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

Based on blind community voting, Seedream 4.5 is currently the #1 ranked AI text-to-image model with an Elo rating of 1281. 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 3D Imaging & Modeling

3D Imaging & Modeling · Text-to-Image

Elo rankings from blind votes across 2 challenges in this category.

Grok Imagine Image Pro

ImagineArt 1.5 (Preview)

Stable Diffusion 3.5 Large

Imagen 4.0 Ultra Generate 001

Highlights

10 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 3D Imaging & Modeling

29 models ranked · Last update: July 11, 2026 10:30 PM

#	Model	Price	¢/img	Speed	Elo
1	Seedream 4.5 ByteDance	$$	4¢		1281
2	FLUX.2 [dev] Turbo fal	$	0.8¢		1257
3	Grok Imagine Image Pro xAI	$$$	7¢		1255
4	Nano Banana 2 Google	$$	2.2¢		1251
5	FLUX.2 [dev] Flash fal	$	0.5¢		1251
6	ImagineArt 1.5 (Preview) Vyro AI	$$	3¢	—	1244
7	FLUX.2 [max] Black Forest Labs	$$	3¢		1240
8	Nano Banana Pro Google	$$$	6.7¢		1239
9	Wan 2.6 Alibaba	$$	3¢		1232
10	GPT Image 1.5 OpenAI	$	0.9¢		1231

11	Seedream 4.0 ByteDance	$$	3¢	1231
12	FLUX.2 [flex] Black Forest Labs	$$$	6¢	1230
13	Recraft V4 Recraft AI	$$	4¢	1230
14	GPT Image 1 Mini OpenAI	$	0.5¢	1219
15	Stable Diffusion 3.5 Large Stability AI	$$$	6.5¢	1218
16	Seedream 5.0 Lite ByteDance	$$	3.5¢	1213
17	Nano Banana Google	$$	3.9¢	1204
18	FLUX.2 [pro] Black Forest Labs	$$	1.5¢	1202
19	Imagen 4.0 Ultra Generate 001 Google	$$$	6¢	1198
20	Z-Image Turbo Alibaba	$	0.5¢	1198
21	FLUX.2 [dev] Black Forest Labs	$$	1.2¢	1196
22	Recraft V4 Pro Recraft AI	$$$$	25¢	1195
23	Qwen Image 2512 Alibaba	$$	2¢	1194
24	Nano Banana 2 Lite Google	$$	1.7¢	1189
25	Grok Imagine Image xAI	$$	2¢	1186
26	Reve Image 1.0 Reve AI	$$	4¢	1176
27	DALL-E 3 OpenAI	$$	4¢	1093
28	DALL-E 2 OpenAI	$$	1.6¢	1058
29	FLUX.1 [schnell] FP8 Black Forest Labs	Free	Free	1050

ByteDance's Seedream 4.5 leads the 3D entry with a 1281 Elo and 70.0% win rate, displacing several models that typically dominate the overall general-purpose leaderboard. Despite the focus on modeling depth, the budget-tier FLUX.2 [dev] Turbo remains highly competitive at 1257 Elo while costing 80% less per image than the category leader.

Rivalries

Aggregate head-to-head across the arena

Nano Banana Stable Diffusion 3.5 Large

50% 2 challenges 50%

Qwen Image 2512 Grok Imagine Image

56% 2 challenges 44%

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

3D Imaging & Modeling · 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 3D Imaging & Modeling

Rivalries

Highlighted challenges

The Reversed Rodeo

Geometric Composition

Cast your vote

Suggest a prompt