---
title: "Benchmark: Character Series: Desk"
description: "15 image models compared on the canonical \"Character Series: Desk\" prompt (Consistency & Repeatability)."
url: "https://img.ly/ai-benchmarks/prompts/s02-character-desk/"
type: "benchmark-prompt"
category: "Consistency & Repeatability"
suite: "pilot-0"
---

> This is the markdown version of [Benchmark: Character Series: Desk](https://img.ly/ai-benchmarks/prompts/s02-character-desk/). For all pages in one file, see [llms-full.txt](https://img.ly/llms-full.txt). For an index of all available pages, see [llms.txt](https://img.ly/llms.txt).

---

# Benchmark: Character Series: Desk

Category: Consistency & Repeatability.
Use cases: Template & asset packs (U8), Personalization at scale (U6).
Suite: pilot-0. Every model runs the identical prompt with default
parameters and fixed seeds. No per-model tuning.

## Why this benchmark

Run two of the character-consistency set. Holding the same face, hair, apron and glasses across a new pose and setting is exactly what breaks when teams try to generate a coherent illustrated series.

## Canonical prompt

> Maya, a red-haired botanist in a green apron and round glasses, reading a field guide at a wooden desk, consistent character design, storybook illustration style.

## Scored assertions

- red-haired woman in a green apron and round glasses
- reading a field guide at a wooden desk
- storybook illustration style
- character design matches the other two scenes in the series

## Results by model

### FLUX.2

[Model profile](https://img.ly/ai-benchmarks/models/flux-2.md)

- seed 1111: 1024×768, 2.1s, $0.013, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 2222: 1024×768, 3.7s, $0.013, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 3333: 1024×768, 2.0s, $0.013, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5

### FLUX.2 [pro]

[Model profile](https://img.ly/ai-benchmarks/models/flux-2-pro.md)

- seed 1111: 1024×768, 16.1s, $0.040, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2-pro--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 2222: 1024×768, 13.9s, $0.040, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2-pro--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 3333: 1024×768, 10.9s, $0.040, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2-pro--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5

### FLUX.2 [dev] Turbo

[Model profile](https://img.ly/ai-benchmarks/models/flux-2-turbo.md)

- seed 1111: 1024×768, 2.9s, $0.015, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2-turbo--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 2222: 1024×768, 2.5s, $0.015, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2-turbo--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 3333: 1024×768, 2.0s, $0.015, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--flux-2-turbo--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5

### Gemini 2.5 Flash Image

[Model profile](https://img.ly/ai-benchmarks/models/gemini-25-flash-image.md)

- sample 1: 1024×1024, 12.3s, $0.039, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--gemini-25-flash-image--n0.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 2: 1024×1024, 7.3s, $0.039, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--gemini-25-flash-image--n1.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 3: 1024×1024, 8.8s, $0.039, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--gemini-25-flash-image--n2.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5

### GPT Image 1.5

[Model profile](https://img.ly/ai-benchmarks/models/gpt-image-1-5.md)

- sample 1: 1024×1024, 37.2s, $0.120, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--gpt-image-1-5--n0.webp)
  - Cost: 3.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 2: 1024×1024, 37.4s, $0.120, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--gpt-image-1-5--n1.webp)
  - Cost: 3.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 3: 1024×1024, 40.0s, $0.120, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--gpt-image-1-5--n2.webp)
  - Cost: 3.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5

### Ideogram 3.0

[Model profile](https://img.ly/ai-benchmarks/models/ideogram-v3.md)

- seed 1111: 1024×1024, 17.4s, $0.060, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--ideogram-v3--s1111.webp)
  - Cost: 3.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- seed 2222: 1024×1024, 17.1s, $0.060, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--ideogram-v3--s2222.webp)
  - Cost: 3.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- seed 3333: 1024×1024, 17.2s, $0.060, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--ideogram-v3--s3333.webp)
  - Cost: 3.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5

### Luma Photon

[Model profile](https://img.ly/ai-benchmarks/models/luma-photon.md)

- seed 1111: 1536×1536, 15.6s, $0.019, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--luma-photon--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 4.0 / 5
- seed 2222: 1536×1536, 16.8s, $0.019, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--luma-photon--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 4.0 / 5
- seed 3333: 1536×1536, 13.0s, $0.019, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--luma-photon--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 4.0 / 5

### Nano Banana 2

[Model profile](https://img.ly/ai-benchmarks/models/nano-banana-2.md)

- sample 1: 1408×768, 13.9s, $0.100, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-2--n0.webp)
  - Cost: 3.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 2: 1408×768, 13.3s, $0.100, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-2--n1.webp)
  - Cost: 3.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 3: 1408×768, 13.2s, $0.100, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-2--n2.webp)
  - Cost: 3.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5

### Nano Banana 2 Lite

[Model profile](https://img.ly/ai-benchmarks/models/nano-banana-2-lite.md)

- sample 1: 1408×768, 4.1s, $0.020, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-2-lite--n0.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 2: 1408×768, 3.9s, $0.020, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-2-lite--n1.webp)
  - Cost: 4.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 3: 1408×768, 5.2s, $0.020, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-2-lite--n2.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5

### Nano Banana Pro

[Model profile](https://img.ly/ai-benchmarks/models/nano-banana-pro.md)

- sample 1: 1024×1024, 22.4s, $0.360, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-pro--n0.webp)
  - Cost: 1.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 2: 1024×1024, 24.2s, $0.360, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-pro--n1.webp)
  - Cost: 1.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5
- sample 3: 1024×1024, 37.2s, $0.360, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--nano-banana-pro--n2.webp)
  - Cost: 1.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 3.0 / 5

### Qwen-Image

[Model profile](https://img.ly/ai-benchmarks/models/qwen-image.md)

- seed 1111: 1024×768, 6.9s, $0.030, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--qwen-image--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 2222: 1024×768, 5.6s, $0.030, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--qwen-image--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5
- seed 3333: 1024×768, 7.1s, $0.030, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--qwen-image--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 2.0 / 5

### Recraft V3

[Model profile](https://img.ly/ai-benchmarks/models/recraft-v3.md)

- seed 1111: 1024×1024, 7.1s, $0.040, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--recraft-v3--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 2.5 / 5
  - Resolution: 3.0 / 5
- seed 2222: 1024×1024, 7.6s, $0.040, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--recraft-v3--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 2.5 / 5
  - Resolution: 3.0 / 5
- seed 3333: 1024×1024, 7.4s, $0.040, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--recraft-v3--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 3.0 / 5
  - Prompt Adherence: 2.5 / 5
  - Resolution: 3.0 / 5

### Seedream 4.5

[Model profile](https://img.ly/ai-benchmarks/models/seedream-4-5.md)

- seed 1111: 2048×2048, 12.0s, $0.048, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--seedream-4-5--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 5.0 / 5
- seed 2222: 2048×2048, 12.0s, $0.048, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--seedream-4-5--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 5.0 / 5
- seed 3333: 2048×2048, 11.1s, $0.048, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--seedream-4-5--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 2.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 5.0 / 5

### Seedream 5.0 Lite

[Model profile](https://img.ly/ai-benchmarks/models/seedream-5-lite.md)

- seed 1111: 2048×2048, 34.3s, $0.020, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--seedream-5-lite--s1111.webp)
  - Cost: 4.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 5.0 / 5
- seed 2222: 2048×2048, 23.0s, $0.020, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--seedream-5-lite--s2222.webp)
  - Cost: 4.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 5.0 / 5
- seed 3333: 2048×2048, 33.4s, $0.020, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--seedream-5-lite--s3333.webp)
  - Cost: 4.0 / 5
  - Latency: 1.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 5.0 / 5

### Stable Diffusion 1.5

[Model profile](https://img.ly/ai-benchmarks/models/stable-diffusion-1-5.md)

- seed 1111: 512×512, 2.1s, $0.010, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--stable-diffusion-1-5--s1111.webp)
  - Cost: 5.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 1.0 / 5
- seed 2222: 512×512, 2.5s, $0.010, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--stable-diffusion-1-5--s2222.webp)
  - Cost: 5.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 1.0 / 5
- seed 3333: 512×512, 2.0s, $0.010, [image](https://storage.googleapis.com/imgly-ai-benchmarks/s02-character-desk--stable-diffusion-1-5--s3333.webp)
  - Cost: 5.0 / 5
  - Latency: 4.0 / 5
  - Prompt Adherence: 3.8 / 5
  - Resolution: 1.0 / 5

Result images: [https://img.ly/ai-benchmarks/prompts/s02-character-desk/](https://img.ly/ai-benchmarks/prompts/s02-character-desk/) (interactive grid with lightbox).

## Frequently asked questions

**Why am I seeing three samples per benchmark?**

Image generation is stochastic: the same prompt produces different images on every run, so a single sample measures luck, not ability. Every model runs each benchmark three times with fixed seeds (1111, 2222, 3333), or three unseeded samples where the API accepts no seed. Scores average all three samples, and the consistency benchmarks measure the variation itself.

**Do all AI models get the identical prompt?**

Yes. Every model receives the same prompt text with default parameters and no per-model tuning, so differences in output reflect the model, not prompt engineering. The suite is versioned and prompts are append-only, which keeps historical scores comparable.

**Which AI image model is best at consistency & repeatability?**

The results on this page are scored on this exact prompt, so the strongest model for it is easy to spot; this benchmark sits in the Consistency & Repeatability category. Scores are per model version and reflect this benchmark only. For a ranking across every benchmark see the model rankings, and to weight the numbers by a specific job see the use-case pages.

**How are the benchmark scores calculated?**

Each image is scored 0 to 5 per criterion. Measured criteria (resolution, latency, cost, transparency, color accuracy) are computed automatically; quality criteria (text accuracy, prompt adherence, composition) are judged by an automated Claude vision tier against each prompt’s checklist. Page scores are unweighted means over all of a model’s runs in that scope. Blind expert-panel review has not run yet; the dataset is pilot-0.

**Can I use AI-generated images like these in production?**

Model output is a starting point, not a finished asset. Production work usually needs background removal, exact brand colors or editable text, none of which generation guarantees on every run. The IMG.LY AI Editor gives your users those controls to refine any model’s output to production quality.

**How often is the benchmark updated?**

The suite re-runs on notable model releases so the rankings stay current. The results shown are the pilot-0 dataset, scored by measured criteria plus an automated Claude vision tier, with blind expert review planned. Prompts are versioned and append-only, so scores stay comparable across runs.


---

## More Resources

- **[IMG.LY Website](https://img.ly/index.md)** - Creative editing SDKs for photo, video, and design
- **[Documentation](https://img.ly/docs/cesdk/)** - CE.SDK developer documentation
- **[Contact Sales](https://img.ly/forms/contact-sales.md)** - Get a custom quote. A public JSON API accepts the request directly, no account or key needed. Ask your user for consent and their details first.