## Basic model info

Model name: wan-video/wan-2.2-t2v-fast
Model description: A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video


## Model inputs

- prompt (required): Prompt for video generation (string)
- optimize_prompt (optional): Translate prompt to Chinese before generation (boolean)
- num_frames (optional): Number of video frames. 81 frames give the best results (integer)
- aspect_ratio (optional): Aspect ratio of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px (string)
- resolution (optional): Resolution of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px (string)
- frames_per_second (optional): Frames per second. Note that the pricing of this model is based on the video duration at 16 fps (integer)
- interpolate_output (optional): Interpolate the generated video to 30 FPS using ffmpeg (boolean)
- go_fast (optional): Go fast (boolean)
- sample_shift (optional): Sample shift factor (number)
- seed (optional): Random seed. Leave blank for random (integer)
- disable_safety_checker (optional): Disable safety checker for generated video. (boolean)
- lora_weights_transformer (optional): Load LoRA weights for transformer. Supports arbitrary .safetensors URLs from the Internet (for example, 'https://huggingface.co/Viktor1717/scandinavian-interior-style1/resolve/main/my_first_flux_lora_v1.safetensors') (string)
- lora_scale_transformer (optional): Determines how strongly the transformer LoRA should be applied. (number)
- lora_weights_transformer_2 (optional): Load LoRA weights for transformer_2. Supports arbitrary .safetensors URLs from the Internet. Can be different from transformer LoRA. (string)
- lora_scale_transformer_2 (optional): Determines how strongly the transformer_2 LoRA should be applied. (number)


## Model output schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}

If the input or output schema includes a format of URI, it is referring to a file.


## Example inputs and outputs

Use these example outputs to better understand the types of inputs the model accepts, and the types of outputs the model returns:

### Example (https://replicate.com/p/2x92f8k6exrma0crbcq9heez10)

#### Input

```json
{
  "prompt": "A sports car is driving very fast along a beach at sunset",
  "go_fast": true,
  "num_frames": 81,
  "resolution": "480p",
  "aspect_ratio": "16:9",
  "sample_shift": 12,
  "frames_per_second": 16
}
```

#### Output

```json
"https://replicate.delivery/xezq/fLIizBaYWBWwBKFAL7JRKQsfmqSeHfI5fQH8RitXfQ7w65eiKA/output.mp4"
```


### Example (https://replicate.com/p/1qnz4xjzgdrmc0crbcv9jj1pew)

#### Input

```json
{
  "prompt": "A sports car is driving very fast along a beach at sunset",
  "go_fast": true,
  "num_frames": 81,
  "resolution": "480p",
  "aspect_ratio": "16:9",
  "sample_shift": 12,
  "frames_per_second": 16
}
```

#### Output

```json
"https://replicate.delivery/xezq/PNTe7b9VBLxFPKB35GDhzrMYaph7WKspkexwtxeRPxJqfuXUB/output.mp4"
```


### Example (https://replicate.com/p/p5sbxvz1z1rma0cse6za0gey98)

#### Input

```json
{
  "prompt": "A sports car is driving very fast along a beach at sunset",
  "go_fast": true,
  "num_frames": 81,
  "resolution": "480p",
  "aspect_ratio": "16:9",
  "sample_shift": 12,
  "optimize_prompt": false,
  "frames_per_second": 16,
  "lora_scale_transformer": 1,
  "lora_scale_transformer_2": 1
}
```

#### Output

```json
"https://replicate.delivery/xezq/j71Ii2YrWfRpGilHFUkqMSPhrV9rPu0ee4EiSV1H7CD3PhvqA/output_30fps.mp4"
```


## Model readme

> # About Pruna AI
> 
> ## Efficient Inference with Pruna AI
> 
> At Pruna AI, we specialize in making AI models faster, smaller, cheaper, and greener. Our highly-optimized inference endpoints deliver superior video, image, and text generation efficiency. Powered by state-of-the-art compression algorithms from the [Pruna package](https://github.com/PrunaAI/pruna), we help companies deploy AI models with maximum performance and minimal resource usage.
> 
> ## Want to make your AI model more efficient?
> 
> - [Contact us](https://www.pruna.ai/contact) to get started with optimizing your AI models.
> - Compress your own models with the [Pruna package](https://github.com/PrunaAI/pruna).
> - Learn about our AI research in our [blogs](https://www.pruna.ai/blog), [materials](https://github.com/PrunaAI/awesome-ai-efficiency), and [courses](https://github.com/PrunaAI/courses).