Wan-2.6 Text-to-video by QWEN
alibaba/wan-2.6/text-to-videoA speed-optimized text-to-video option that prioritizes lower latency while retaining strong visual fidelity. Ideal for iteration, batch generation, and prompt testing.
Set up the model and run your first generation.
Ctrl ⏎Examples
Runs published with this model. Load one into the playground and change whatever you like.
A cinematic sci-fi trailer. Shot 1: Wide shot, a lonely explorer in a battered spacesuit walking across a desolate red Martian desert, a massive derelict spaceship in the distance. Shot 2: Close-up, the explorer stops and wipes dust off their helmet visor, eyes widening in shock. Shot 3: Over-the-shoulder shot, revealing a glowing, bioluminescent blue flower blooming rapidly in front of them. 8k resolution, highly detailed, consistent character.
seed: -1size: 1920*1080duration: 15shot_type: multienable_prompt_expansion: true
A 15-second fixed-camera time-lapse video. An ancient oak tree stands alone on a grassy hill. The video transitions smoothly through four seasons: starting with lush green leaves in Spring, turning golden yellow in Autumn, and finally, the branches becoming bare and covered in heavy snow in Winter. Clouds move rapidly across the sky, changing lighting conditions, photorealistic, seamless transitions.
seed: -1size: 1920*1080duration: 15shot_type: multienable_prompt_expansion: true
Dimly lit old-style cha chaan teng corner, "Huinantian" humid air heavy, cinematic medium shot, Asian man B, 30-35 years old, lean build, immaculately parted short hair, slightly flattened by humidity. He has a sculpted square face, tight jawline, deep and slightly weary eyes gazing forward, brows subtly furrowed, forehead and cheeks subtly glistening with moisture, thin, strong lips, faint stubble. He wears a well-tailored dark grey suit jacket, tie slightly loosened, suit fabric subtly reflecting a wet sheen. A half-burnt cigarette in his hand, smoke suppressed by humidity, a few butts in the ashtray. An almost untouched coffee in front, faint steam rising, seemingly subdued by humidity. Background features heavily blurred silhouettes of diners, smoke swirling, visible moisture on walls. Warm yellow tones, high contrast lighting, film grain, Wong Kar-wai style --ar 16:9
seed: -1size: 1920*1080duration: 15shot_type: multienable_prompt_expansion: false
Providers
Where this model can run, priced for your account. Auto routing picks the top row and moves down it if a provider fails.
| Provider | Price | Speed | Completed |
|---|---|---|---|
| Atlas CloudLowest price | $0.070 /sec | — | — |
| fal.ai | $0.100 /sec | — | — |
| Replicate | $0.100–$0.150 /sec | — | — |
| OpenRouter | — | — | — |
Speed and reliability appear once this platform has enough recent runs on a provider.
Wan-2.6 Image-to-video Flash$0.090Wan-2.6 Image-to-image$0.021Wan-2.6 Image-to-video$0.350Wan-2.6 Video-to-video$0.350Wan-2.6 Text-to-image$0.021
Questions
- $0.350 per generation on ElliSekiz — the provider's own price, billed 1:1 from a prepaid USD balance with no markup and no subscription. Failed generations are free.
- Atlas Cloud, fal.ai, Replicate, OpenRouter. Requests route to the cheapest available provider automatically, or you can pin one per request or per model.
- POST to https://ellisekiz.ai/api/v1/generations with "model": "alibaba-wan-2.6-text-to-video" and your prompt, authenticated with an ElliSekiz API token. The API tab on this page has the full request for this model, including its own parameters.
- audio, duration, enable_prompt_expansion, negative_prompt, seed, size, shot_type, generate_audio — each one is in the playground form on this page and in the API example.
$0.350 per generation (≈5s clip) · billed 1:1 at provider cost · compare providers