> For the complete documentation index, see [llms.txt](https://xalora-ai.gitbook.io/xalora-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://xalora-ai.gitbook.io/xalora-ai-docs/text2video-workflow.md).
# Text2Video Workflow
Generate videos from text descriptions using advanced AI models.
This workflow extends the base [ComfyUI Workflow](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-workflow) functionality to support text-to-video generation.
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#supported-models-to-workflow-id-mapping)Supported Models to Workflow ID Mapping
| Workflow ID | Model |
| ----------- | ------- |
| 1 | Hunyuan |
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#before-you-start)Before you start
1. [Get an API key](https://heurist.ai/credits)
2. Define environment variables in `.env` file:
Copy
```
XALORA_API_KEY=your_api_key
XALORA_WORKFLOW_URL=https://sequencer-v2.xalora.xyz
```
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#example-request)Example Request
Copy
```
import Xalora from 'xalora'
const xalora = new Xalora({
apiKey: process.env['XALORA_API_KEY']
});
async function generateVideo() {
const text2VideoTask = new Text2VideoTask({
workflow_id: '1',
prompt: 'a rabbit moving quickly in a beautiful winter scenery nature trees sunset tracking camera',
timeout_seconds: 600 // optional
});
const response = await xalora.workflow.executeWorkflowAndWaitForResult(
text2VideoTask,
600000, // 10 minutes timeout
15000 // 15 seconds polling interval
);
console.log('Generated video URL:', response.result);
}
```
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#example-response)Example Response
Copy
```
{
"task_id": "7599f1f038",
"create_timestamp": 1733965543,
"inference_latency": 0.608921,
"upload_latency": 2.316333,
"task_type": "txt2vid",
"status": "finished",
"result": "https://example.com/generated-video.webp",
"task_details": {
"parameters": {
"fps": 24,
"height": 480,
"length": 37,
"prompt": "a rabbit moving quickly in a beautiful winter scenery nature trees sunset tracking camera",
"quality": 80,
"seed": 704883238463297,
"steps": 30,
"width": 848
}
},
"timeout_seconds": 600,
"workflow_id": "1"
}
```
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#parameters)Parameters
**Type**: `Text2VideoTask`
| Property | Type | Required | Description |
| ---------------- | ------ | -------- | --------------------------------------------------------------------------------------------------------- |
| workflow\_id | string | true | The ID of the workflow to execute. |
| prompt | string | true | The prompt to use for the video generation. |
| width | number | false | The width of the video. Default is 848. |
| height | number | false | The height of the video. Default is 480. |
| length | number | false | The length of the video in frames. Default is 37. |
| steps | number | false | The number of steps to use for the video generation. Default is 30. |
| seed | number | false | The seed to use for the video generation. |
| fps | number | false | The frames per second of the video. Default is 24. |
| quality | number | false | The quality of the video. Default is 80. |
| job\_id\_prefix | string | false | An optional prefix for the job ID. Default is “sdk-workflow”. |
| timeout\_seconds | number | false | The timeout for the task in seconds. If the task is not finished within the timeout, it will be canceled. |
| consumer\_id | string | false | The ID of the consumer. |
| api\_key | string | false | The API key of the consumer. |
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#returns)Returns
**Type**: `WorkflowTaskResult`
| Property | Type | Required | Description |
| ------------------ | ------ | -------- | ---------------------------------------------- |
| task\_id | string | true | The ID of the executed task. |
| status | enum | true | The status of the task. |
| result | any | false | The result of the task, if available. |
| task\_details | any | false | The details of the task, if available. |
| timeout\_seconds | number | false | The timeout for the task in seconds. |
| workflow\_id | string | false | The ID of the workflow that executed the task. |
| create\_timestamp | number | false | The timestamp when the task was created. |
| inference\_latency | number | false | The latency of the inference in seconds. |
| upload\_latency | number | false | The latency of the upload in seconds. |
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#authentication)Authentication
Authentication uses a combined consumer ID and API key format: `consumerId#apiKey`. You can provide these in two ways:
1. In the Xalora client initialization using environment variables:
Copy
```
const xalora = new Xalora({
apiKey: process.env['XALORA_API_KEY'] // format: consumerId#apiKey
});
```
2. In the `Text2VideoTask` object, the task-specific values will override the client defaults if provided.
Copy
```
const text2VideoTask = new Text2VideoTask({
consumer_id: 'consumerId',
api_key: 'apiKey',
...
});
```
## [](https://docs.heurist.ai/dev-guide/heurist-sdk/comfyui-txt2vid#types)Types
`Text2VideoTask`
A class representing a text-to-video task, extending the abstract `WorkflowTask` class.
Copy
```
class Text2VideoTask extends WorkflowTask {
constructor(options: Text2VideoTaskOptions)
get task_type(): WorkflowTaskType.Text2Video
get task_details(): {
parameters: {
prompt: string
width?: number
height?: number
length?: number
steps?: number
seed?: number
fps?: number
quality?: number
}
}
}
```
`WorkflowTaskType`
An enum representing the types of workflow tasks.
Copy
```
enum WorkflowTaskType {
Text2Video = 'txt2vid'
}
```
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://xalora-ai.gitbook.io/xalora-ai-docs/text2video-workflow.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.