Vidu Contest
WaveSpeed.ai
Accueil/Explorer/Wan 2.2 Models/wavespeed-ai/wan-2.2/t2v-720p-ultra-fast
text-to-video

text-to-video

Wan 2.2 T2V 720P Ultra-Fast

wavespeed-ai/wan-2.2/t2v-720p-ultra-fast

WAN 2.2 T2V 720p Ultra-Fast generates high-quality 720p videos from text prompts with unlimited output and ultra-fast throughput. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input

Idle

Votre requête coûtera $0.1 par exécution.

Pour $1 vous pouvez exécuter ce modèle environ 10 fois.

Encore une chose ::

ExemplesTout voir

README

Wan 2.2 Text-to-Video 720p Ultra Fast

Generate 720p HD videos from text at maximum speed with Wan 2.2 Ultra Fast. This streamlined model delivers high-quality output with the fastest turnaround — perfect for rapid prototyping, high-volume production, and quick creative exploration.

Need custom styles? Try Wan 2.2 T2V 720p LoRA Ultra Fast for LoRA support with fast processing.

Why It Looks Great

  • Maximum speed: The fastest 720p text-to-video option available.
  • Pure text-to-video: Generate complete videos from descriptions alone — no images needed.
  • 720p HD output: Sharp, professional-quality video at an unbeatable price.
  • Landscape & portrait: Supports both 1280×720 and 720×1280 orientations.
  • Negative prompt support: Exclude unwanted elements for precise control.
  • Prompt Enhancer: Built-in tool to refine your descriptions automatically.
  • Reproducible results: Use the seed parameter to recreate exact outputs.

Parameters

ParameterRequiredDescription
promptYesText description of the scene, action, and atmosphere you want.
negative_promptNoElements to avoid in the generated video.
sizeNoOutput dimensions: 1280×720 (landscape) or 720×1280 (portrait). Default: 1280×720.
durationNoVideo length: 5 or 8 seconds. Default: 5.
seedNoRandom seed for reproducibility. Use -1 for random.

How to Use

  1. Write your prompt — describe the scene, characters, motion, and atmosphere in detail.
  2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
  3. Add negative prompt (optional) — specify elements to exclude.
  4. Choose size — select landscape (1280×720) or portrait (720×1280) orientation.
  5. Set duration — choose 5 or 8 seconds.
  6. Set seed (optional) — for reproducible results.
  7. Run — click the button to generate.
  8. Download — preview and save your video.

Pricing

Per 5-second billing based on duration.

DurationCalculationCost
5 seconds5 ÷ 5 × $0.10$0.10
8 seconds8 ÷ 5 × $0.10$0.16

Size Options

SizeOrientationBest For
1280×720LandscapeYouTube, presentations, desktop viewing
720×1280PortraitTikTok, Instagram Reels, Stories, mobile

Best Use Cases

  • Rapid Prototyping — Test video concepts at lightning speed before committing to final production.
  • High-Volume Production — Generate large batches of content at the lowest cost.
  • Quick Previews — Create fast previews to validate ideas and prompts.
  • Social Media Content — Produce platform-optimized HD videos efficiently.
  • Creative Exploration — Experiment with different scenes and narratives affordably.

Example Prompts

  • "A cozy, sun-drenched library with towering bookshelves. A young woman with glasses sits in a comfortable armchair, a steaming mug of tea on a small table beside her. She is engrossed in a thick book, her expression one of quiet contentment. The camera slowly zooms in."
  • "Drone shot flying through autumn forest, golden leaves falling, morning mist, cinematic"
  • "Street food vendor cooking at night market, steam rising, warm lighting, bustling atmosphere"
  • "Abstract liquid metal morphing and flowing, reflective surfaces, mesmerizing motion"
  • "Puppy running through meadow of wildflowers, slow motion, golden hour, joyful energy"

Model Comparison

ModelCost (5s)SpeedFeatures
T2V 720p Ultra Fast$0.10FastestBasic T2V
T2V 720p LoRA Ultra Fast$0.15Fast+ LoRA support
T2V 720p$0.30StandardPremium quality

Pro Tips for Best Results

  • Ultra Fast is perfect for testing — iterate quickly, then use standard models for finals.
  • Include camera directions: "slowly zooms in", "tracking shot", "drone shot".
  • Describe atmosphere and mood: "cozy", "sun-drenched", "quiet contentment".
  • Match orientation to platform: portrait for TikTok/Reels, landscape for YouTube.
  • Use negative prompts to avoid "blur", "jitter", "distortion" for cleaner output.
  • At $0.10 per 5 seconds, you can afford to experiment freely.

Notes

  • Duration options are 5 or 8 seconds only.
  • This is the most affordable 720p text-to-video option.
  • For custom style control, consider LoRA-enabled variants.
  • Processing is optimized for maximum speed.