Alibaba Wan 2.6 Text To Video

Alibaba Wan 2.6 Text To Video

Playground

Alibaba WAN 2.6 Text-to-Video turns plain prompts into coherent, cinematic clips with crisp detail, stable motion, and strong instruction-following—great for ads, explainers, and social posts. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Alibaba / WAN 2.6 — Text-to-Video (wan2.6-t2v)

WAN 2.6 Text-to-Video is Alibaba’s WanXiang 2.6 model that turns a pure text prompt (optionally with audio) into a 5–15s cinematic clip. It supports multi-shot storytelling, vertical or landscape formats, and resolutions up to 1080p, making it a strong fit for ads, trailers, and social content.

🚀 Highlights

• Prompt-only video generation – No reference image required: describe the scene and WAN 2.6 builds the entire sequence.
• Multi-shot narratives – With prompt expansion and multishots enabled, the model can split your idea into several shots while preserving key characters and style.
• 5–15 second clips – Enough room for intros, reveals, and full micro-stories.
• Flexible sizes – Horizontal and vertical presets across ** 720p / 1080p** tiers.
• Prompt-aware consistency – Keeps identities, outfits, and scene semantics coherent across the whole clip.

🧩 Parameters

• prompt* – Main description of the video: scene, characters, motion, camera moves, style.

• negative_prompt – Things to avoid (e.g. watermark, text, distortion, extra limbs).

• audio (optional) – URL or file of an audio track; reserved for advanced workflows where you want to align motion with existing sound.

• size – Resolution presets:

  • 720p tier

    • 1280×720 (landscape)
    • 720×1280 (vertical)

  • 1080p tier

    • 1920×1080 (landscape)
    • 1080×1920 (vertical)

• duration – One of 5s, 10s, 15s.

• shot_type –

  • single → single continuous shot.
  • multi → when combined with enable_prompt_expansion, lets the model create a multi-shot sequence.

• enable_prompt_expansion – If enabled, WAN 2.6 first expands your prompt into an internal, more detailed script before generating.

• seed – Random seed; set to -1 for different results each time or use a fixed integer for reproducible motion/layout.

Output: an MP4 video at the chosen resolution and orientation.

💰 Pricing

Pricing depends on duration and resolution tier:

✅ How to Use

1. Write your prompt – Describe what happens, who appears, how the camera moves, and the visual style.
2. (Optional) Add a negative_prompt to suppress artifacts or unwanted elements.
3. (Optional) Provide an audio track if your workflow requires it.
4. Choose a size (one of the 720p / 1080p presets, landscape or vertical).
5. Set duration to 5 / 10 / 15 seconds.
6. Enable prompt_expansion and multishots if you want richer, multi-shot storytelling.
7. Set a seed (or leave -1 for variation) and click Run to generate your clip.

💡 Prompt Tips

• Start with a clear setting + subject + action: “Cyberpunk city street at night, rain on the ground, a lone biker rides through neon fog, cinematic camera tracking shot.”
• For multi-shot stories, hint at structure: “Shot 1: wide city skyline at dawn; Shot 2: hero walks across rooftop; Shot 3: close-up as they put on helmet.”
• Keep negative prompts short and focused (e.g. blurry, watermark, extra limbs) instead of full sentences.
• Match size to platform: vertical (720×1280 / 1080×1920) for Shorts/Reels/TikTok, landscape for YouTube and web.

More Models to Try

• kwaivgi/kling-video-o1/text-to-video Kwaivgi’s cinematic text-to-video model, great for character-driven scenes, smooth camera moves, and short-form storytelling.

• alibaba/wan-2.5/text-to-video Alibaba’s WAN 2.5 prompt-to-video engine, focused on fast, coherent ads, explainers, and product demos.

• google/veo3.1/text-to-video Google Veo 3.1 text-to-video, tuned for crisp compositions, filmic motion, and marketing-ready visuals.

• openai/sora-2/text-to-video OpenAI Sora 2, a high-end text-to-video generator for long, detailed, physics-aware scenes and premium creative content.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/text-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1280*720",
    "duration": 5,
    "shot_type": "single",
    "enable_prompt_expansion": false,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"