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)

Grok Imagine Image Pro

Stable Diffusion 3.5 Large

1148 #21

FLUX.1 Kontext [pro]

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

Best AI Models for Portraits

29 models ranked · Last update: August 13, 2026 2:25 AM

#	Model	Price	¢/img	Speed	Elo
1	FLUX.2 [dev] Turbo fal	$	0.8¢		1279
2	Nano Banana 2 Google	$$	2.2¢		1267
3	ImagineArt 1.5 (Preview) Vyro AI	$$	3¢	—	1252
4	Nano Banana Google	$$	3.9¢		1233
5	FLUX.2 [dev] Flash fal	$	0.5¢		1232
6	Z-Image Turbo Alibaba	$	0.5¢		1232
7	FLUX.2 [pro] Black Forest Labs	$$	1.5¢		1232
8	Nano Banana Pro Google	$$$	6.7¢		1230
9	Recraft V4 Recraft AI	$$	4¢		1229
10	GPT Image 1.5 OpenAI	$	0.9¢		1223

11	Recraft V4 Pro Recraft AI	$$$$	25¢		1218
12	FLUX.2 [dev] Black Forest Labs	$$	1.2¢		1216
13	GPT Image 1 Mini OpenAI	$	0.5¢		1206
14	Lucid Origin Leonardo AI	$$	2¢	—	1198
15	Qwen Image 2512 Alibaba	$$	2¢		1198
16	Grok Imagine Image Pro xAI	$$$	7¢		1176
17	Reve Image 1.0 Reve AI	$$	4¢		1173
18	FLUX.1 Krea [dev] Black Forest Labs	$$	2.5¢		1171
19	Grok Imagine Image xAI	$$	2¢		1169
20	Stable Diffusion 3.5 Large Stability AI	$$$	6.5¢		1153
21	FLUX.1 Kontext [pro] Black Forest Labs	$$	4¢		1148
22	HiDream I1 Fast HiDream AI	$	0.5¢		1138
23	Recraft V4.1 Pro Recraft AI	$$$$	25¢		1134
24	Qwen Image 2.0 Alibaba	$$	3.5¢		1120
25	Imagen 4.0 Fast Generate 001 Google	$$	2¢		1108
26	Seedream 5.0 Lite ByteDance	$$	3.5¢		1102
27	Vidu Q2 ShengShu Technology	$$$$	10¢		1044
28	DALL-E 3 OpenAI	$$	4¢		1042
29	DALL-E 2 OpenAI	$$	1.6¢		1034

FLUX.2 [dev] Turbo leads the portrait category with a 1279 Elo and 78.9% win rate, narrowly outpacing Google’s Nano Banana 2 (1267 Elo) despite the latter's higher 81.8% individual win rate. This specialized ranking favors efficiency, as top-tier portrait performance is dominated by "Fast" and "Medium" speed models costing $0.030/img or less.

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

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