Alibaba Wan 2.6 Spicy — Image-to-Video
Wan 2.6 Spicy converts images into unlimited high-quality videos with smooth, cinematic motion. It transforms static images into dynamic 720p and 1080p clips with expressive motion, rich color, and natural transitions — perfect for creative storytelling and scalable content generation.
Why It Works Well
-
Unlimited-style generation
Optimized for high-quality, smooth animations at scale.
-
Expressive motion
Bold, vivid motion and rich tonal contrast with stable temporal coherence.
-
Flexible resolution
720p or 1080p to match your needs.
-
Duration options
5s, 10s, or 15s clips.
Parameters
| Parameter | Required | Description |
|---|
| image | Yes | The keyframe or base image to animate (URL or upload) |
| prompt | Yes | Describe the motion, story, and style |
| resolution | No | 720p (default) or 1080p |
| duration | No | 5, 10, or 15 seconds (default: 5) |
| shot_type | No | single (default) or multi |
| negative_prompt | No | Elements to avoid |
| enable_prompt_expansion | No | Enable prompt expansion (default: false) |
| seed | No | Random seed; -1 for random |
How to Use
- Upload your image — ensure clarity and proper framing.
- Enter a prompt — describe desired motion, mood, or camera movement.
- Select resolution and duration — choose based on your needs.
- Set a seed (optional) — for consistent, reproducible results.
- Run — click the button to generate your video.
Pricing
| Duration | 720p | 1080p |
|---|
| 5 s | $0.50 | $0.75 |
| 10 s | $1.00 | $1.50 |
| 15 s | $1.50 | $2.25 |
Billing Rules
- 720p rate: $0.50 per 5 seconds
- 1080p rate: $0.75 per 5 seconds (1.5× multiplier)
Best Use Cases
- Creative Storytelling — Transform static images into dynamic narrative clips.
- Social Media Content — Generate eye-catching videos for TikTok, Reels, and Stories.
- Music Videos — Create visually expressive content with bold motion.
- Marketing & Ads — Produce scalable video content from product images.
- Artistic Projects — Experimental and avant-garde video generation.
Pro Tips
- Works best with clear, well-lit images with proper framing.
- Use detailed prompts describing motion, mood, and camera movement for best results.
- Enable prompt expansion for automatically enhanced descriptions.
- Use negative_prompt to exclude unwanted elements or styles.
- Same API shape as Wan 2.6 Image-to-Video for easy integration.
Notes
- Both image and prompt are required fields.
- Ensure uploaded image URLs are publicly accessible.
- 1080p resolution costs 1.5× the 720p rate.
Related Models
- Wan 2.6 Image-to-Video Pro — Pro tier with 4K support.
- Wan 2.6 Image-to-Video — Standard image-to-video.
- Wan 2.6 Text-to-Video — Generate videos from text prompts.