Create AI videos with seed for reproducibility and negative prompts. Supports portrait and square formats.
Specify a seed for identical results. Perfect for iterations and A/B testing
Exclude unwanted elements: blur, artifacts, watermarks and other defects
Create videos for any platform: YouTube, TikTok, Instagram and more
Create videos from text descriptions with synchronized audio and dialogue
Bring a static image to life while preserving style, characters and composition
| Parameter | WAN 2.5 | WAN 2.6 |
|---|---|---|
| Seed (reproducibility) | — | |
| Negative prompt | — | |
| Aspect ratios | 16:9, 9:16, 1:1 | 16:9 only |
| Auto-extend prompt | — | |
| Video length | 5, 10s | 5, 10, 15s |
| Prompt limit | 800 chars | No limit |
| Video-to-Video | — | |
| Multi-Shots mode | — | |
| Price (min) | ··· | ··· |
WAN 2.5 has a strict limit — maximum 800 characters per prompt. Our service automatically compresses prompts during translation, but writing concisely from the start is better.
[Scene/Place] + [Subject] + [Action] + [Camera] + [Atmosphere]Example:
"City at night, neon signs. A girl in a leather jacket walks on wet asphalt. Medium shot, slow camera pull-back. Rain, reflections in puddles."
By default we use an optimized negative prompt, but you can change it:
blurry, low quality, distorted, watermark, text overlay, logo, grainy, pixelated, overexposed, underexposed, bad anatomy, deformed, ugly, artifacts, glitch, noise
WAN 2.5 supports lip-sync and audio synchronization. Write dialogue in quotation marks:
"A woman looks at the camera and says: 'Hi! I'm so glad to see you!' She smiles and waves. Warm light, blurred background."
💡 Dialogue in quotation marks is preserved as-is even after translation
| Parameters | 720p | 1080p |
|---|---|---|
| 5 seconds | ··· | ··· |
| 10 seconds | ··· | ··· |
💡 WAN 2.5 is cheaper than WAN 2.6 at the same parameters
WAN 2.5 supports seed for reproducible results, negative prompts to exclude unwanted elements, and three aspect ratios (16:9, 9:16, 1:1). However, WAN 2.5 has an 800-character prompt limit and does not support video-to-video mode or 15-second videos.
Seed is a number that determines generation randomness. With the same seed and the same prompt, you'll get an identical result. Useful for iteration: change the prompt while keeping the generation style.
A negative prompt describes what should NOT be in the video. For example: 'blurry, low quality, watermarks'. It helps avoid typical AI generation artifacts.
It's a technical limit of the WAN 2.5 API. Our service automatically compresses prompts during translation while preserving the meaning. You can also enable 'Auto-extend' — the API will then fill in a short prompt on its own.
WAN 2.5 supports three formats: 16:9 (landscape, for YouTube), 9:16 (portrait, for TikTok/Reels), and 1:1 (square, for Instagram). Unlike WAN 2.6, which only works with 16:9.
When this option is enabled, the API uses a built-in language model to automatically expand your short prompt. Especially useful given the 800-character limit.
Generation typically takes 3 to 8 minutes depending on duration, resolution, and server load. A 5-second video at 720p generates fastest.
Yes! WAN 2.5 generates video with native synchronized audio. The model understands scene context and adds matching audio, including dialogue and ambient sounds.
Create AI videos with precise generation control. Seed for reproducibility, negative prompts, and three video formats.
Start generating