Direct multi-shot narratives
Describe your clip shot by shot — "Shot 1 [0-3s] wide angle … Shot 2 [3-6s] close-up …" — and Wan 2.7 executes the storyboard in one coherent take, up to 15 seconds. It is built for sequences, not just single moves.
AI video model
Wan 2.7 AI Video Generator
Direct shot-by-shot scenes up to 15 seconds with Wan 2.7: lock character identity with up to 5 reference images and get native audio at a budget-friendly rate.
Multi-shot videoIdentity lockBudget friendly
Explore More Models
Compare Wan 2.7 with other video models — same workspace, one click to switch.
Get Inspired
A glimpse of what people are creating with AI video models on CreateVision AI.
Wan 2.7 — multi-shot stories with locked character identity
Alibaba's Tongyi Wanxiang 2.7 turns shot-by-shot prompts into coherent scenes up to 15 seconds, keeps characters consistent from reference images, and generates native audio — at one of the friendliest per-second rates in its class.
Reference identity lock
Reference-to-video accepts up to five images — characters, products, or scenes — referenced in order as Image 1, Image 2 and so on. Faces, outfits, and objects stay consistent across camera moves instead of drifting between frames.
Budget-friendly per-second billing
Wan 2.7 undercuts most models of its quality tier on cost per second, making it the right pick for drafts you want at final-worthy quality — and long 10-15 second cuts that would be expensive elsewhere. The exact cost shows before you generate.
Native audio and flexible framing
Audio is generated automatically to match the visuals — music, ambience, and effects with no extra step. Output at 720p or 1080p in five aspect ratios, from vertical 9:16 social clips to classic 16:9.
Keep exploring CreateVision AI
One account, the full image and video generation workflow.
Choose Your Plan
Start free with daily credits. Upgrade for premium models, faster generation, and 4K output.
Free
$0
Perfect for getting started
- 80 credits per day, 400 per month
- Z Image Turbo drafts at 0 credits
- Standard generation speed
- Generation history included
Premium
Most popular$29/month
Billed annually · $240/year
- 1,600 credits/day, 8,000 credits/month
- All premium models — GPT Image 2, Nano Banana, Seedream, Seedance, Veo, Kling
- 5x generation speed, priority queue
- AI prompt enhancement
Ultimate
$49/month
Billed annually · $300/year
- 4,000 credits/day, 18,000 credits/month
- HD generation up to 4K resolution
- Private generation — results stay out of the gallery
- Fastest queue and early access to new models
Frequently Asked Questions
1
What is Wan 2.7 best at?
Multi-shot storytelling with consistent characters: describe the clip shot by shot, attach up to five reference images, and get a coherent scene up to 15 seconds with native audio.
2
How is it priced?
Per second of output, varying with resolution (720p or 1080p). Wan 2.7 is one of the most cost-efficient models in its quality tier; the exact cost shows before generation, and failed runs refund automatically.
3
What modes does it support?
Text-to-video, image-to-video (animate a first frame), and reference-to-video with up to 5 reference images referenced as Image 1, Image 2 and so on.
4
How long can clips be?
2 to 15 seconds per generation — one of the longest ranges available — at 720p or 1080p.
5
How does it compare to HappyHorse 1.1?
Wan 2.7 is the control-and-value pick: longer clips, tighter identity lock, lower cost. HappyHorse 1.1 leads on native dialogue and multilingual lip-sync. Both generate audio natively.
6
What if the generation fails?
Credits are refunded automatically for failed video generations.
