---
title: "GPT Image 2.6 SVG Generation: How Good Is It? | Zorse Blog"
description: See GPT Image 2.6 SVG game art examples, compare SVG and WebP file sizes, check drawing limitations, and try a Responses API code sample.
canonical: https://zorse.io/blog/generating-svg-game-art-with-gpt-image-2-6
last-updated: 2026-11-06
---

# GPT Image 2.6 SVG Generation: How Good Is It?

1.  [Blog](https://zorse.io/blog)
2.  GPT Image 2.6 SVG Generation: How Good Is It?

Devlog

The frog was smaller than its thumbnail. The lion showed why file size is only half the story.

By [Austin Greco](https://zorse.io/about) · November 5, 2026 · Updated November 6, 2026

-   [AI](https://zorse.io/blog/tag/ai)
-   [Game art](https://zorse.io/blog/tag/game-art)

![A green frog, lion, penguin and elephant in a layered landscape, with blue vector control points following the frog’s outline](https://zorse.io/assets/gpt-image-26-svg-editorial-hero.BGPMH_nk_TIEGK.webp)

The frog came back as an 11 KB SVG, smaller than its tiny in-game thumbnail. The bright green skin, big eyes and clean black outlines made it easy to like. Beside the original, though, the changes were obvious: a wider smile, taller eyes and feet in different places.

When OpenAI [released Sunburst and Flare on November 4, 2026](https://developers.openai.com/api/docs/changelog#november-2026), I tried the new SVG output on four animals from **Animal Explorer**, my animal-learning game project. I wanted smaller files and artwork that could scale from a phone’s animal picker to a large TV screen.

The frog made a promising first impression. The lion showed how a compact, technically valid SVG could still be a bad drawing. These comparisons explain what to look for, with file sizes and an API example for trying it yourself.

[See the animals](https://zorse.io/blog/generating-svg-game-art-with-gpt-image-2-6#start-with-the-frog) · [Compare file sizes](https://zorse.io/blog/generating-svg-game-art-with-gpt-image-2-6#how-small-are-the-files) · [Try the API example](https://zorse.io/blog/generating-svg-game-art-with-gpt-image-2-6#try-the-svg-request)

## Start with the frog

![Animal Explorer’s original green frog on the left and an SVG frog with larger eyes, a wider smile and more symmetrical legs on the right](https://zorse.io/assets/gpt-image-26-svg-frog.HcNpmCyO_m030q.webp)

The original frog on the left; an 11 KB SVG reinterpretation on the right. Look at the eyes, smile and pose. [View the original artwork.](https://zorse.io/assets/gpt-image-26-svg/frog-original.af707292.webp) [Open the SVG.](https://zorse.io/assets/gpt-image-26-svg/frog.c1ec633c.svg)

The first frog kept the lime-green body, pale throat and friendly expression. Its face and feet remained readable in a small preview. Open the SVG and zoom in: the outlines stay crisp because they are vector shapes.

This **11,068-byte** version came from a detailed written description, **without the source image attached**. It is a new drawing of the frog, with its own expression and pose.

### A reference still leaves room for a redraw

Next, I supplied the original PNG as image context in the Responses API and tried both Sunburst and Flare. Each pair used the same written prompt. For the second pair, I asked for flat cel-shading instead of gradients.

![Sunburst frog with large round eyes, a distinct smiling line above the yellow muzzle and symmetrical front legs](https://zorse.io/assets/gpt-image-26-svg/frog-source-shading-sunburst.abe7dc49.svg)

**Sunburst, gradients.** The grin sits above the yellow muzzle.

![Flare frog with upright large eyes and a broad yellow chin above a tapered belly](https://zorse.io/assets/gpt-image-26-svg/frog-source-shading-flare.eefd35a0.svg)

**Flare, gradients.** The smile follows the top of the pale muzzle.

![Flat-shaded Sunburst frog with black outlines, larger eyes and bright green flat color shapes](https://zorse.io/assets/gpt-image-26-svg/frog-flat-shading-sunburst.446674c9.svg)

**Sunburst, flat shading.** Bright green shapes and black contours.

![Flat-shaded Flare frog with broad yellow muzzle, symmetrical forelegs and green cel-shaded highlights](https://zorse.io/assets/gpt-image-26-svg/frog-flat-shading-flare.998a5373.svg)

**Flare, flat shading.** A broad yellow muzzle and tapered belly.

All four have connected limbs and clear black contours. Flare keeps the smile close to the pale muzzle, while Sunburst draws a separate grin above it. None preserves the exact pose. The earlier text-only frog also used a different prompt, so this does not isolate the benefit of adding a reference.

Flat shading brought a useful surprise. Both flat versions have **zero gradients**, but only one got smaller: Sunburst went from 11,816 to 8,323 bytes, while Flare went from 11,015 to 11,170. The shapes needed for flat shading take space too. Choose it for the look you want, then measure the result.

## How small are the files?

A collection of large animal images adds up. The useful comparison is with Animal Explorer’s existing **WebP assets, including picker thumbnails**, rather than the larger source PNGs.

Existing WebP assets and new SVG drawings, in bytes
| Animal | Full WebP | Picker WebP | New SVG |
| --- | --- | --- | --- |
| Frog | 414,862 | 51,416 | 11,068 |
| Lion, later Flare | 482,880 | 42,370 | 16,037 |
| Penguin, text prompt | 399,656 | 28,758 | 7,933 |
| Elephant, flat revision | 561,966 | 45,018 | 8,939 |

All four selected SVGs are smaller than their picker thumbnails. The frog is about **78% smaller than its 226 × 216 thumbnail**, while its vector edges can stay sharp at larger sizes.

These are different drawings, so the table is not a like-for-like compression test. The numbers measure files on disk. App-download savings, memory use and rendering speed still need testing in a build of the game.

## The lion: more detail did not fix the drawing

An early, simplified lion lost much of the original’s charm. Asking for layered fur and shading produced this more elaborate, 18,545-byte version:

![Original Animal Explorer lion with a rounded russet mane, black contours, compact face and connected front legs](https://zorse.io/assets/gpt-image-26-svg/lion-original.5d3b7823.webp)

**Existing lion.** A rounded mane, compact face and connected front legs.

![Generated lion SVG with swept orange mane tufts, brown outlines and front-leg joins that do not clearly connect to the body](https://zorse.io/assets/gpt-image-26-svg/lion-detailed.8838a456.svg)

**More detailed SVG.** The mane changes, and the front legs look disconnected. [Inspect the vector.](https://zorse.io/assets/gpt-image-26-svg/lion-detailed.8838a456.svg)

The mane sweeps in a different direction, the outlines turn brown, and the front legs look disconnected. Extra detail drew attention away from the compact face and rounded mane that made the original appealing.

A later Flare result, with the original PNG supplied as context, was more convincing. Its paws and tail read as attached, and its face feels closer to the source. The mane, rear haunch and paw placement still change.

![Original Animal Explorer lion with a continuous pointed hairline, compact face, three visible paws and russet mane](https://zorse.io/assets/gpt-image-26-svg/lion-original.5d3b7823.webp)

**Existing artwork.** Watch the mane shape and the position of the paws.

![Flare lion SVG with attached paws and tail, a solid pointed hairline, black main contours and a reshaped mane](https://zorse.io/assets/gpt-image-26-svg/lion-flare-qhigh-chigh.fb968d8e.svg)

**Flare, with reference.** Connected paws and tail, but a different mane.

That version is **16,037 bytes**, smaller than the earlier, less convincing lion. In this case, the better drawing was also the lighter file.

### Look closely at the hairline

The Sunburst lions below used the same source PNG and written prompt. Both used high image quality; I changed the [complexity setting](https://developers.openai.com/api/docs/guides/image-prompting#model-parameters), which controls how much planning the model does, from low to high.

![Sunburst lion at low complexity with a large head, yellow face and a forked mane overlay at the forehead](https://zorse.io/assets/gpt-image-26-svg/lion-sunburst-qhigh-clow.d07e011e.svg)

**Sunburst, low complexity.** Notice the forked tuft above the face.

![Sunburst lion at high complexity with larger highlighted eyes, broad cheeks and yellow gaps beneath a forked forehead tuft](https://zorse.io/assets/gpt-image-26-svg/lion-sunburst-qhigh-chigh.9cfae304.svg)

**Sunburst, high complexity.** More facial highlights, the same hairline problem.

Changing complexity left the path count at **51**, with file sizes of 12,832 and 13,325 bytes. The hairline stayed broken in both.

![Enlarged Sunburst hairline showing two yellow gaps inside a forked brown mane overlay and a black line behind it](https://zorse.io/assets/gpt-image-26-svg/lion-forelock-sunburst.5e92ffed.png)

**Sunburst close-up.** Yellow gaps break up the hairline; a black line cuts across the forehead.

![Enlarged Flare hairline with a continuous brown widow’s peak and no yellow gaps](https://zorse.io/assets/gpt-image-26-svg/lion-forelock-flare.5d64815b.png)

**Flare close-up.** The pointed hairline stays solid.

In the Sunburst close-up, yellow gaps split the tuft and a black line crosses the forehead. Flare’s pointed hairline stays solid.

The lions look convincing at first glance, but the enlarged view reveals where the drawing breaks down. Check hairlines, mouths, paws, shoulders and tails: a small mistake where shapes meet can spoil an otherwise polished character.

There is only one sample per follow-up setting, so this is not a model ranking. The unchanged path count shows why `complexity` should not be treated as a path-count limit.

## A penguin’s proportions, an elephant’s forehead

The penguin shows how much identity can sit in a few proportions. The first text-prompt SVG kept the dark body, pale belly and orange feet, but made the eyes bigger and the body rounder.

![Original Animal Explorer penguin with a tall dark body, white belly, small blue-green eyes and orange feet](https://zorse.io/assets/gpt-image-26-svg/penguin-original.5c24381e.webp)

**Existing penguin.** A tall body and small eyes.

![Generated penguin SVG with larger eyes, a shorter rounder body and outstretched flippers](https://zorse.io/assets/gpt-image-26-svg/penguin.bbb21d4d.svg)

**Text-prompt SVG.** Rounder body, bigger eyes.

Supplying the original PNG in later requests still left room for a redesign. Sunburst spread the flippers and warmed the belly toward beige; Flare kept a narrower body. Both changed the face and beak.

![Sunburst penguin with outstretched dark flippers, pale beige-gray belly and large oval eyes](https://zorse.io/assets/gpt-image-26-svg/penguin-source-shading-sunburst.68f22ef2.svg)

**Sunburst, with reference.** Wider flippers, warmer belly.

![Flare penguin with narrow dark body, white belly, orange feet and reshaped face and beak](https://zorse.io/assets/gpt-image-26-svg/penguin-source-shading-flare.78cfeda2.svg)

**Flare, with reference.** Narrower body, reshaped face.

The elephant offered a useful chance to be more specific. The first SVG looked too sculpted, so I supplied the original PNG and asked for a broad baby forehead, a compact body, modest ears, upright legs and sparse flat shading.

![Original baby elephant with a broad head, pink inner ears, a small curled trunk and compact gray body](https://zorse.io/assets/gpt-image-26-svg/elephant-original.99020c75.webp)

**Existing elephant.** Broad forehead, small curled trunk.

![Gray elephant SVG with dimensional shading, a sculpted head and body, pink inner ears and a curved trunk](https://zorse.io/assets/gpt-image-26-svg/elephant-shaded.52a55cff.svg)

**Shaded SVG.** A more sculpted head and body.

![Revised elephant SVG with a broad rounded forehead, flat gray fills, black outlines and a curved trunk](https://zorse.io/assets/gpt-image-26-svg/elephant-flat.2901c35a.svg)

**Flat revision.** Rounder forehead, simpler shading. [Open the SVG.](https://zorse.io/assets/gpt-image-26-svg/elephant-flat.2901c35a.svg)

The revision moved toward the rounded, simpler treatment I wanted and dropped from **16,275 to 8,939 bytes**. The trunk, feet and silhouette still changed, but the broader forehead and flatter shading gave the next drawing a clear direction. “Make it cute” would have been a much less useful instruction.

That is the most practical prompting lesson from this set: **describe the character’s defining shapes, not just its style.** Eye size, forehead, pose, outline color and the way limbs meet the body give you something concrete to judge in the next result.

## Why tracing was not an easy answer

Before this experiment, I had tried [VTracer](https://github.com/visioncortex/vtracer), which traces raster colors into vector shapes. Different curve, palette and tracing settings kept running into the same problem: the lion’s mane.

![Lion mane close-up showing smooth orange shading on the left and flatter color bands in the traced version on the right](https://zorse.io/assets/gpt-image-26-svg/vtracer-mane.048f19a4.webp)

The original mane is on the left. VTracer turns its soft shading into flatter color bands on the right.

Soft shading became bands of color. Smoothed pixel edges turned into little contours. Combining VTracer fills with [Potrace](https://potrace.sourceforge.net/) outlines meant preparing masks, deciding which dark regions were lines, and assembling the layers. Flattening the mane and adding an explicit stroke cleaned up its boundary, but sacrificed shading.

The two workflows left different kinds of work. Tracing held close to the source pixels and needed cleanup. Generation produced a more freely drawn character and needed a judgment about which changes to keep. That distinction matters more than declaring a winner between these separate experiments.

## Try the SVG request

OpenAI’s [“Generate SVG output” section](https://developers.openai.com/api/docs/guides/image-generation#generate-svg-output) documents SVG generation for GPT Image 2.6. The API first creates a reference image, then uses that image to produce the SVG. That generated reference is separate from an existing game asset you supply as context. **The image-edit endpoint does not support SVG output.** In these tests, supplying the original PNG still produced a new drawing rather than an exact vector copy.

I used the **Responses API**, with `gpt-6.1-sol` as the outer model and Sunburst or Flare selected in the image-generation tool. The saved results identify **Sol as the SVG author** in `svg_usage.model`. The Sunburst and Flare labels above refer to the requested image-generation stage.

Here is the text-only pattern used for the first frog, with a shortened prompt. You will need an API key and access to the named models. Generation is billed, and each run produces a new result.

```
import base64
from pathlib import Path
from openai import OpenAI

client = OpenAI(max_retries=0, timeout=600)

response = client.responses.create(
    model="gpt-6.1-sol",
    input=(
        "Generate exactly one image. A seated lime-green baby frog, "
        "large oval eyes, pale yellow throat and belly, four feet, "
        "smooth true-black contours, restrained shading, "
        "transparent background. No text or scenery."
    ),
    reasoning={"effort": "low"},
    max_output_tokens=8000,
    max_tool_calls=1,
    parallel_tool_calls=False,
    tool_choice={"type": "image_generation"},
    tools=[{
        "type": "image_generation",
        "model": "gpt-image-2.6-sunburst",
        "action": "generate",
        "output_format": "svg",
        "quality": "high",
        "complexity": "high",
        "size": "1024x1024",
        "background": "transparent",
    }],
)

calls = [item for item in response.output
         if item.type == "image_generation_call"]
if len(calls) != 1 or not calls[0].result:
    raise RuntimeError("Expected one completed SVG result")

svg_bytes = base64.b64decode(calls[0].result, validate=True)
Path("frog.svg").write_bytes(svg_bytes)
print(calls[0].model_dump().get("svg_usage"))
```

For the direct Images API, follow the request format in OpenAI’s [SVG output instructions](https://developers.openai.com/api/docs/guides/image-generation#generate-svg-output); it differs from the Responses API example above.

## Before an SVG goes into the game

All **15 generated SVGs** contained vector shapes, without embedded bitmaps, scripts or external resources. These animals have not yet been tested in the running game; small files and crisp browser previews do not tell us how they will look or perform there.

Before replacing an asset, work through four checks:

1.  **Start with the face and silhouette.** Compare against the original before getting attached to the new shading or a small file size.
2.  **Inspect the joins.** Enlarge the hairline, mouth and limb connections, then check that they still read at the smallest intended size.
3.  **Measure against the assets you actually ship.** Include thumbnails and the versions packaged in the game, then test memory use and rendering speed on-device.
4.  **Try it in the real scene.** Check transparency, clipping, light and dark surroundings, and the largest display size you support.

GPT Image 2.6 makes a promising starting point when there is room to reinterpret a character. For an established cast, the face, pose and silhouette need as much attention as the file size. The frog makes the case for trying it. The lion is a good reminder to zoom in.

[Open the 11 KB frog SVG](https://zorse.io/assets/gpt-image-26-svg/frog.c1ec633c.svg) to inspect the shapes, or [try the API example](https://zorse.io/blog/generating-svg-game-art-with-gpt-image-2-6#try-the-svg-request) on one character you know well before changing the whole cast.

For a different take on the same challenge, [see how Bunny Hop’s animation work kept a robot’s original smile](https://zorse.io/blog/smoother-pixel-art-with-rife) while making its body move more smoothly.

[← All posts](https://zorse.io/blog)

Source: [GPT Image 2.6 SVG Generation: How Good Is It?](https://zorse.io/blog/generating-svg-game-art-with-gpt-image-2-6)
