Wan-t2v
Generate videos directly from text descriptions
Wan-t2v (Text-to-Video) generates complete videos from text descriptions without requiring input images. It supports 480p and 720p resolutions with both 16:9 and 9:16 aspect ratios, making it versatile for different content types from landscape cinematics to vertical social media content.
Rate Limit: 30 requests per minute
Category: Text-to-Video
Pricing:
| Resolution | Price |
|---|---|
| 480p | $0.05 / video |
| 720p | $0.10 / video |
Quickstart
Section titled “Quickstart”Start with uploading an image
Section titled “Start with uploading an image”curl -X POST "https://api.pruna.ai/v1/files" \ -H "apikey: YOUR_API_KEY" \ -F "content=@/path/to/your/file.jpg"Note: Use -F (form) with @ prefix to upload a file from your local filesystem. The file path should be absolute or relative to your current directory.
Response:
{ "id": "fqadqq42xq", "name": "test.jpg", "content_type": "image/jpeg", "size": 185093, "etag": "\"14e9a51deaac6bee2dd8b5c52d7d0b5f\"", "checksums": { "sha256": "aa10d5d09bcee5cb5d854bd81899308b0cf0c0c50e29d4f00c2c06e51f0e2fe6" }, "metadata": { "content_length": 185093, "width": 1344, "height": 768 }, "created_at": "2025-01-08T18:51:26.729Z", "expires_at": "2025-01-09T18:51:26.729Z", "urls": { "get": "https://api.pruna.ai/v1/files/fqadqq42xq" }}curl -X POST 'https://api.pruna.ai/v1/predictions' \ -H 'Content-Type: application/json' \ -H 'apikey: YOUR_API_KEY' \ -H 'Model: wan-t2v' \ -d '{ "input": { "prompt": "A sports car is driving very fast along a beach at sunset, aerial drone shot, cinematic", "num_frames": 81, "resolution": "720p", "aspect_ratio": "16:9", "frames_per_second": 16 } }'Parameters
Section titled “Parameters”Required Parameters
Section titled “Required Parameters”| Parameter | Type | Description |
|---|---|---|
| prompt | string | Detailed description of the video scene, action, camera movement, and style |
Video Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
| num_frames | integer | 81 | Number of video frames (81-121). 81 frames give the best results |
| resolution | string | "480p" | Video resolution: "480p" or "720p" |
| aspect_ratio | string | "16:9" | Aspect ratio: "16:9" (landscape, 832x480px or 1280x720px) or "9:16" (vertical, 480x832px) |
| frames_per_second | integer | 16 | Frame rate (5-30 fps). Pricing is based on 16 fps duration |
| interpolate_output | boolean | true | Enable frame interpolation for smoother motion (30 FPS) |
| go_fast | boolean | true | Enable fast processing mode |
Advanced Parameters
Section titled “Advanced Parameters”| Parameter | Type | Default | Description |
|---|---|---|---|
| optimize_prompt | boolean | false | Translate prompt to Chinese before generation (may improve results) |
| sample_shift | number | 12.0 | Sample shift factor (1.0-20.0) |
| lora_scale_transformer | number | 1.0 | LoRA scale for transformer |
| lora_scale_transformer_2 | number | 1.0 | LoRA scale for transformer_2 |
| lora_weights_transformer | string (URI) | - | Custom LoRA weights URL (.safetensors) |
| lora_weights_transformer_2 | string (URI) | - | Second custom LoRA weights URL |
| seed | integer | random | Random seed for reproducibility |
| disable_safety_checker | boolean | false | Disable safety checker |