What is the best AI text to image model?

Based on blind community voting, Nano Banana Pro is currently the #1 ranked AI text to image model with an Elo rating of 1285. 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.

ARENA Leaderboard

See how AI image models stack up against each other. How it works

Best AI Models for Photorealism

Ranking the best AI text to image models for photorealism, based on 5 blind community-voted challenges.

Highlights

10 images

Best AI Models for Photorealism

38 models ranked · Last update: June 14, 2026 9:10 PM

#	Model	Price	¢/img	Speed	Elo
1	Nano Banana Pro Google	$$$	6.7¢		1285
2	GPT Image 1.5 OpenAI	$	0.9¢		1270
3	GPT Image 1 Mini OpenAI	$	0.5¢		1252
4	GPT Image 2 OpenAI	$$	3.9¢		1243
5	ImagineArt 1.5 (Preview) Vyro AI	$$	3¢	—	1238
6	Seedream 4.5 ByteDance	$$	4¢		1233
7	Grok Imagine Image Pro xAI	$$$	7¢		1229
8	Z-Image Turbo Alibaba	$	0.5¢		1226
9	FLUX.2 [max] Black Forest Labs	$$	3¢		1220
10	Qwen Image 2.0 Pro Alibaba	$$$	7.5¢		1219

11	Nano Banana Google	$$	3.9¢		1216
12	Nano Banana 2 Google	$$	2.2¢		1214
13	Seedream 4.0 ByteDance	$$	3¢		1206
14	FLUX.2 [pro] Black Forest Labs	$$	1.5¢		1205
15	FLUX.2 [klein] 9B Black Forest Labs	$	0.6¢		1203
16	Recraft V4 Recraft AI	$$	4¢		1203
17	Seedream 5.0 Lite ByteDance	$$	3.5¢		1203
18	Qwen Image 2512 Alibaba	$$	2¢		1198
19	FLUX.2 [dev] Flash fal	$	0.5¢		1197
20	FLUX.2 [dev] Black Forest Labs	$$	1.2¢		1192
21	FLUX.1 [schnell] FP8 Black Forest Labs	Free	Free		1191
22	Wan 2.7 Alibaba	$$	3¢		1191
23	Wan 2.7 Pro Alibaba	$$$	7.5¢		1190
24	Grok Imagine Image xAI	$$	2¢		1180
25	Qwen Image Max Alibaba	$$$	7.5¢		1179
26	Imagen 4.0 Fast Generate 001 Google	$$	2¢		1178
27	DALL-E 3 OpenAI	$$	4¢		1175
28	FLUX.2 [dev] Turbo fal	$	0.8¢		1174
29	Stable Diffusion 3.5 Large Stability AI	$$$	6.5¢	—	1166
30	FLUX.2 [flex] Black Forest Labs	$$$	6¢		1163

Nano Banana Pro leads the Photorealism category with a 1285 Elo and 82.7% win rate, outperforming premium models from OpenAI and ByteDance. OpenAI presents the highest value in this category, as the low-tier GPT Image 1.5 maintains an 81.0% win rate and 1270 Elo at less than 15% of the market leader's price.

Elo vs Cost

1 model without pricing omitted

Elo vs Speed

21 models waiting for enough speed data

Highlighted Battles

The most competitive head-to-head matchups, selected by closeness and vote count.

FLUX.2 [dev] vs ImagineArt 1.5 (Preview)

Candid Street Photography

50% · 50%

Nano Banana vs Z-Image Turbo

Candid Street Photography

50% · 50%

GPT Image 1 Mini vs Qwen Image 2.0 Pro

The Capybara Taxi Driver

50% · 50%

FLUX.1 Kontext [dev] vs Seedream 5.0 Lite

Magic Burger Explosion: Fiery Photorealism Challenge

50% · 50%

Think a model is ranked wrong? Cast your vote

Challenges

Candid Street Photography Photorealism

Prompt

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

Top 3

GPT Image 1 Mini

Nano Banana Pro

GPT Image 1.5

Bottom 3

Stable Diffusion 3.5 Large

Recraft V4 Pro

FLUX.2 [flex]

24 models competed

Vote on this challenge All results & rankings

Magic Burger Explosion: Fiery Photorealism Challenge Text Rendering Photorealism Product, Branding & Commercial

Prompt

“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”

Top 3

GPT Image 2

Z-Image Turbo

Nano Banana Pro

Bottom 3

Wan 2.7 Pro

Grok Imagine Image

Stable Diffusion 3.5 Large Turbo

15 models competed

Vote on this challenge All results & rankings

Chalkboard Menu Text Rendering Photorealism

Prompt

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

Top 3

DALL-E 3

GPT Image 1 Mini

Qwen Image 2.0 Pro

Bottom 3

FLUX.2 [klein] 9B

Wan 2.7 Pro

Wan 2.7

9 models competed

Vote on this challenge All results & rankings

The Capybara Taxi Driver Photorealism

Prompt

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

Top 3