# CogVideoX-5B

> Generate videos from prompts using CogVideoX-5B


## Overview

- **Endpoint**: `https://fal.run/fal-ai/cogvideox-5b`
- **Model ID**: `fal-ai/cogvideox-5b`
- **Category**: text-to-video
- **Kind**: inference


## Pricing

- **Price**: $0.2 per videos

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`prompt`** (`string`, _required_):
  The prompt to generate the video from.
  - Examples: "A garden comes to life as a kaleidoscope of butterflies flutters amidst the blossoms, their delicate wings casting shadows on the petals below. In the background, a grand fountain cascades water with a gentle splendor, its rhythmic sound providing a soothing backdrop. Beneath the cool shade of a mature tree, a solitary wooden chair invites solitude and reflection, its smooth surface worn by the touch of countless visitors seeking a moment of tranquility in nature's embrace."

- **`video_size`** (`ImageSize | Enum`, _optional_):
  The size of the generated video.
  - Default: `{"width":720,"height":480}`
  - One of: ImageSize | Enum

- **`negative_prompt`** (`string`, _optional_):
  The negative prompt to generate video from Default value: `""`
  - Default: `""`
  - Examples: "Distorted, discontinuous, Ugly, blurry, low resolution, motionless, static, disfigured, disconnected limbs, Ugly faces, incomplete arms"

- **`loras`** (`list<LoraWeight>`, _optional_):
  The LoRAs to use for the image generation. We currently support one lora.
  - Default: `[]`
  - Array of LoraWeight

- **`num_inference_steps`** (`integer`, _optional_):
  The number of inference steps to perform. Default value: `50`
  - Default: `50`
  - Range: `1` to `50`

- **`seed`** (`integer`, _optional_):
  The same seed and the same prompt given to the same version of the model
  will output the same video every time.

- **`guidance_scale`** (`float`, _optional_):
  The CFG (Classifier Free Guidance) scale is a measure of how close you want
  the model to stick to your prompt when looking for a related video to show you. Default value: `7`
  - Default: `7`
  - Range: `0` to `20`

- **`use_rife`** (`boolean`, _optional_):
  Use RIFE for video interpolation Default value: `true`
  - Default: `true`

- **`export_fps`** (`integer`, _optional_):
  The target FPS of the video Default value: `16`
  - Default: `16`
  - Range: `4` to `32`



**Required Parameters Example**:

```json
{
  "prompt": "A garden comes to life as a kaleidoscope of butterflies flutters amidst the blossoms, their delicate wings casting shadows on the petals below. In the background, a grand fountain cascades water with a gentle splendor, its rhythmic sound providing a soothing backdrop. Beneath the cool shade of a mature tree, a solitary wooden chair invites solitude and reflection, its smooth surface worn by the touch of countless visitors seeking a moment of tranquility in nature's embrace."
}
```

**Full Example**:

```json
{
  "prompt": "A garden comes to life as a kaleidoscope of butterflies flutters amidst the blossoms, their delicate wings casting shadows on the petals below. In the background, a grand fountain cascades water with a gentle splendor, its rhythmic sound providing a soothing backdrop. Beneath the cool shade of a mature tree, a solitary wooden chair invites solitude and reflection, its smooth surface worn by the touch of countless visitors seeking a moment of tranquility in nature's embrace.",
  "video_size": {
    "width": 720,
    "height": 480
  },
  "negative_prompt": "Distorted, discontinuous, Ugly, blurry, low resolution, motionless, static, disfigured, disconnected limbs, Ugly faces, incomplete arms",
  "num_inference_steps": 50,
  "guidance_scale": 7,
  "use_rife": true,
  "export_fps": 16
}
```


### Output Schema

The API returns the following output format:

- **`video`** (`File`, _required_):
  The URL to the generated video

- **`timings`** (`Timings`, _required_)

- **`seed`** (`integer`, _required_):
  Seed of the generated video. It will be the same value of the one passed in the
  input or the randomly generated that was used in case none was passed.

- **`prompt`** (`string`, _required_):
  The prompt used for generating the video.



**Example Response**:

```json
{
  "video": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  },
  "prompt": ""
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/fal-ai/cogvideox-5b \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "prompt": "A garden comes to life as a kaleidoscope of butterflies flutters amidst the blossoms, their delicate wings casting shadows on the petals below. In the background, a grand fountain cascades water with a gentle splendor, its rhythmic sound providing a soothing backdrop. Beneath the cool shade of a mature tree, a solitary wooden chair invites solitude and reflection, its smooth surface worn by the touch of countless visitors seeking a moment of tranquility in nature's embrace."
   }'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/cogvideox-5b",
    arguments={
        "prompt": "A garden comes to life as a kaleidoscope of butterflies flutters amidst the blossoms, their delicate wings casting shadows on the petals below. In the background, a grand fountain cascades water with a gentle splendor, its rhythmic sound providing a soothing backdrop. Beneath the cool shade of a mature tree, a solitary wooden chair invites solitude and reflection, its smooth surface worn by the touch of countless visitors seeking a moment of tranquility in nature's embrace."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/cogvideox-5b", {
  input: {
    prompt: "A garden comes to life as a kaleidoscope of butterflies flutters amidst the blossoms, their delicate wings casting shadows on the petals below. In the background, a grand fountain cascades water with a gentle splendor, its rhythmic sound providing a soothing backdrop. Beneath the cool shade of a mature tree, a solitary wooden chair invites solitude and reflection, its smooth surface worn by the touch of countless visitors seeking a moment of tranquility in nature's embrace."
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/fal-ai/cogvideox-5b)
- [API Documentation](https://fal.ai/models/fal-ai/cogvideox-5b/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/cogvideox-5b)
- [GitHub Repository](https://huggingface.co/THUDM/CogVideoX-5b/blob/main/LICENSE)

### fal.ai Platform

- [Platform Documentation](https://docs.fal.ai)
- [Python Client](https://docs.fal.ai/clients/python)
- [JavaScript Client](https://docs.fal.ai/clients/javascript)