---
title: Pick an image model family for the job
display: 'Pick an image *model* family for the job'
nav_title: Image models guide
summary:
  - "Narrow more than 750 models to two or three candidates, run them on your brief, and keep the winner."
  - "Answer three questions first: the job, what you start from and your budget. The model library's filters answer each one."
  - "Generate the same prompt with each candidate and compare the results with Compare Images; the price shows on Generate."
description: The image model families as of October 2026, what each does well, and how to shortlist two or three for your brief.
section: images
order: 30
type: guide
level: Build
roles: [all]
time: { read: 6, do: 15 }
needs: ["Any plan with credits"]
last_verified: 2026-11-11
models_checked: ["GPT Image 2.5 Sunburst", "GPT Image 2.5 Flare", "Nano Banana 2.1", "Seedream 5.0 Pro", "MAI Image 2.5 Pro", "Krea 2 Large", "Krea 2 Medium", "Ideogram 4.5", "Recraft V4 Styles Pro SVG", "Retro Diffusion Plus", "Krea 3", "Z-Image"]
related: [generate-images, text-and-typography-in-images]
video: tutorials/image-models-guide.mp4
video_caption: Pick a model for the job
about: "Scenario has more than 750 models, and the right one depends on the job. This lesson narrows them down with the filters of the model library, tests a new model against the one you used before with Compare Images, then finds a different model for a second job: the same character, in a new scene, made from his image. The models and prices in this lesson are as of November 2026."
chapters:
  - { at: 0, title: "Three questions", image: "/media/images/images/image-models-guide/ch-01-three-questions.webp" }
  - { at: 74.3, title: "Compare", image: "/media/images/images/image-models-guide/ch-02-compare.webp" }
  - { at: 96.5, title: "Another job", image: "/media/images/images/image-models-guide/ch-03-another-job.webp" }
thumb: images/image-models-guide/thumb.webp
steps:
  - title: "Open the model library"
    text: "Create › Images, click the model's name at the top of the panel, then View model library at the bottom of the list."
  - title: "Answer the three questions"
    text: "Tick the job under Capabilities (Text to Image), what you start from under Input kind (here only a prompt), and set Budget and Speed under Budget and speed."
  - title: "Try a new model"
    text: "Tick New · last 30 days under Shortlists, hover Krea 3 to read its rank, typical time, cost tier and samples, and click Use this model."
  - title: "Generate with the same prompt and size"
    text: "The prompt stays when you switch models. Krea 3: Model Berry (quality), Image Size 16:9 (1024x576) to match the first image, Reasoning Level Low, Negative Prompt and Seed empty. Click Generate."
  - title: "Compare the two images"
    text: "Select the Krea 3 image and the GPT Image 2.5 Sunburst one with the circle in each corner, click Compare Images, then Split and drag the line."
  - title: "Find a model for another job"
    text: "Clear the filters, tick Image under Input kind and Edit with Prompts under Capabilities, and use Nano Banana 2.1, which keeps a character as he is."
  - title: "Add the reference and generate"
    text: "Reference images › Select from Library: the character from the first lesson, Confirm. Replace the prompt with what changes and what must stay, then click Generate."
    prompt: |-
      The same character standing on a rocky canyon ridge at sunrise. Keep his armor, shield and pose.
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: "The tank hero made in [Generate images](/images/generate-images) with GPT Image 2.5 Sunburst: give the agent its asset ID. It's the image to compare against and the reference for the second job."
  - title: "Shortlist with recommend"
    text: "recommend ranks models for a task by measured quality, speed and cost, and is free. Krea 3 is too new for some lists, so the agent looks it up by name."
    prompt: |-
      Use recommend to rank models for text to image, quality first, and give me the top three with what each is best at and its cost tier. Then find Krea 3 with search and give me its model ID. Don't run anything yet.
  - title: "Brief the agent: same prompt, new model"
    text: "Only the model changes: the prompt is read from the first image, and the size matches it at 16:9."
    prompt: |-
      Read the prompt of the tank hero with asset_get. Run it word for word with Krea 3, one image, at 16:9 (1024 x 576), with its Berry (quality) engine and Reasoning Level low, no negative prompt and no seed. Read the parameter names with model_schema_get first. Quote the cost with a dry run first and wait for my go. Then show me the Krea 3 image next to the GPT Image 2.5 Sunburst one at the same size.
  - title: "The second job: same character, new scene"
    text: "An edit from an image needs a model that reads references and keeps a character. Accept when the armor, shield and pose are kept in the new scene; reject a changed character."
    prompt: |-
      Use Nano Banana 2.1 (model_google-gemini-nano-banana-2-1), one image, with referenceImages set to an array holding only the tank hero's asset ID. Quote the cost with a dry run first and wait for my go.

      Prompt, word for word:
      The same character standing on a rocky canyon ridge at sunrise. Keep his armor, shield and pose.
  - title: "File the test and report"
    prompt: |-
      Create a collection called "Model tests: tank hero" and add the original, the Krea 3 image and the Nano Banana 2.1 image to it. Report each image's model, settings, asset ID and cost, and the total cost spent.
updated: 2026-11-11
canonical: https://learn.scenario.com/images/image-models-guide
---

Last updated: 2026-11-11

# Pick an image model family for the job

> The image model families as of October 2026, what each does well, and how to shortlist two or three for your brief.

In short:

- Narrow more than 750 models to two or three candidates, run them on your brief, and keep the winner.
- Answer three questions first: the job, what you start from and your budget. The model library's filters answer each one.
- Generate the same prompt with each candidate and compare the results with Compare Images; the price shows on Generate.


Scenario has more than 750 models, and the right one depends on the job. This lesson narrows them down with the filters of the model library, tests a new model against the one you used before with **Compare Images**, then finds a different model for a second job: the same character, in a new scene, made from his image.

:::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. In the image panel, click the model's name, then **View model library**.
2. Tick the job under **Capabilities**, what you start from under **Input kind**, and set **Budget** and **Speed**.
3. Hover a model to read its details, then click **Use this model**.
4. Generate with the same prompt and size, select both images and click **Compare Images**.
5. For a new job, clear the filters and start again: the right model changes with the job.
:::

## Before you start

- **Have an image to compare against.** This lesson tests models on the character from [Generate images](https://learn.scenario.com/images/generate-images.md), made with GPT Image 2.5 Sunburst. Any image you made with a known prompt works.
- **Where it lives:** **Create** › **Images** opens the image panel. The model sits at the top of the left column.
- **Three questions decide the model:** what the job is, what you start from, and what you can spend. The model library has a filter for each.
- **Change one thing at a time.** To judge a model, keep the prompt and the size the same, so only the model changes.

## Step 1: Open the model library

In the image panel, click the model's name at the top, here **GPT Image 2.5 Sunburst**. A short list opens, with a search box, a row of icons to filter by what a model makes (images, video, audio, 3D and more), and each model's rank and typical time. At the bottom, click **View model library**.

![The model list open in the image panel, with View model library at the bottom](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/05e9b04dcdc4943e480260bafc403fbacb53b4ecdc6b1c745d9ae17d88fcda07.webp)

The library opens as **Choose a model**: every model in Scenario, from Scenario, partners and your team. The filters on the left answer the three questions.

## Step 2: Answer the three questions

**What is the job?** That's **Capabilities**: make an image from text, edit one, upscale it, remove a background, turn it into a vector, and more. Each capability shows how many models can do it. Click **Show all** to see the full list. The first job here is a character from a text prompt, so tick **Text to Image**.

**What do you start from?** That's **Input kind**. Here, just a prompt, so leave it. If you start from reference images, tick **Image**, then check in the model's details how many references it can use.

![Output Kind set to Image, and Image under Input Kind](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/89590b2c30a9518fef42bb74688889f393a571aad86d537efb5616ec3f8e5039.webp)

**What is your budget?** Under **Budget and speed**, **Budget** sets the maximum cost, from **$** to **$$$**. For one great image, you can spend more. For lots of images, a cheaper model keeps the cost down. The **Speed** slider below sets how long a model may take to make an image, from seconds up to **Any speed**.

![Text to Image ticked under Capabilities, with the Budget buttons and the Speed slider below](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/bec92a42a735f2274e920a5756c1922a593d5a090047dcd55b8d76d1ae217e19.webp)

Every filter you tick shows as a chip above the list, with the number of models left.

## Step 3: Try a new model

To see the most recent image models, tick **New · last 30 days** under **Shortlists**. With **Text to Image** still ticked, three models are left. **Krea 3** is one of them.

Hover a model to see its details on the right:

- **Recommended:** its rank. New models may show **Not ranked**.
- **Typical time:** how long one image usually takes.
- **Cost:** its cost tier, from $ to $$$. The exact cost shows on the **Generate** button.
- A short description, its **Input** and **Output**, its capabilities, and **Content samples** made with it.

Krea 3 takes text only and makes polished images from detailed prompts, from editorial photos and products to anime, watercolor and pixel art. Click **Use this model**.

![The library filtered to the new text-to-image models, with Krea 3's details on the right](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/6a8ebd26c59bda88109908ec2a3e1b40663385dcce11946f4c73967e56849d2e.webp)

To read everything about a model before you pick it, click **View model details**, or **Browse in Model Hub** at the bottom of the library.

## Step 4: Generate with the same prompt and size

The prompt stays in the panel when you switch models, so only the model changes. The settings do change: each model has its own. For Krea 3:

- **Model:** the engine. **Berry (quality)** is for quality, Jam for speed.
- **Image Size:** match the image you compare against. The first image was 16:9, so pick **16:9 (1024x576)**.
- **Reasoning Level:** leave it at **Low**. Raise it when a prompt packs in a lot of text or detail.
- **Negative Prompt** and **Seed:** leave them empty.

![Krea 3 with the same prompt and Image Size set to 16:9 (1024x576)](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/22972daaed232d741e2af9c0065c964db8287c6283c5f7d16563d9216545470d.webp)

Click **Generate**. The cost shows on the button before you click.

## Step 5: Compare the two images

When the Krea 3 image is ready, select it and the image from before: click the circle in the corner of each one in the Session. A bar appears at the bottom with **2 selected**. Click **Compare Images**.

![The selection bar: 2 selected, Select All, Clear and Compare Images](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/49829cf21344ce33f5bbef3527f44756503a0228d94c030baa57d5aa3c05da6a.webp)

**Compare Images** opens on **Side by Side**, with each model's name under its image.

![Compare Images, Side by Side: Krea 3 on the left, GPT Image 2.5 Sunburst on the right](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/867a3c1653183419d958efba4a93bbbb0d0c6b79623fdb0ad59c0918282be860.webp)

Click **Split** to lay one image over the other, then drag the line to see what each model did differently: the build of the character, the shield, the light, the background.

![Split view, with the line dragged across the character](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/afb5eacc1a767499f5fe8f517e5517892220daf23968755db6ce6c98f98616e9.webp)

Here, Krea 3 made a chunkier, more cartoon-like character, and GPT Image 2.5 Sunburst a taller, more detailed one. Neither is wrong: the one that fits your brief wins.

:::check
**Accept when:** the model follows every part of the prompt you care about (subject, pose, framing, style), at the size you need, within your budget and time.
**Reject when:** it drops or changes something the prompt asked for, its style doesn't fit the project, or it costs or takes more than the job allows. Try the next model on your shortlist.
:::

## Step 6: Find a model for another job

The second job is the same character in a new scene, made from his image. The job and the input have changed, so the model has to change too.

1. Open the model library again and clear the filters.
2. You start from an image: tick **Image** under **Input kind**.
3. The job is to edit it with a prompt: tick **Edit with Prompts** under **Capabilities**.

The list changes. Krea 3 is gone, because it only reads text. **Nano Banana 2.1** generates and edits images with up to 14 references, and it keeps a character as he is. Click **Use this model**.

![The library filtered to Input: Image and Edit with Prompts, with Nano Banana 2.1's details](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/219dfae1d78993ba9841d3ff8d02c1eff2c5d8f7c9e54151d7dd27ef61bd4b6c.webp)

## Step 7: Add the reference and generate

1. Open **Reference images** and click **Select from Library**.
2. Pick the character from the first lesson and click **Confirm**. The image shows under **Reference images**.
3. Replace the prompt with what changes, and what must stay.

![Nano Banana 2.1 with the character under Reference images and the new prompt being typed](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/8b35b6dda6625b10733f9f19f93ab3733a71575d4f59df99f42e1745ae2259e4.webp)

The prompt the film uses:

```
The same character standing on a rocky canyon ridge at sunrise. Keep his armor, shield and pose.
```

Click **Generate**. The same character stands in a new scene.

![The result: the same character with his shield, on a canyon ridge at sunrise](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/657762ce3f6e1dcf29414eb23eb19558724b43ac36d80a9ffbad0ccc83d40b59.webp)

The **Info** panel next to the image shows the model, the prompt, the reference image and every setting, so you can reload the setup for the next version.

![The Info panel: Nano Banana 2.1, the prompt, the reference image and the settings](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/3e571c9a3756e22bf84e7b191b8b422061f8c986d6bdc5e3d909e1005f0a3023.webp)

## The model library filters

| Filter | What it answers | Example |
|---|---|---|
| **Capabilities** | What the model does | Text to Image, Edit with Prompts, Image Upscale, Remove Background, Vectorize, Pixelate |
| **Output kind** | What it makes | Image, Video, Audio, 3D, World, Text |
| **Input kind** | What you give it | Text, Image, Video, Audio, 3D |
| **Provider** | Who made it | Scenario, Recraft AI, BFL, Ideogram, Krea and more |
| **Shortlists** | A ready-made selection | New · last 30 days |
| **Budget** | The highest cost tier you accept | $, $$, $$$ |
| **Speed** | The longest typical time you accept | From seconds to Any speed |

The search box at the top finds a model by name or provider.

## Image model families compared

These are the models this lesson meets, with what their details and the Knowledge Center say they do best.

| Model | Starts from | Best for |
|---|---|---|
| GPT Image 2.5 Sunburst | Text or images | Detailed, precise images |
| GPT Image 2.5 Flare | Text or images | Fast, high-quality everyday content, from social posts to product shots and quick concepts |
| Nano Banana 2.1 | Text, up to 14 references, or a video | Keeping a character or product as it is in new scenes; panoramic and very tall formats |
| Krea 3 | Text only | Polished images from detailed prompts, with crisp text on posters, signs and labels |
| Ideogram 4.5 | Text or images | Posters, logos and packaging with accurate text; edits with up to four references and a mask |
| Z-Image | Text or images | Photorealistic images, with text in English and Chinese |
| MAI Image 2.5 | Text or images | Photorealistic generation and editing |
| Krea 2 Large | Text | Photograph-grade results with grain and motion blur |
| Krea 2 Medium | Text, style references | A chosen illustrated or anime look |
| Recraft V4 SVG and V4 Pro SVG | Text | Real vector files (SVG) for logos and icons |
| Retro Diffusion Plus | Text | Pixel illustrations, character portraits and scenes |

Models come and go every month. Treat this table as a starting shortlist and check the library's **New · last 30 days** before a big project.

## Tips for a fair test

- **Keep the prompt, the size and the image count the same.** Otherwise you compare settings, not models.
- **Test on your real brief,** not on the model's samples. A model that shines on landscapes may miss your character's details.
- **Shortlist two or three models,** not ten. Generate each once, compare, and keep the winner.
- **Start with a base model.** If none fits a project's style after a few tries, a trained model may be the answer. See [Give a whole team one brand look](https://learn.scenario.com/playbooks/brand-style-model.md).
- **Check what a model accepts.** The details show its **Input**; a text-only model ignores reference images.

## Common problems

| What you see | What to do |
|---|---|
| The model you want isn't in the list | A filter hides it. Clear the filters, or search by name |
| The library shows no models | Two of your filters exclude each other. Untick one |
| The new model ignores your reference image | It only reads text. Filter by **Input kind** › **Image** and pick another |
| The two images can't be compared fairly | Match **Image Size** and the prompt, then generate again |
| **Compare Images** doesn't show | Select exactly the images you want: the circle in each image's corner |
| The character changed in the new scene | Use a model built to keep a character, such as Nano Banana 2.1, and say what to keep in the prompt |

## What's next

You can pick a model for the job. Next, write prompts that get the most out of it in [Write better prompts](https://learn.scenario.com/methods/prompt-images.md). For images with words in them, see [Text and typography in images](https://learn.scenario.com/images/text-and-typography-in-images.md). To run a full model test for a team, follow [Run a model shoot-out for your studio](https://learn.scenario.com/playbooks/compare-models-for-your-studio.md).

Source: https://learn.scenario.com/images/image-models-guide