Images · Alibaba (Wan)
Wan 2.7 Image
Alibaba Wan's image models with a thinking mode for complex scenes. Use the standard one for drafts, Pro for final product shots.
Anonymized Low costWhat sets it apart
Alibaba Wan's image models with a thinking mode for complex scenes, suited to product and advertising imagery. Use the standard one for drafts and Pro for final shots.
- Thinking mode for complex scenes
- Product and advertising imagery
- Standard for drafts, Pro for final shots
Strengths and limits
Where it shines
- Handles multi-subject scenes and embedded text
- Suited to product and advertising imagery
Think twice when
- Anonymized, not private: Alibaba Cloud's policy applies
- Pro costs more than twice the standard model
- Prompts up to 3,000 characters
- About 1.9 credits (standard)
Use cases
An ad visual
A perfume bottle on a mirror surface with rose petals, a slogan in elegant script, soft pink backdrop, advertising photo.
It suits product and advertising imagery.
A multi-subject scene
A family of four cooking together in a bright kitchen, a banner on the wall reading 'Sunday Brunch'.
It handles multiple subjects and embedded text.
Against its rivals
- Luma Uni-1Luma reasons about layout; Wan has a thinking mode and favors product imagery.#22 of 37 on Artificial Analysis Text to Image Arena (1,014 Elo)
- SeedreamSeedream ranks higher and keeps subjects consistent across a series.#12 of 37 on Artificial Analysis Text to Image Arena (1,081 Elo)
- Qwen ImageQwen Image 3 ranks higher on text-heavy layouts.#11 of 37 on Artificial Analysis Text to Image Arena (1,090 Elo)
Version history
Each version, dated, with what it changed over the one before.
Hollow points are earlier versions no longer offered in Sub Rosa.
See the numbers
| Version | Released | Elo |
|---|---|---|
| Wan 2.6 Image | 2025-12 | 1,026 |
| Wan 2.7 and 2.7 Pro | 2026-04 | 990 |
- Wan 2.6 ImageEarlier, not in Sub Rosa
- Previous generation, scoring 1026 on the arena
- Wan 2.7 and 2.7 ProLatest
- Seventh generation, standard and Pro tiers, both between 983 and 990 on the arena
Benchmarks
How to read these scores: what a benchmark tells you.
Artificial Analysis Text to Image Arena: #29 of 37 models measured in the catalog. Thousands of people compare two images made from the same prompt without knowing the models, and pick the better one. An Elo rating, as in chess: higher is preferred more often. 100 points apart means the higher one wins about 64% of duels.
- 1. GPT Image 2.5 SunburstGPT Image1,197
- 2. GPT Image 2.5 FlareGPT Image1,191
- 3. GPT Image 2GPT Image1,172
- 4. Nano Banana 2.1Nano Banana1,172
- 5. Grok Imagine 2.0Grok Imagine1,155
- 6. Nano Banana 2Nano Banana1,125
- 7. Muse ImageMuse Image1,115
- 8. GPT Image 1.5GPT Image1,107
- 9. Nano Banana ProNano Banana1,102
- 10. Nano Banana 2 LiteNano Banana1,096
- 29. Wan 2.7Wan 2.7 Image990
- 32. Wan 2.7 ProWan 2.7 Image983
See the numbers
| Model | Elo |
|---|---|
| 1. GPT Image 2.5 Sunburst | 1,197 |
| 2. GPT Image 2.5 Flare | 1,191 |
| 3. GPT Image 2 | 1,172 |
| 4. Nano Banana 2.1 | 1,172 |
| 5. Grok Imagine 2.0 | 1,155 |
| 6. Nano Banana 2 | 1,125 |
| 7. Muse Image | 1,115 |
| 8. GPT Image 1.5 | 1,107 |
| 9. Nano Banana Pro | 1,102 |
| 10. Nano Banana 2 Lite | 1,096 |
| 29. Wan 2.7 | 990 |
| 32. Wan 2.7 Pro | 983 |
All 2 models in this family
| Model | Use | Privacy | Price |
|---|---|---|---|
Wan 2.7wan-2-7-text-to-image | Image | Anonymized | $0.0169 per image |
Wan 2.7 Prowan-2-7-pro-text-to-image | Image | Anonymized | $0.0422 per image |
Specifications
| Specification | Wan 2.7 Pro | Wan 2.7 |
|---|---|---|
| Released | April 2026 | April 2026 |
| Accepts | text | text |
| Produces | images | images |
| Price | $0.0422 per image | $0.0169 per image |
| Privacy | Anonymized | Anonymized |
Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.
Sources
Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.