Why did FLUX 1.1 Pro win the Image — Product photo benchmark?

FLUX 1.1 Pro scored highest across the 5 rated dimensions (Photorealism, Material accuracy, Lighting direction, Prompt adherence, E-commerce readiness). FLUX 1. See the per-model scorecard above for the specific strengths and weaknesses on each dimension.

Can I trust these benchmark results?

We ran the exact same prompt 3-5 times on each model with temperature 0.7 where configurable, then averaged. Scores are editorial — honest, careful, reproducible — but not an academic study with 1,000 runs. The exact prompt is published above so you can verify yourself.

How often is this benchmark updated?

Last run: 2026-09-23. We re-run when a tested model gets a major version bump (Midjourney v6 → v7, Claude 3.5 → 4, etc.) or quarterly if nothing changes. If a new model enters the category (e.g. a new image model competing with Midjourney), it gets added to the leaderboard within 30 days of launch.

Which model is the best value for money on this task?

Imagen 3 (Vertex). For most users, the price-performance winner matters more than the overall winner — if you're running thousands of generations a month, a 10× cheaper model that scores 1-2 points lower is often the right call.

How can I reproduce this benchmark?

The exact prompt is in the "The prompt" section above. Copy it, run it on these 5 models (FLUX 1.1 Pro, Midjourney v6.1, Imagen 3 (Vertex), Stable Diffusion 3.5, DALL-E 3) with temperature 0.7, and score each output on Photorealism, Material accuracy, Lighting direction, Prompt adherence, E-commerce readiness. Your results will be within one point of ours on most dimensions.

Best AI model for e-commerce product photography

Task: Studio-grade product photo for Shopify / Amazon.

Image Generation5 modelsLast run: 2026-09-23

🏆 Winner

FLUX 1.1 Pro

🥈 Runner-up

Midjourney v6.1

💰 Price-performance

Imagen 3 (Vertex)

FLUX 1.1 Pro is the clear winner for e-commerce product photography — material realism and lighting consistency across regens are the two things it does better than every competitor right now. Midjourney is a close second but often adds spurious logo-shaped details that need cleanup. For high-volume Shopify stores, Vertex's Imagen 3 at ~2¢/image is a serious cost consideration.

The prompt (identical across all runs)

Copy-paste prompt

Product photography, a minimalist stainless-steel coffee tumbler, matte black finish, placed on a cream marble pedestal, warm Scandinavian studio lighting from top-right, soft rim light, shallow depth of field, 4:5 aspect ratio, shot on Hasselblad H6D 100C, no logos, no text, no watermark, ultra-clean, Instagram shoppable aesthetic.

Leaderboard

Rank	Model	Total /50	Cost / run
🥇	FLUX 1.1 Pro	50	5.0¢
🥈	Midjourney v6.1	47	4.0¢
🥉	Imagen 3 (Vertex)	45	2.0¢
#4	DALL-E 3	41	4.0¢
#5	Stable Diffusion 3.5	36	1.0‰ cent

Needed 3 regens to avoid plasticky material. Not production-ready without touch-up.

Methodology

• Each model ran the exact same prompt 3-5 times (temperature 0.7 where configurable).
• We scored each run across 5 dimensions on a 1-10 scale, then averaged for the final.
• Cost is per completed run, rounded to the nearest 0.1¢.
• Last run: 2026-09-23. We re-run benchmarks when a model receives a major version bump.
• These are editorial benchmarks, not an academic study. We publish the exact prompt so you can reproduce.

More image generation benchmarks

Image — Cinematic portrait

Photorealistic cinematic portrait with correct hands and faces.

Image — Anime

High-quality anime-style illustration.

Image — Logo mark

A clean, scalable logo mark that reads at any size.

FAQs — Image — Product photo

The prompt (identical across all runs)

Copy-paste prompt

Product photography, a minimalist stainless-steel coffee tumbler, matte black finish, placed on a cream marble pedestal, warm Scandinavian studio lighting from top-right, soft rim light, shallow depth of field, 4:5 aspect ratio, shot on Hasselblad H6D 100C, no logos, no text, no watermark, ultra-clean, Instagram shoppable aesthetic.

Rank

Model

Total /50

Cost / run

🥇

FLUX 1.1 Pro

5.0¢

🥈

Midjourney v6.1

4.0¢

🥉

Imagen 3 (Vertex)

2.0¢

DALL-E 3

4.0¢

Stable Diffusion 3.5

1.0‰ cent

Per-model scorecard

🥇 FLUX 1.1 Pro

50 / 50 · 5.0¢ per run

Photorealism

10/10

Material accuracy

10/10

Lighting direction

10/10

Prompt adherence

10/10

E-commerce readiness

10/10

Perfect material rendering — the "matte black" vs "stainless steel" contrast was exactly right. No visual artifacts.

Midjourney v6.1

47 / 50 · 4.0¢ per run

Photorealism

10/10

Material accuracy

9/10

Lighting direction

10/10

Prompt adherence

9/10

E-commerce readiness

9/10

Beautiful but added a subtle logo-shaped blur on the tumbler — would need Photoshop cleanup.

Imagen 3 (Vertex)

45 / 50 · 2.0¢ per run

Photorealism

9/10

Material accuracy

9/10

Lighting direction

9/10

Prompt adherence

9/10

E-commerce readiness

9/10

Google's product-focused model. Clean. Follows lighting instructions precisely.

DALL-E 3

41 / 50 · 4.0¢ per run

Photorealism

8/10

Material accuracy

7/10

Lighting direction

8/10

Prompt adherence

10/10

E-commerce readiness

8/10

Best at literal prompt adherence (actually drew a tumbler, not a mug). Material rendering a step behind FLUX.

Stable Diffusion 3.5

36 / 50 · 1.0‰ cent per run

Photorealism

7/10

Material accuracy

7/10

Lighting direction

7/10

Prompt adherence

8/10

E-commerce readiness

7/10

Needed 3 regens to avoid plasticky material. Not production-ready without touch-up.

Methodology

• Each model ran the exact same prompt 3-5 times (temperature 0.7 where configurable).

• We scored each run across 5 dimensions on a 1-10 scale, then averaged for the final.

• Cost is per completed run, rounded to the nearest 0.1¢.

• Last run: 2026-09-23. We re-run benchmarks when a model receives a major version bump.

• These are editorial benchmarks, not an academic study. We publish the exact prompt so you can reproduce.