What is the best AI text-to-image model?

Based on blind community voting, FLUX.2 [dev] Turbo is currently the #1 ranked AI text-to-image model with an Elo rating of 1279. Rankings update in real time as new votes come in.

How are AI text-to-image models ranked on Lumenfall?

Lumenfall Arena ranks AI models through blind community voting. In each matchup, two models generate from the same prompt and voters pick the better result without seeing model names. Votes are processed using TrueSkill, a Bayesian rating algorithm developed by Microsoft Research, that produces a single Elo score reflecting each model's relative quality.

What is an Elo rating for AI models?

An Elo rating is a numerical score representing a model's skill relative to other models. Under the hood, Lumenfall uses TrueSkill, which tracks two values per model: mu (estimated skill) and sigma (uncertainty). The displayed Elo is calculated as 1000 + 10 x (mu - 3*sigma), a conservative lower bound. A model must prove itself consistently across many matchups to earn a high rating.

Best AI Models for Portraits

Portraits · Text-to-Image

Elo rankings from blind votes across 1 challenge in this category.

ImagineArt 1.5 (Preview)

Highlights

5 images

Price · Performance

Best models, by

Every ranked model plotted by price against its Elo. The upper-left frontier is the best value: top quality at the lowest cost.

Best Text-to-Image Models by Price

1 model without pricing omitted.

Best AI Models for Portraits

51 models ranked · Last update: October 25, 2026 9:10 AM

#	Model	Price	¢/img	Elo
1	FLUX.2 [dev] Turbo fal	$	0.8¢	1279
2	Nano Banana 2 Google	$$	2.2¢	1268
3	ImagineArt 1.5 (Preview) Vyro AI	$$	3¢	1261
4	Wan 2.7 Alibaba	$$	3¢	1253
5	Z-Image Turbo Alibaba	$	0.5¢	1242
6	Qwen Image 2512 Alibaba	$$	2¢	1238
7	Recraft V4 Recraft AI	$$	4¢	1236
8	FLUX.2 [dev] Flash fal	$	0.5¢	1233
9	Nano Banana Google	$$	3.9¢	1232
10	FLUX.2 [pro] Black Forest Labs	$$	1.5¢	1232

11	Nano Banana Pro Google	$$$	6.7¢		1229
12	GPT Image 1.5 OpenAI	$	0.9¢		1228
13	Recraft V4 Pro Recraft AI	$$$$	25¢		1215
14	FLUX.2 [dev] Black Forest Labs	$$	1.2¢		1212
15	GPT Image 2 OpenAI	$$	3.9¢		1212
16	Lucid Origin Leonardo AI	$$	2¢	—	1204
17	GPT Image 1 Mini OpenAI	$	0.5¢		1201
18	Reve Image 1.0 Reve AI	$$	4¢		1196
19	FLUX.1 Kontext [pro] Black Forest Labs	$$	4¢		1196
20	Wan 2.7 Pro Alibaba	$$$	7.5¢		1195
21	HiDream I1 Full HiDream AI	$$$	5¢		1188
22	Grok Imagine Image Pro xAI	$$$	7¢		1181
23	Qwen Image 2.0 Alibaba	$$	3.5¢		1176
24	Recraft V4.1 Pro Recraft AI	$$$$	25¢		1175
25	FLUX.2 [klein] 9B Black Forest Labs	$	0.6¢		1171
26	Grok Imagine Image xAI	$$	2¢		1168
27	Bria FIBO Bria	$$	4¢		1161
28	Nano Banana 2 Lite Google	$$	1.7¢		1159
29	FLUX.2 [max] Black Forest Labs	$$	3¢		1157
30	Stable Diffusion 3.5 Large Stability AI	$$$	6.5¢		1156

FLUX.2 [dev] Turbo leads the portrait category with a 1,279 Elo and 78.9% win rate, narrowly outpacing Google’s Nano Banana 2 by 11 Elo points. While current-generation FLUX and Google models dominate the top tier, Alibaba’s Qwen Image 2512 maintains a 100% win rate in limited head-to-head matchups, indicating high competitive potential despite its lower Elo ranking (1,238).

Rivalries

Aggregate head-to-head across the arena

Stable Diffusion 3.5 Large HiDream I1 Fast

67% 1 challenge 22%

Think a model is ranked wrong? Cast your vote

Highlighted challenges

GPT Image 2 is first to make it GPT Image 2

Text-to-Image Art Photorealism

The Reversed Rodeo

This competition tests how well AI image models truly understand language versus how much they rely on visual habits from their training data. The prompt is deliberately simple on the surface but devilishly hard in practice. Most models default to the familiar trope of an astronaut riding a horse. By forcing the reversal, we measure three critical capabilities that separate good models from great ones: Strict instruction following (including negations) Accurate subject-object relationships and spatial hierarchy Resistance to strong dataset biases

Text-to-Image 3D Imaging & Modeling Photorealism

Geometric Composition

A spatial-reasoning test. Each object has a precise relationship (inside, on top, behind, seen through the glass), so it measures whether a model follows explicit placement instructions and handles transparency and refraction rather than just approximating the scene.

View all challenges

Keep the arena honest

Cast your vote

Pick winners in blind matchups. Every vote nudges the Elo and shapes these rankings.

Cast Your Vote

Suggest a prompt

Got an idea worth testing? Submit a prompt and watch the models battle it out.

Vote Now

Models · slot A

Portraits · Text-to-Image

Highlights

Best models, by

Best Text-to-Image Models by Price

Best Text-to-Image Models by Speed

Best AI Models for Portraits

Rivalries

Highlighted challenges

The Reversed Rodeo

Geometric Composition

Cast your vote

Suggest a prompt