Skip to main content

HunyuanImage 3.0 Instructvs.Wan 2.7 Image Pro

Which one is better?

In our own test both are on par. Neither is in the arena. Neither has an API price.

Same prompt, two images

Same task, the first image of each. The task with the biggest difference is preselected.

HunyuanImage 3.0 Instruct: Character and detail, first image from the fixed test run
HunyuanImage 3.0 Instruct43 out of 100
Wan 2.7 Image Pro: Character and detail, first image from the fixed test run
Wan 2.7 Image Pro68 out of 100

Result for “Character and detail”:Wan 2.7 Image Pro slightly ahead

Prompt given to both modelsCreate a square cinematic full-body portrait of a fictional bicycle courier waiting under a transparent umbrella at a rainy tram stop in Hamburg at blue hour. She wears a mustard raincoat, navy trousers, red sneakers, a silver helmet, and carries a teal messenger bag. Keep both hands visible, render the bicycle correctly, use realistic wet-street reflections, and include no readable brand names.

What the rating looks at: Anatomy, clothing, and spatial consistency.

“Ahead”: better in all three rating rounds. “Slightly ahead”: a higher value, but not in every round.

Test protocol of the images

Both models receive the same archived prompt in exactly one request, and the first result counts. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier and prompt processing can still differ. The images are a practical visual test, not a reconstruction of the arena configuration.

Character and detail

HunyuanImage 3.0 Instruct: fal, requested 1024x1024, n=1, seed=480451513, prompt expansion disabled, estimated cost $0.094372, generated Aug 14, 2026, 1:51 PM. Source

Wan 2.7 Image Pro: fal, requested 1024x1024, n=1, seed=1941203496, estimated cost $0.075000, generated Nov 1, 2026, 9:25 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

HunyuanImage 3.0 Instruct image SHA 256: 7c813735994e5781c420b23e15898e1d4c8b9a83b24dae9c72e9d7b08fe7ceb4

Wan 2.7 Image Pro image SHA 256: 0bd2cf4922b58d78d0e6ec3d804aaccd427e5317066816fdc039ca5c80f4de28

Infographic

HunyuanImage 3.0 Instruct: fal, requested 1024x1024, n=1, seed=1316714523, prompt expansion disabled, estimated cost $0.094372, generated Aug 14, 2026, 1:52 PM. Source

Wan 2.7 Image Pro: fal, requested 1024x1024, n=1, seed=1839059937, estimated cost $0.075000, generated Nov 1, 2026, 9:26 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

HunyuanImage 3.0 Instruct image SHA 256: a9c50516fcbe8008d3d67c0651882f7c712aff66ee244b7f8aa7b83c0a67aaab

Wan 2.7 Image Pro image SHA 256: caa6b4e95e0676d9867358db906f1f029dd320960e9dd1b8300283a5e2723077

Product photography

HunyuanImage 3.0 Instruct: fal, requested 1024x1024, n=1, seed=1892985637, prompt expansion disabled, estimated cost $0.094372, generated Aug 14, 2026, 1:51 PM. Source

Wan 2.7 Image Pro: fal, requested 1024x1024, n=1, seed=1277346407, estimated cost $0.075000, generated Nov 1, 2026, 9:24 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

HunyuanImage 3.0 Instruct image SHA 256: 89ed8da585fcce3df9f76584dfc426a5142fe3b950c79a306a7ce3b79746ed99

Wan 2.7 Image Pro image SHA 256: 1ed875886c86963322fdf329bf809943b96886fb4f373197e1654256316ac67c

Typography and layout

HunyuanImage 3.0 Instruct: fal, requested 1024x1024, n=1, seed=1326433162, prompt expansion disabled, estimated cost $0.094372, generated Aug 14, 2026, 2:41 PM. Source

Wan 2.7 Image Pro: fal, requested 1024x1024, n=1, seed=1291974856, estimated cost $0.075000, generated Nov 1, 2026, 9:23 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

HunyuanImage 3.0 Instruct image SHA 256: 4563cdd9bb047b4df3316484fcc4fe369ba6635f0360e434f45577d013468b6c

Wan 2.7 Image Pro image SHA 256: 4e860e01ecb53ed47d9a3ad2be57e9f2567e8dc010e44780615f71e30713f648

The numbers at a glance

Arena ratingfrom votes by users · higher is better
n/a

HunyuanImage 3.0 Instruct

not in the arena

n/a

Wan 2.7 Image Pro

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better
64

HunyuanImage 3.0 Instruct

Rank 18 of 74

73

Wan 2.7 Image Pro

Rank 8 of 74

Price per imagedollars through the API · lower is better
n/a

HunyuanImage 3.0 Instruct

no API price

n/a

Wan 2.7 Image Pro

no API price

Ranks among the 22 image models with an arena rating and the 74 with a GraduallyBench run; prices compared with 28 models with an API price.

HunyuanImage 3.0 Instruct

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known. Access: API, local.
License
Open weights.

Wan 2.7 Image Pro

Subscription
At Alibaba from ≈ €6.39 a month (Token Plan Individual Lite, with limited credits). 7 plans in Germany.
Via API
No API price known. Access: API.
Weights
unknown.

Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.

GraduallyBench from Nov 1, 2026 · Subscription database from Sep 29, 2026 (34 days old)

All data side by side

The better value is bold. For ratings only when the gap is clear.

KennzahlHunyuanImage 3.0 InstructWan 2.7 Image Pro
Ratings
Arena ratingfrom votes by users, higher is bettern/an/a
Arena rankn/an/a
Arena votesmore votes, a safer ratingn/an/a
GraduallyBenchour own rating, 0 to 1006473
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition8282
Product photographyMaterials, reflections, and fine details8080
Character and detailAnatomy, clothing, and spatial consistency4368
InfographicNumbers, labels, and visual organization5162
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
ReleasedJanuary 2026n/a
Weightsopen means: runs locallyopenunknown
AccessAPI, localAPI
Parameters80 billionnot published
Largest outputnot consistently published4K
Plans in Germanynaming exactly this modeln/a7

API prices for one image at 1,024 × 1,024 pixels according to Artificial Analysis.

Sources: HunyuanImage 3.0 Instruct model source (verified Aug 15, 2026) · Wan 2.7 Image Pro model source (verified Nov 1, 2026)

Arena ratings by category

From blind votes on LMArena. “Ahead” means the lead is clear.

No shared arena score in the stored snapshot

The stored benchmark database contains no measurement for HunyuanImage 3.0 Instruct and Wan 2.7 Image Pro from the same arena and category. Older model versions are not used as substitutes.

Compare another matchup