---
title: "AI Image Model Rankings"
description: "Every benchmarked image model with headline criteria."
url: "https://img.ly/ai-benchmarks/models/"
type: "index"
---

> This is the markdown version of [AI Image Model Rankings](https://img.ly/ai-benchmarks/models/). 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).

---

Every model in the IMG.LY GenAI Benchmarks, alphabetical. Each links to
the markdown version of its profile (scores, cost, latency, licensing).

- [FLUX.2](https://img.ly/ai-benchmarks/models/flux-2.md): Black Forest Labs' flagship base model: fast, inexpensive, and strong all-round quality. The default workhorse tier on the IMG.LY AI Gateway.
- [FLUX.2 [dev] Turbo](https://img.ly/ai-benchmarks/models/flux-2-turbo.md): A distilled, very fast and cheap FLUX.2 variant tuned for high-throughput generation.
- [FLUX.2 [pro]](https://img.ly/ai-benchmarks/models/flux-2-pro.md): Black Forest Labs' pro-tier FLUX.2: higher-fidelity output than the base model at a modest price step.
- [Gemini 2.5 Flash Image](https://img.ly/ai-benchmarks/models/gemini-25-flash-image.md): The prior-generation Gemini 2.5 Flash Image (the original Nano Banana), kept as a generational reference.
- [GPT Image 1.5](https://img.ly/ai-benchmarks/models/gpt-image-1-5.md): OpenAI's GPT Image 1.5: strong instruction following and text rendering from the GPT-image line, at a mid-premium price.
- [Ideogram 3.0](https://img.ly/ai-benchmarks/models/ideogram-v3.md): Ideogram 3.0: a model with a reputation for the strongest in-image text rendering.
- [Luma Photon](https://img.ly/ai-benchmarks/models/luma-photon.md): Luma AI's Photon text-to-image model: photographic quality at a low price point.
- [Nano Banana 2](https://img.ly/ai-benchmarks/models/nano-banana-2.md): Google's fast Gemini 3.1 Flash Image model: strong instruction following at a lower price and latency than Nano Banana Pro.
- [Nano Banana 2 Lite](https://img.ly/ai-benchmarks/models/nano-banana-2-lite.md): The budget tier of Google's Nano Banana 2 line: cheapest access to the Gemini image family.
- [Nano Banana Pro](https://img.ly/ai-benchmarks/models/nano-banana-pro.md): Google's flagship LLM-native image model (Gemini 3 Pro Image): top-tier instruction following and text rendering at a premium per-image price.
- [Qwen-Image](https://img.ly/ai-benchmarks/models/qwen-image.md): Alibaba's open-weights Qwen-Image: capable text-to-image with notably strong multilingual text rendering.
- [Recraft V3](https://img.ly/ai-benchmarks/models/recraft-v3.md): Recraft V3: a design-focused model with brand-style controls and (in newer versions) true vector output.
- [Seedream 4.5](https://img.ly/ai-benchmarks/models/seedream-4-5.md): ByteDance's mid-generation flagship, with strong photorealism and prompt adherence at a mid-tier price point.
- [Seedream 5.0 Lite](https://img.ly/ai-benchmarks/models/seedream-5-lite.md): ByteDance's next-generation Seedream 5.0 in a lightweight, low-cost configuration.
- [Stable Diffusion 1.5](https://img.ly/ai-benchmarks/models/stable-diffusion-1-5.md): The 2022 open-weights baseline, included as legacy contrast to show how far design-production readiness has moved since the first mainstream diffusion generation.

---

## 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.