Flux Dev

Flux Dev is a high-speed image generation API designed for rapid prototyping and development workflows.

Features

High-Speed Generation: Optimized for fast image generation with minimal latency
Developer-Focused: Designed specifically for development and prototyping needs
Flexible Controls: Comprehensive parameter settings for fine-tuned results
HTTP API Access: Simple integration via RESTful API endpoints

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task

Submit a task to generate an image using the Flux Dev Fast API.

curl --location --request POST 'https://api.wavespeed.ai/api/v2/wavespeed-ai/flux-dev' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data-raw '{
  "prompt": "A futuristic cityscape with flying cars and neon lights",
  "image": "https://example.com/input_image.jpg",
  "strength": 0.6,
  "size": "1024*1024",
  "num_inference_steps": 28,
  "guidance_scale": 5.0,
  "num_images": 1,
  "seed": -1,
  "enable_safety_checker": true
}'

Query Result

Check the status and retrieve the result of a previously submitted task.

curl --location --request GET 'https://api.wavespeed.ai/api/v2/predictions/{request_id}/result' \
--header 'Authorization: Bearer YOUR_API_KEY'

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
prompt	string	No	""	-	Text description of the image to generate
image	string	No	""	-	Base64 encoded image or image URL for image-to-image generation
strength	float	No	0.6	0.0 ~ 1.0	Strength of the image-to-image transformation
loras	array	No	[]	max 5 items	List of LoRA models to apply
size	string	No	”1024*1024”	512 ~ 1536 per dimension	Image dimensions in width*height format
num_inference_steps	int	No	28	1 ~ 50	Number of inference steps for dev model
seed	int	No	-1	-	Random seed for reproducible results. -1 for random seed
guidance_scale	float	No	5.0	0.0 ~ 10.0	Guidance scale for generation
num_images	int	No	1	1 ~ 4	Number of images to generate
enable_safety_checker	boolean	No	true	-	Enable safety checker for generated content

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction (e.g., `wavespeed-ai/wan-2.1/t2v-480p`)
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created
data.error	string	Error message (empty if no error occurred)
data.executionTime	integer	Execution time in milliseconds

Result Query Parameters

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction
data.model	string	Model ID used for the prediction (e.g., `wavespeed-ai/wan-2.1/t2v-480p`)
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created
data.error	string	Error message (empty if no error occurred)
data.executionTime	integer	Execution time in milliseconds

Result Query Parameters

Maximum requests per minute: 120 (optimized for development workflows)
Maximum concurrent requests: 20
Maximum image dimensions: 1536x1536
Response timeout: 30 seconds
Designed for development use - consider using other Flux APIs for production

webhooks flux-lora