WAN 2.1 T2V 720P offers text-to-video 720p generation from prompts, enabling unlimited AI video creation for social and marketing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.3per run·~33 / $10
ExamplesView all
A rugged male secret agent in a torn tactical suit sprints through a war-torn urban alley, pistol in one hand, a bleeding gash on his brow. His eyes are sharp and calculating, sweat glistening on his tense face. Explosions light up the background as he dives into cover in slow motion
一位穿着时髦的年轻美女，站在客厅，背景虚化，惊讶的捂住嘴
Theme: A Dramatic underwater scene of a hot woman trapped inside a van after it crashed into the water, breathing and bubbles fantasy. Main Subject: a close up side face view of a Japanese woman (young, hot, perfect in every possible way) wearing scuba goggles, a string bikini top, and distressed denim short-shorts that reveals her toned legs, trapped underwater inside a van. She takes a breath from a scuba tank that is resting on the seat next to her, moaning with relief after nearly drowning. Focus on the subtle shape and movement of her lips and cheeks as she breathes from the scuba tanks regulator in her mouth, subtly leaning towards the camera to show off her body and lips. Special emphasis is on the shape, movement, and size of the bubbles she exhales as they rise upwards in a realistic way, visually indicating her breath and dependency on the scuba tank for air. Blue-Green underwater lighting. The entire focus of the image is ensuring the visual accuracy and detail of her breathing and exhaling bubbles from the scuba regulator underwater, ensuring she looks hot doing so, secondary focus is in ensuring a realistic underwater environment. Highly detailed and realistic film grab with added focus on underwater physics.
A graceful white swan gliding effortlessly across a calm, reflective pond. Its long neck curves elegantly, and lily pads dot the water's surface, creating a tranquil scene in soft morning light.
A lone astronaut floats gracefully through a nebular cloud in deep space, starlight shimmering on their visor. Slow, cinematic zoom out. Dreamy, ethereal lighting. UHD, 8K, highly detailed.
A young woman sits by a window on a rainy day, holding a warm mug. Her gaze is distant, reflecting a quiet contemplation. Soft, diffused natural light. Cozy, melancholic atmosphere. Shot from a slightly high angle.
A humanoid robot carefully tending to glowing bioluminescent plants in a controlled, sterile lab environment. Its movements are precise and fluid. Clean, minimalist design, soft blue and green lighting.
A fantastical creature, half-dragon, half-butterfly, gracefully soaring through a sky filled with floating islands, inspired by Studio Ghibli's art style. Hand-painted textures, dreamlike atmosphere.
An elderly couple sits on a park bench, holding hands and watching children play. Sunlight filters through autumn leaves, creating warm highlights. Their faces show contentment and a shared lifetime of memories. Gentle, static shot, warm tones.
A cute, fluffy corgi puppy playfully chasing its own tail on a sunny meadow, rendered in a charming stop-motion animation style. Warm, inviting colors, slightly jerky but adorable movement.
Related Models
README
Wan 2.1 Text-to-Video 720p
Create cinematic-quality videos from text descriptions with Wan 2.1 Text-to-Video 720p. This powerful model transforms your written prompts into stunning 720p HD videos with smooth motion, rich detail, and professional visual quality — no source footage required.
Why It Stands Out
- Pure text-to-video generation: Describe any scene, character, or action and watch it come to life in HD.
- Cinematic quality: 720p resolution delivers sharp, detailed visuals suitable for professional use.
- Prompt Enhancer: Built-in AI-powered prompt optimization helps you craft better descriptions for improved results.
- Negative prompt support: Exclude unwanted elements for cleaner, more controlled outputs.
- Flexible duration: Generate 5-second or 10-second clips depending on your needs.
- Reproducibility: Use the seed parameter to recreate exact results or iterate on variations.
Pricing
| Duration | Price |
|---|---|
| 5 seconds | $0.30 |
| 10 seconds | $0.45 |
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video you want to generate. |
| negative_prompt | No | Elements to avoid in the generated video. |
| size | No | Output resolution (default: 1280×720). |
| num_inference_steps | No | Quality/speed trade-off (default: 30). |
| duration | No | Video length in seconds: 5 or 10 (default: 5). |
| guidance_scale | No | Prompt adherence strength (default: 5). |
| flow_shift | No | Motion intensity control (default: 5). |
| seed | No | Set for reproducibility; -1 for random. |
How to Use
- Write a prompt describing the scene, action, and style you want. Use the Prompt Enhancer for AI-assisted optimization.
- Set parameters — adjust size, duration, guidance scale, and other settings as needed.
- Add a negative prompt (optional) to exclude unwanted elements.
- Click Run and wait for your video to generate.
- Preview and download the result.
Best Use Cases
- Social Media Content — Create high-quality video content for YouTube, Instagram, and TikTok.
- Marketing & Advertising — Produce concept videos, ad creatives, and promotional clips without filming.
- Storytelling & Animation — Generate scenes for short films, music videos, or narrative projects.
- Game & App Trailers — Create cinematic trailers and gameplay concepts from descriptions.
- Creative Exploration — Bring any imaginable scene to life for art projects and experimentation.
Pro Tips for Best Quality
- Be detailed in your prompt — describe subject appearance, action, environment, lighting, mood, and camera movement.
- Use negative prompts to reduce common artifacts: blur, distortion, jitter, watermarks, or low quality.
- Start with lower inference steps for quick previews, then increase for final renders.
- Fix the seed when iterating to compare the effect of different parameters.
- For complex scenes, break down the description into clear visual elements.
Notes
- Processing time varies based on duration and current queue load.
- Please ensure your prompts comply with content guidelines.
Wan 2.1 T2v 720p API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/t2v-720p with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Wan 2.1 T2v 720p below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/t2v-720p" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "1280*720",
"num_inference_steps": 30,
"duration": 5,
"guidance_scale": 5,
"flow_shift": 5,
"seed": -1
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/wan-2.1/t2v-720p", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "1280*720",
"num_inference_steps": 30,
"duration": 5,
"guidance_scale": 5,
"flow_shift": 5,
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/wan-2.1/t2v-720p",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "1280*720",
"num_inference_steps": 30,
"duration": 5,
"guidance_scale": 5,
"flow_shift": 5,
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.1 T2v 720p API — Frequently asked questions
What is the Wan 2.1 T2v 720p API?
Wan 2.1 T2v 720p is a WaveSpeedAI model for video generation, exposed as a REST API on WaveSpeedAI. WAN 2.1 T2V 720P offers text-to-video 720p generation from prompts, enabling unlimited AI video creation for social and marketing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Wan 2.1 T2v 720p API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.1-t2v-720p.
How much does Wan 2.1 T2v 720p cost per run?
Wan 2.1 T2v 720p starts at $0.30 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Wan 2.1 T2v 720p accept?
Key inputs: `prompt`, `duration`, `size`, `seed`, `guidance_scale`, `num_inference_steps`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.1-t2v-720p.
How long does Wan 2.1 T2v 720p take to generate?
Average end-to-end generation time on WaveSpeedAI is around 85 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Wan 2.1 T2v 720p outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.