Flux 3
Overview
FLUX 3 marks Black Forest Labs’ most ambitious expansion beyond standalone image generation, bringing image, video, audio, language, and action prediction into one shared multimodal architecture. It builds on Self-Flow, BFL’s approach for aligning multimodal generation and understanding within the same underlying system. By substantially scaling the compute and data used to train images, video, and audio together, FLUX 3 can learn how scenes are structured, how objects move, how physical events produce sound, and how actions reshape the world over time.
Test API KEY: key_00000000000000000000000000000000Endpoints
1. Create Task
Request
POST https://api.pixwithapi.online/api/task/createHeaders
| Header | Value | Required |
|---|---|---|
| Content-Type | application/json | Yes |
| Api-Key | {API_KEY} | Yes |
Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| prompt | string | Yes | The video generation prompt. Max length: 5000. |
| image_urls | array | Conditional | Optional ordered keyframe images for image-to-video. Provide 1 to 8 public image URLs. Omit for text-to-video. |
| model_id | string | Yes | 2-82 |
| options | object | Yes | Generation options. |
| options.prompt_optimization | boolean | No | Translate and optimize the prompt before generation. Default: false. |
| options.aspect_ratio | string | No | Output aspect ratio. Valid values: 'Auto', '21:9', '2:1', '16:9', '4:3', '1:1', '3:4', '9:16'. Default: 'Auto'. |
| options.resolution | string | No | Output resolution. Valid values: '720p', '1080p'. Default: '720p'. |
| options.duration | int | No | Output duration in seconds. Valid values: 5, 10, 15, 20. Default: 5. |
| options.sound | boolean | No | Generate synchronized audio. Default: true. |
Example Request — Text-to-Video
{
"prompt": "A cinematic tracking shot of a fox walking through a misty forest at dawn",
"model_id": "2-82",
"options": {
"prompt_optimization": true,
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"sound": true
}
}Example Request — Image-to-Video
{
"prompt": "Animate the scene with a slow camera push and natural motion",
"image_urls": [
"https://cdn.pixwithapi.online/images/example-first-frame.jpg",
"https://cdn.pixwithapi.online/images/example-last-frame.jpg"
],
"model_id": "2-82",
"options": {
"prompt_optimization": true,
"aspect_ratio": "Auto",
"resolution": "1080p",
"duration": 10,
"sound": true
}
}Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | int | 1=success, 0=error |
| message | string | Success and failure messages |
| data | object | |
| data.task_id | string | Task identifier. |
| data.estimated_time | int | Estimated time in seconds. |
Response
{
"code": 1,
"message": "success",
"data": {
"task_id": "d425ab4dc256f0ebaa84862b9cea8a3d",
"estimated_time": 90
}
}Last updated on