---
title: Generate images from the image panel
display: '*Generate* images from the image panel'
nav_title: Generate images
summary:
  - "The image panel turns a description, and optionally references, into new images you can check and reuse."
  - "Choose the model first: it decides which references and settings the panel shows below it."
  - "Open it from Create > Images; the Generate button shows the price in CU before you click."
description: Use every part of the image generator, from model and prompt to references, size, count, quality and the results view.
section: images
order: 10
type: guide
level: Start
roles: [all]
time: { read: 7, do: 10, wait: 1 }
needs: ["Any plan with credits; the example run uses GPT Image 2.5 Sunburst"]
last_verified: 2026-11-11
models_checked: ["GPT Image 2.5 Sunburst", "GPT Image 2.5 Flare", "Nano Banana 2.1", "Ideogram 4.5"]
hero: images/generate-images/voltaris-tank-sunburst.webp
related: [your-first-image, image-settings-explained, image-models-guide, prompt-images]
video: tutorials/generate-images.mp4
video_caption: Generate images
about: "The image panel turns a written description into new images. This lesson walks through it from top to bottom and makes a game character with GPT Image 2.5 Sunburst: two takes of a tank hero for an invented hero shooter, at 2048 × 1152. Then it shows what you can do with the result. The models and prices in this lesson are as of November 2026."
chapters:
  - { at: 0, title: "The image panel", image: "/media/images/images/generate-images/ch-01-image-panel.webp" }
  - { at: 110.4, title: "Generate", image: "/media/images/images/generate-images/ch-02-generate.webp" }
  - { at: 122.6, title: "The result", image: "/media/images/images/generate-images/ch-03-the-result.webp" }
thumb: images/generate-images/thumb.webp
steps:
  - title: "Pick a model"
    text: "Create › Images, then click the model's name at the top of the panel and pick GPT Image 2.5 Sunburst. The model decides which references and settings appear below it."
  - title: "Write the prompt"
    text: "Subject first, then pose and framing, background, light, style, and what must not appear. Keep the style paragraph the same in every prompt for this world."
    prompt: |-
      Character art for VOLTARIS, an invented free-to-play hero shooter: the tank hero, a broad-shouldered bearded man with dark skin and a short black topknot, in riveted burnt-orange armor with cyan light strips. On the left side of the picture, a huge hexagonal energy shield glowing amber, nearly as tall as he is, held in his right hand with its bottom edge on the ground. He stands upright, full body, front three-quarter view, looking at the camera with a calm, confident expression. Behind him an empty metal landing platform on a floating salvage island, a few patched canvas awnings far back, open sky with soft late-afternoon light. The whole figure and the whole shield in frame with space around them, eye-level camera. No text, no logos, no watermark.

      Style: stylized 3D at the standard of the best free-to-play hero shooters: bold readable silhouettes, appealing expressive faces, hand-tuned stylized PBR (painted metal, soft cloth, rubber), saturated but controlled palette, cinematic key light with a cool rim.
  - title: "Add reference images, if you need them"
    text: "Reference Images takes a drag and drop, Select from Library, Upload or Sketch. This character needs none, so leave it empty."
  - title: "Choose the settings"
    text: "Settings: Image Count 2, Dimensions 16:9 (2048 × 1152), Quality High, Background Auto."
  - title: "Generate"
    text: "The cost shows on the Generate button. Click it, or press Cmd/Ctrl + Enter; the takes appear in the Session tab."
  - title: "Open the result"
    text: "Click a take to open it. The Info panel shows the model, the full prompt and every setting; Details adds the type, size and date."
  - title: "Reuse, upscale or edit it"
    text: "Use as Reference, Reload Parameters or Enhance from the bar above the image; the ... menu holds Edit with Prompts, Remove Background, Vectorize and the other tools."
  - title: "Find your images in the session"
    text: "Close the viewer and use the filters: Type, All, Date, Tags, Models, Collections. Reset clears the view without deleting anything."
agent_steps:
  - title: "Connect the Scenario MCP"
    text: "Connect your agent and sign in once at [mcp.scenario.com](https://mcp.scenario.com). Then tell it which Scenario team and project to use, so every file lands there."
  - title: "Give the agent the files"
    text: "Nothing to upload: this character is made from the prompt alone, with no reference."
  - title: "Brief the agent"
    text: "The same model, prompt and settings as the web app, so the takes match."
    prompt: |-
      Use GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst): width 2048, height 1152, quality "high", background "auto", numOutputs 2. No reference. Quote the cost with a dry run first and wait for my go.

      Prompt, word for word:
      Character art for VOLTARIS, an invented free-to-play hero shooter: the tank hero, a broad-shouldered bearded man with dark skin and a short black topknot, in riveted burnt-orange armor with cyan light strips. On the left side of the picture, a huge hexagonal energy shield glowing amber, nearly as tall as he is, held in his right hand with its bottom edge on the ground. He stands upright, full body, front three-quarter view, looking at the camera with a calm, confident expression. Behind him an empty metal landing platform on a floating salvage island, a few patched canvas awnings far back, open sky with soft late-afternoon light. The whole figure and the whole shield in frame with space around them, eye-level camera. No text, no logos, no watermark.

      Style: stylized 3D at the standard of the best free-to-play hero shooters: bold readable silhouettes, appealing expressive faces, hand-tuned stylized PBR (painted metal, soft cloth, rubber), saturated but controlled palette, cinematic key light with a cool rim.

      When the job is done, show me both takes with asset_display.
  - title: "Check and redo"
    text: "Accept when the armor colors, the topknot and the shield on the left, held in his right hand, match the prompt, the whole figure is in frame and no text, logo or watermark appeared. Reject a missing or swapped detail, a malformed hand or shield, or a cut-off figure."
    prompt: |-
      Check each take against the prompt: the burnt-orange armor with cyan strips, the topknot, the amber shield on the left held in his right hand, the whole figure in frame, and no text, logos or watermark. If a take fails, change one thing in the prompt or the settings, tell me what you changed, and run it once more after a new quote.
  - title: "File the results and report"
    prompt: |-
      Create a collection called "VOLTARIS tank hero" and add the takes I keep to it. Report the model, the settings, every asset ID and the total cost spent, so I can reuse a take later as a reference by its asset ID.
updated: 2026-11-11
canonical: https://learn.scenario.com/images/generate-images
---

Last updated: 2026-11-11

# Generate images from the image panel

> Use every part of the image generator, from model and prompt to references, size, count, quality and the results view.

In short:

- The image panel turns a description, and optionally references, into new images you can check and reuse.
- Choose the model first: it decides which references and settings the panel shows below it.
- Open it from Create > Images; the Generate button shows the price in CU before you click.


The image panel turns a written description into new images. This lesson walks through it from top to bottom and makes a game character with **GPT Image 2.5 Sunburst**: two takes of a tank hero for an invented hero shooter, at 2048 × 1152. Then it shows what you can do with the result.

:::note As of November 2026
The models, settings and prices in this article are the ones Scenario offered in November 2026. New models and updates arrive often, so check the model library for newer options before you choose.
:::

:::steps Quick version
1. Open **Create** › **Images**.
2. Pick a model at the top of the panel. It decides which settings appear below it.
3. Write the prompt: subject, pose, background, light, style, and what must not appear.
4. Set **Image Count**, **Dimensions**, **Quality** and **Background**, then click **Generate**.
5. Open a result to read its **Info**, reuse it, upscale it or edit it.
:::

## Before you start

- **Where it lives.** The image panel is under **Create** › **Images** in the top bar. You set everything up in the column on the left, and your images appear on the right, in the **Session** tab.
- **The model comes first.** Each model accepts different inputs. When you change the model, the reference and settings sections below it change too, so pick the model before you tune anything else.
- **Credits.** Every run uses credits. The cost shows on the **Generate** button and updates as you change the settings.
- **What you need.** A description of the image you want. A reference image is optional; this lesson doesn't use one.

## Step 1: Pick a model

Click the model's name at the top of the panel to open the list.

- Search by name in the box at the top of the list.
- Use the row of icons under it to filter by what a model makes: **ALL**, images, video, audio, 3D and more.
- Each model shows its rank and about how long a run takes.
- **View model library**, at the bottom of the list, opens the full library, where you can compare every model with examples.

For this character, pick **GPT Image 2.5 Sunburst**, a model built for detailed, precise images. The panel opened on its faster sibling, **GPT Image 2.5 Flare**, which suits everyday work.

![The model list open in the image panel, with the search box, the type filters, ranks and run times](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/662e36ef29ecb9fae1a3dd994d268711bae2868ef43fb5d7106151d5c63cadd5.webp)

## Step 2: Write the prompt

The prompt is your description of the image. A clear order helps the model:

1. The subject first: who or what, and what they look like.
2. The pose and the framing.
3. The background.
4. The light.
5. The style.
6. What must not appear.

This is the prompt the film uses. The last paragraph is the game's style. Keep it the same in every prompt for this world, so every image of it looks the same.

```
Character art for VOLTARIS, an invented free-to-play hero shooter: the tank hero, a broad-shouldered bearded man with dark skin and a short black topknot, in riveted burnt-orange armor with cyan light strips. On the left side of the picture, a huge hexagonal energy shield glowing amber, nearly as tall as he is, held in his right hand with its bottom edge on the ground. He stands upright, full body, front three-quarter view, looking at the camera with a calm, confident expression. Behind him an empty metal landing platform on a floating salvage island, a few patched canvas awnings far back, open sky with soft late-afternoon light. The whole figure and the whole shield in frame with space around them, eye-level camera. No text, no logos, no watermark.

Style: stylized 3D at the standard of the best free-to-play hero shooters: bold readable silhouettes, appealing expressive faces, hand-tuned stylized PBR (painted metal, soft cloth, rubber), saturated but controlled palette, cinematic key light with a cool rim.
```

![The prompt box filled in, with the three prompt tools under it](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/9eb1fb361c418a9d9378cdeef44c113cf20b67cccbd2c527b79ef933060c55d8.webp)

Under the box are three prompt tools:

- The first icon writes a new prompt from scratch, suited to the current model.
- **Prompt Spark** (the sparkle icon) improves the prompt you wrote, adding detail to a few words or a rough idea.
- The last icon translates your prompt into English.

Above the box, undo, redo and a trash icon let you step back or clear the prompt.

## Step 3: Add reference images, if you need them

Below the prompt, open **Reference Images**. A reference shows the model something words can't: a character to keep, a style to match, an object to place. You can:

- **Drag & drop or paste** an image into the box.
- **Select from Library** to pick an image you already have in Scenario.
- **Upload** a file from your computer.
- **Sketch** a rough guide by hand.

This character doesn't need one, so leave it empty. When you use several, say in the prompt what each one is for, for example "Image 1 is the character, image 2 is the setting". How many references a model accepts depends on the model.

![Reference Images open, with Drag & drop or paste, Select from Library, Upload and Sketch](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/7951b7698fa7c03f2c3c6248fc5659ad5ac77f38cebd0ad80e6138315c885c10.webp)

## Step 4: Choose the settings

Open **Settings**. These are the settings GPT Image 2.5 Sunburst shows; another model can show others.

- **Image Count** is how many images one run makes. Set it to **2**, to get two takes of the same prompt to choose from.
- **Dimensions** sets the size in pixels. Open the presets and pick **16:9**, at **2048 × 1152**.
- **Quality** goes from low up to max. Higher looks better and takes longer. **High** is a good choice for a final; low is enough to test an idea.
- **Background** stays on **Auto**. Choose transparent when you need a cutout, like an icon or a sticker.

![Settings with Image Count at 2, Dimensions 2048 × 1152, Quality High and Background Auto](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/d3447370fe73f631611c60ff3728f988f8009fc5f757fae585c6139fe4de1277.webp)

Each of these is explained in more depth, with the settings of other models, in [Image settings explained](https://learn.scenario.com/images/image-settings-explained.md).

## Step 5: Generate

The **Generate** button shows what the run costs, and it updates as you change the count, the size or the quality. Click it, or press Cmd/Ctrl + Enter.

Your images start in the **Session** tab, as tiles marked **Generating**. A detailed image like this takes under a minute. You can keep working on the next prompt while it runs.

## Step 6: Open the result

Here are the two takes from the same prompt. Click one to open it full size.

The **Info** panel on the right shows the model, the full prompt and every setting (here Image Count 2, Width 2,048, Height 1,152, Quality High, Background Auto), so you always know how an image was made. **Details**, under it, adds the type, the size in pixels and when it was made. Use the arrows on each side, or the strip of thumbnails, to move between images, and the zoom controls under the image to check details.

![One of the two takes open in the viewer, with the Info panel showing the model, prompt and settings](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/9883db36b6c8d369880c6e1e7f03e7ae5924c8603be20f8c537a5892d164f2bb.webp)

## Step 7: Reuse, upscale or edit it

The bar above the image is where the next step starts.

- **Use as Reference** sends the image back to the panel as a reference, to build the next image on it.
- **Reload Parameters** restores the exact setup: model, prompt and settings. Change one thing, generate again, and you know what made the difference.
- **Enhance** upscales it. See [Upscale images](https://learn.scenario.com/images/upscale-and-enhance-images.md).

![The viewer's bar: Use as Reference, Reload Parameters, Enhance and the ... menu](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/04018462638a447d8fbb51cb2ceeddb967db0f9cb050ee5aedfcd1def86eec91.webp)

The **...** menu next to **Enhance** holds the other tools: **Convert to 3D**, **Convert to Video**, **Edit with Prompts**, **Retouch**, **Expand**, **Remove Background**, **Pixelate**, **Vectorize**, **Find Similar Content**, **Run Quality Gate** and **Run IP Detection**. On the right of the bar are the download icon (PNG, JPEG or WebP), delete and **Collections**.

![The ... menu open, from Convert to 3D down to Run IP Detection](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/6757ef2a921fd47e068ba42996de77967a655d6a910d14ebca5500e8203a2759.webp)

## Step 8: Find your images in the session

Close the viewer to go back to your session. The filters above the images narrow the view:

![The filter bar: Type, All, Date, Tags, Models, Collections and Reset](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/eea434269fef00ccad92f8d7ef5dcc02e5dc0fe0fee60f3cd3a1095a0d4bcd4e.webp)

- **Type** shows only some kinds of results: generations, enhancements, background removals, uploads and so on.
- **All**, **Date**, **Tags**, **Models** and **Collections** narrow by who made it, when, how it's tagged, which model made it and where it's filed.
- **Reset** clears the view without deleting anything. Your images stay in your library.

![The Type filter open, with Generate, Enhance, Restyle, Expand, Vectorize, Edit with Prompts, Pixelate, Remove Background and Upload](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/46bcad20574025bb11db584b938496b52e7adea38dd1b72c31e303f41263d495.webp)

On the right of the filter bar, the slider changes the size of the thumbnails, and the layout icon switches how they're arranged.

:::check
**Accept when:** the subject matches the prompt (here the armor colors, the topknot, the shield on the left, held in his right hand), the whole figure is in frame, nothing you excluded appears (text, logos, watermarks), and the style matches the rest of your project.
**Reject when:** a part of the prompt is missing or swapped, hands or the prop are malformed, the figure is cut off, or text appeared. Change one thing in the prompt or the settings with **Reload Parameters**, and run it again.
:::

## The panel at a glance

| Part | What it does | In this lesson |
|---|---|---|
| **Model** | The AI that makes the image; decides what the panel shows below | GPT Image 2.5 Sunburst |
| **Prompt** | Your description of the image, with prompt tools under it | Character, pose, background, light, style, exclusions |
| **Reference Images** | Pictures that guide the model | None |
| **Image Count** | Images per run | 2 |
| **Dimensions** | Size in pixels, from presets | 16:9, 2048 × 1152 |
| **Quality** | Effort per image; higher is slower | High |
| **Background** | Full image or cutout | Auto |
| **Generate** | Starts the run; shows the cost | |

## Common problems

| What you see | What to do |
|---|---|
| A setting from another lesson is missing | You're on a different model. Each model shows only the settings it accepts. |
| The image ignores part of the prompt | Put the subject first and keep one idea per sentence. Say where things are ("on the left side of the picture"). |
| Text or a logo appears | Add "No text, no logos, no watermark" to the end of the prompt. |
| Two images of the same world look different | Keep the same style paragraph, word for word, in every prompt. |
| The run takes long | High quality and large sizes take longer. Test at a lower quality, then run the final at high. |
| Your images seem gone after **Reset** | Reset only clears the session view. The images are still in your library. |

## What's next

Now that you know the panel, learn what each setting does on different models in [Image settings explained](https://learn.scenario.com/images/image-settings-explained.md), then pick the right model for each job with the [Image models guide](https://learn.scenario.com/images/image-models-guide.md). To write better prompts, see [Prompt images](https://learn.scenario.com/methods/prompt-images.md).

Source: https://learn.scenario.com/images/generate-images