← All models
Wan 2.2 T2v Fast
Fast Wan 2.2 text to video with 480p. Ultra-fast open source text to video model. Video model under 30 second output.
Example
Details
- Accepts
- text
Pricing
- Price
- 0.208 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed. Leave blank for random |
| promptrequired | string | Prompt for video generation |
| go_fast | boolean | Go fast |
| num_frames | integer | Number of video frames. 81 frames give the best results |
| resolution | stringenum: 480p, 720p | |
| aspect_ratio | —enum: 16:9, 9:16 | Aspect ratio of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px |
| sample_shift | number | Sample shift factor |
| optimize_prompt | boolean | Translate prompt to Chinese before generation |
| frames_per_second | integer | Frames per second. Note that the pricing of this model is based on the video duration at 16 fps |
| interpolate_output | boolean | Interpolate the generated video to 30 FPS using ffmpeg |
| disable_safety_checker | boolean | Disable safety checker for generated video. |
| lora_scale_transformer | number | Determines how strongly the transformer LoRA should be applied. |
| lora_scale_transformer_2 | number | Determines how strongly the transformer_2 LoRA should be applied. |
| lora_weights_transformer | string | |
| lora_weights_transformer_2 | string | Load LoRA weights for transformer_2. Supports arbitrary .safetensors URLs from the Internet. Can be different from transformer LoRA. |