studio product photography, no other text.", "width": 2048, "height": 1152 } ]' ``` **CLI**: ```bash runware run openai:gpt-image@2.6-flare \ positivePrompt="An e-commerce product hero for the website of a running shoe brand. A single low-top running sneaker in off-white knit with a sage green heel tab and a gum rubber sole stands in three-quarter view on a pale concrete plinth, centered in the lower half of the frame. A kraft paper price tag hangs from the laces on a cotton string and reads \"\$129\" in black stamped type. Across the upper third, on a soft sage green backdrop, the headline \"LOOPWAY RUNNER\" is set in large white sans-serif capitals. Soft diffused daylight from the upper left, a gentle shadow falling to the right of the plinth. Straight-on shot at plinth height, 85mm lens. Photoreal studio product photography, no other text." \ width=2048 \ height=1152 ``` **JSON**: ```json { "taskType": "imageInference", "taskUUID": "6e1c9a4f-2b87-4d3e-9f05-8a7d3c2b1e64", "model": "openai:gpt-image@2.6-flare", "positivePrompt": "An e-commerce product hero for the website of a running shoe brand. A single low-top running sneaker in off-white knit with a sage green heel tab and a gum rubber sole stands in three-quarter view on a pale concrete plinth, centered in the lower half of the frame. A kraft paper price tag hangs from the laces on a cotton string and reads \"$129\" in black stamped type. Across the upper third, on a soft sage green backdrop, the headline \"LOOPWAY RUNNER\" is set in large white sans-serif capitals. Soft diffused daylight from the upper left, a gentle shadow falling to the right of the plinth. Straight-on shot at plinth height, 85mm lens. Photoreal studio product photography, no other text.", "width": 2048, "height": 1152 } ``` The rest of the surface, with the full parameter list in the [model reference](https://runware.ai/docs/models/openai-gpt-image-2-6-flare): - `width` and `height` set the frame inside an envelope of four rules, and leaving both out hands the choice to the model. Both cases are covered at the end of this guide. - `settings.quality` sets the rendering effort and `settings.thinkingLevel` how much the model plans before it renders, `high` by default, both covered in [quality and thinking level](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/quality-and-thinking-level). - `inputs.referenceImages` takes up to 16 images and turns the request into an edit, covered in [editing images](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/editing-images). For edits that need precise control, GPT-Image-2.6 Sunburst has a guide to [detailed editing](https://runware.ai/docs/models/openai-gpt-image-2-6-sunburst/guides/detailed-editing). - `inputs.markupImage` carries marks drawn over the first reference to show where the edit goes, covered in [markup editing](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/markup-editing). - `settings.background` set to `transparent` returns the subject on an alpha channel, covered in [transparent backgrounds](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/transparent-backgrounds). - `outputFormat` also takes `SVG` and `GIF` on this model, covered in [SVG output](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/svg-output) and [animated GIFs](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/animated-gifs). - `settings.moderation` is `auto` or `low`, where `low` applies less restrictive filtering. ### [Writing a brief the model can plan from](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#writing-a-brief-the-model-can-plan-from) Anything the prompt leaves out is **a decision the model makes for you**. Name a dashboard and stop, and the model picks the panels and every label on them. **Write the brief a designer would need**, and the model plans from the same information. ![A SaaS analytics dashboard named InsightPro with four metric cards, a performance line chart, a top products list, a traffic sources donut and a real-time activity feed](https://runware.ai/docs/assets/output-brief-short.DICsU5RQ_21YKwr.jpg) *The deliverable alone* > **Prompt**: A product screenshot of a SaaS analytics dashboard. ![A light SaaS analytics dashboard with a dark navy sidebar listing Overview, Revenue, Customers, Churn and Settings under the Tallyfield logo, four KPI cards reading MRR $48,290, Active customers 1,284, Churn rate 2.1% and ARPU $37.61, a rising revenue line chart from Jan to Dec, and a Top plans table](https://runware.ai/docs/assets/output-brief-full.COAVE01S_ZVYbIr.jpg) *The full brief* > **Prompt**: A product screenshot of a SaaS analytics dashboard for a subscription business, shown flat and full screen with no device frame, as if captured from a real product. A narrow dark navy sidebar on the left holds the logo "Tallyfield" at the top and five menu items below it, "Overview", "Revenue", "Customers", "Churn" and "Settings", with "Overview" highlighted. Across the top of the main area sit four KPI cards in one row, each with a small gray label above a large figure: "MRR" and "$48,290", "Active customers" and "1,284", "Churn rate" and "2.1%", "ARPU" and "$37.61". Below the cards, a line chart titled "Revenue, last 12 months" fills the left two thirds, rising steadily from left to right, with the months "Jan" to "Dec" along the x-axis. To the right of the chart, a table titled "Top plans" lists three rows: "Pro" with "$21,400", "Team" with "$18,050" and "Starter" with "$8,840". Clean light interface, white cards on a pale gray background, one indigo accent color, crisp legible UI text, no other text. In the first render **the model invented everything**: the product name InsightPro, the metrics and every figure. In the second, every label and figure is a string from the prompt, and each panel sits where the prompt put it. **[Deliverable]** A product screenshot of a SaaS analytics dashboard for a subscription business, shown flat and full screen with no device frame, as if captured from a real product, **[Sidebar]** A narrow dark navy sidebar on the left holds the logo "Tallyfield" at the top and five menu items below it, "Overview", "Revenue", "Customers", "Churn" and "Settings", with "Overview" highlighted, **[KPI row]** Across the top of the main area sit four KPI cards in one row, each with a small gray label above a large figure: "MRR" and "$48,290", "Active customers" and "1,284", "Churn rate" and "2.1%", "ARPU" and "$37.61", **[Chart]** Below the cards, a line chart titled "Revenue, last 12 months" fills the left two thirds, rising steadily from left to right, with the months "Jan" to "Dec" along the x-axis, **[Table]** To the right of the chart, a table titled "Top plans" lists three rows: "Pro" with "$21,400", "Team" with "$18,050" and "Starter" with "$8,840", **[Style]** Clean light interface, white cards on a pale gray background, one indigo accent color, crisp legible UI text, **[Exclusions]** no other text The brief walks the screen **one region at a time**. Each clause says where its region sits, how many things it holds and what they read, so a missing card or a wrong label traces back to the one clause that described it. **Open with the deliverable.** "A product screenshot of a SaaS analytics dashboard" says what the image is for, and "shown flat and full screen with no device frame" rules out a photo of a laptop on a desk. Describe an interface **as a product that already exists**, in terms of its layout and its labels, and leave concept-art language out of it. #### [Counts and positions](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#counts-and-positions) **Write every count as a number.** "Four KPI cards in one row" and "lists three rows" leave nothing for the model to settle. "Some metrics" leaves it to pick how many, and to pick again on every call. **Place each element against the frame or another element**: "on the left", "across the top of the main area", "below the cards", "to the right of the chart". Every position in the brief refers to the frame or to something the model is already placing, the way you would brief a designer on the same screen. ### [Rendering readable text](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#rendering-readable-text) Words to render go in `positivePrompt` with the rest of the scene. **Wrap every string in quotation marks** so the model renders those exact characters, and **say where each string goes and what it is**, such as the header or a row of the schedule. **[Deliverable]** A class schedule poster for a boutique fitness studio, made to post on social media, **[Palette]** Flat graphic design on a deep charcoal background with one bright coral accent color, **[Header]** At the top, the studio name "KYNETIK STUDIO", spelled K-Y-N-E-T-I-K, in heavy white condensed sans-serif capitals, with "SATURDAY CLASSES" in coral directly below it, **[Schedule]** Below the header, five evenly spaced rows, each with the time on the left in coral and the class name on the right in white: "7:00 AM" and "Spin 45", "8:15 AM" and "Power Yoga", "9:30 AM" and "HIIT Circuit", "11:00 AM" and "Pilates Core", "12:15 PM" and "Mobility Flow", **[Footer]** At the bottom, a smaller line reads "Book in the app · 24 spots per class", **[Typography]** Crisp accurate typography, a clear size hierarchy between the header, the times and the class names, generous spacing, **[Exclusions]** no photographs, no other text ![A charcoal class schedule poster headed KYNETIK STUDIO and SATURDAY CLASSES, with five rows pairing coral times from 7:00 AM to 12:15 PM with Spin 45, Power Yoga, HIIT Circuit, Pilates Core and Mobility Flow, above a footer reading Book in the app · 24 spots per class](https://runware.ai/docs/assets/output-text.DlX5MVgF_xiL4E.jpg) > **Prompt**: A class schedule poster for a boutique fitness studio, made to post on social media. Flat graphic design on a deep charcoal background with one bright coral accent color. At the top, the studio name "KYNETIK STUDIO", spelled K-Y-N-E-T-I-K, in heavy white condensed sans-serif capitals, with "SATURDAY CLASSES" in coral directly below it. Below the header, five evenly spaced rows, each with the time on the left in coral and the class name on the right in white: "7:00 AM" and "Spin 45", "8:15 AM" and "Power Yoga", "9:30 AM" and "HIIT Circuit", "11:00 AM" and "Pilates Core", "12:15 PM" and "Mobility Flow". At the bottom, a smaller line reads "Book in the app · 24 spots per class". Crisp accurate typography, a clear size hierarchy between the header, the times and the class names, generous spacing, no photographs, no other text. **Write times and prices exactly as they should print.** Quote "7:00 AM" when the poster should say 7:00 AM, since "seven" or "7am" leaves the format to the model. Pairing each time with its class in one clause, "7:00 AM" and "Spin 45", tells the model **which two strings share a row**. Two more clauses pay off on a text-heavy design. **Spell an invented name letter by letter**, as the prompt does with KYNETIK, because a made-up word has no spelling for the model to recall. Then **end with "no other text"**, so the empty space on the poster stays empty instead of filling with labels nobody wrote. #### [Text in a photograph](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#text-in-a-photograph) Words that belong inside the scene need **the object they are printed on**. The hero prompt puts the price on a kraft paper tag hanging from the laces and asks for black stamped type, which gives the model a material and a print method to render "$129" with. Text laid over a photo is the other case. **Call it a graphic laid over the image** and name the corner or edge it sits in, as the listing banner in the next section does. ### [Choosing a size](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#choosing-a-size) `width` and `height` are optional. **Leave both out and the model picks the frame**, which suits a first draft before the image has a slot to fill. Set them, and the pair has to fit **one envelope with four rules**: - Each side is between 16 and 3840 pixels. - Each side is a multiple of 16. - The aspect ratio is between 1:3 and 3:1. - The area is between 655,360 and 8,294,400 pixels. The top of the area band is exactly 3840 × 2160, so **a 4K frame fits at full size** and the largest square is 2880 × 2880. The common delivery shapes all have a size that passes the four rules: | Deliverable | Ratio | Size | | --- | --- | --- | | Web banner | 3:1 | 2880 × 960 | | Web hero or slide | 16:9 | 2048 × 1152 | | Dashboard screen | 16:10 | 1920 × 1200 | | Square post | 1:1 | 2048 × 2048 | | Feed post | 4:5 | 1280 × 1600 | | Poster | 2:3 | 1280 × 1920 | | Story | 9:16 | 1152 × 2048 | The same listing prompt at 3:1 for a property portal banner, at 2:3 for a social poster, and with no size sent: ![A wide banner of a white two-story clapboard farmhouse with a covered porch and two rocking chairs behind a green lawn, a red JUST LISTED ribbon across the top-left corner and a white label reading $685,000 and 4 bd · 3 ba · 2,450 sq ft in the bottom-right corner](https://runware.ai/docs/assets/output-size-wide.DR-Iuw1__Z2GRXU.jpg) *2880 × 960, a 3:1 web banner* > **Prompt**: A listing photograph for a real estate agency website. A two-story white clapboard farmhouse with a black front door, a covered front porch with two wooden rocking chairs, and a freshly mowed green lawn with a stone path leading to the steps, under a clear late afternoon sky. A bold red ribbon banner runs diagonally across the top-left corner of the photo, laid over the image as a graphic, and reads "JUST LISTED" in white capitals. A white rounded label laid over the bottom-right corner reads "$685,000" in large dark type above a smaller line, "4 bd · 3 ba · 2,450 sq ft". Eye-level shot from the front walk, 24mm lens, the whole house in frame. Photoreal real estate photography, bright natural color, no other text. ![A tall framing of the same farmhouse listing, sky above the roof and the lawn and stone path filling the foreground, with the JUST LISTED ribbon in the top-left corner and the price label in the bottom-right](https://runware.ai/docs/assets/output-size-tall.DBG0hYGF_ZnQ7YE.jpg) *1280 × 1920, a 2:3 social poster* > **Prompt**: A listing photograph for a real estate agency website. A two-story white clapboard farmhouse with a black front door, a covered front porch with two wooden rocking chairs, and a freshly mowed green lawn with a stone path leading to the steps, under a clear late afternoon sky. A bold red ribbon banner runs diagonally across the top-left corner of the photo, laid over the image as a graphic, and reads "JUST LISTED" in white capitals. A white rounded label laid over the bottom-right corner reads "$685,000" in large dark type above a smaller line, "4 bd · 3 ba · 2,450 sq ft". Eye-level shot from the front walk, 24mm lens, the whole house in frame. Photoreal real estate photography, bright natural color, no other text. ![The same farmhouse listing in the frame the model chose, with the JUST LISTED ribbon in the top-left corner and the price label in the bottom-right](https://runware.ai/docs/assets/output-size-auto.q44Nec3F_ryMbt.jpg) *No width or height sent, returned at 1536 × 1024* > **Prompt**: A listing photograph for a real estate agency website. A two-story white clapboard farmhouse with a black front door, a covered front porch with two wooden rocking chairs, and a freshly mowed green lawn with a stone path leading to the steps, under a clear late afternoon sky. A bold red ribbon banner runs diagonally across the top-left corner of the photo, laid over the image as a graphic, and reads "JUST LISTED" in white capitals. A white rounded label laid over the bottom-right corner reads "$685,000" in large dark type above a smaller line, "4 bd · 3 ba · 2,450 sq ft". Eye-level shot from the front walk, 24mm lens, the whole house in frame. Photoreal real estate photography, bright natural color, no other text. Each frame is **laid out again for its shape** rather than cropped from a larger one. The ribbon and the price label keep their corners at every size, because the prompt anchors them to the corners of the frame rather than to the house. **Pick the size before you write the framing clause.** Positions written against the corners and edges of the frame carry over to a new shape. "The house on the left third" was written for a wide frame and has to be rewritten for a tall one. > [!NOTE] > The area floor rules out small renders. 655,360 pixels is 1024 × 640, and no side can be shorter than 480 even at 3:1, so generate a thumbnail at a legal size and resize it downstream. GIF output has its own size rules, covered in [animated GIFs](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/animated-gifs). ### [Tips](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/guides/prompting#tips) 1. **Open with the deliverable.** "A product screenshot" or "a class schedule poster" in the first clause tells the model what the image is for before any detail arrives. 2. **Brief the layout region by region.** One clause per region, each with its position, its count and its exact text. 3. **Write counts as numbers.** "Four KPI cards" is four. "Some metrics" is however many the model settles on. 4. **Quote every string as it should print.** Times and prices included: "7:00 AM", not "7am". 5. **Spell invented names letter by letter.** A made-up brand has no spelling the model can recall. 6. **End text-heavy prompts with "no other text".** It keeps empty space empty. 7. **Give in-scene text a surface and overlay text a corner.** A tag or a sign for text inside the photo, a named corner or edge for a graphic laid over it. 8. **Choose the size first.** The model lays out the frame it is given, so the framing clause and the aspect ratio are one decision.