text-to-image

FLUX.1 Dev

Name: FLUX.1 Dev API
Brand: VibeDream.ai
Price: 0.02 USD
Availability: InStock

12-billion-parameter rectified-flow transformer for text-to-image generation with inpainting support

On this page

Use one of our client libraries to get started quickly.

FLUX.1 Dev

12-billion-parameter rectified-flow transformer for text-to-image generation with inpainting support. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Image output~5-15sfrom $0.02/run

1. Calling the API

Submit a request

Send a POST request to start generation. The API returns immediately with a prediction ID for polling.

curl -X POST "https://api.vibedream.ai/api/v1/models/flux-dev/generate" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VIBEDREAM_API_KEY" \
  -d '{
    "prompt": "A beautiful sunset over mountains with golden light",
    "image": "https://example.com/your-image.jpg",
    "mask_image": "https://example.com/your-mask_image.jpg",
    "strength": 0.8,
    "size": "1024*1024",
    "num_inference_steps": 28,
    "guidance_scale": 3.5,
    "num_images": 1,
    "seed": -1,
    "output_format": "jpeg"
}'

2. Authentication

The API uses an API Key for authentication.

Get your API Key

Get your API key from vibedream.ai/models/api-keys.

Environment variable

export VIBEDREAM_API_KEY="your-api-key"

3. Queue & Results

Generation requests are queued and processed asynchronously. Poll the prediction endpoint until status is completed or failed.

Submit request

curl -X POST "https://api.vibedream.ai/api/v1/models/flux-dev/generate" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VIBEDREAM_API_KEY" \
  -d '{
    "prompt": "A beautiful sunset over mountains with golden light",
    "image": "https://example.com/your-image.jpg",
    "mask_image": "https://example.com/your-mask_image.jpg",
    "strength": 0.8,
    "size": "1024*1024",
    "num_inference_steps": 28,
    "guidance_scale": 3.5,
    "num_images": 1,
    "seed": -1,
    "output_format": "jpeg"
}'

Response

Returns immediately with a prediction ID. Use id to poll for results.

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "processing",
  "statusUrl": "https://api.vibedream.ai/api/v1/predictions/550e8400-e29b-41d4-a716-446655440000",
  "estimatedTime": "5-15s",
  "costCents": 2,
  "createdAt": "2025-01-15T12:00:00.000Z"
}

Get the result

Polling

# Replace YOUR_PREDICTION_ID with the id from the submit response
curl "https://api.vibedream.ai/api/v1/predictions/YOUR_PREDICTION_ID" \
  -H "Authorization: Bearer $VIBEDREAM_API_KEY"

# Poll every 1-2s until status is "completed" or "failed"

Completed response

outputs is string[] — an array of direct download URLs hosted on assets.vibedream.ai.

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "modelId": "flux-dev",
  "modelName": "FLUX.1 Dev",
  "status": "completed",
  "outputs": [
    "https://assets.vibedream.ai/outputs/550e8400-e29b-41d4-a716-446655440000/1736942400000-0.png"
  ],
  "error": null,
  "createdAt": "2025-01-15T12:00:00.000Z",
  "completedAt": "2025-01-15T12:00:30.000Z"
}

Failed response

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "modelId": "flux-dev",
  "modelName": "FLUX.1 Dev",
  "status": "failed",
  "outputs": null,
  "error": "Your request was flagged by content moderation. Please modify your prompt.",
  "createdAt": "2025-01-15T12:00:00.000Z",
  "completedAt": "2025-01-15T12:00:05.000Z"
}

Field	Type	Description
id	`string`	Unique prediction ID (UUID).
modelId	`string`	ID of the model used for generation.
modelName	`string`	Human-readable model name.
status	`string`	Current status. One of: processing, completed, failed.
outputs	`string[] \| null`	Array of output URLs. Each URL is a direct download link to the generated file on assets.vibedream.ai. null when still processing or failed.
error	`string \| null`	Error message if the generation failed. null on success.
createdAt	`string`	ISO 8601 timestamp when the request was submitted.
completedAt	`string \| null`	ISO 8601 timestamp when generation finished. null while processing.

4. Schema

Input

Parameter	Type	Required	Default	Range	Description
prompt	`string`	Yes	--	--	The positive prompt for the generation
image	`string`	No	--	--	Optional image for image-to-image generationPass a public image URL. Accepted: JPEG, PNG, GIF, WebP.
mask_image	`string`	No	--	--	Mask for inpainting - white areas will be regenerated, black areas preservedPass a public image URL. Accepted: JPEG, PNG, GIF, WebP.
strength	`number`	No	0.8	0 – 1 (step 0.1)	How much to transform the reference image (0 to 1)
size	`string`	No	1024*1024	512512, 768768, 10241024, 1024768, 7681024, 1280720, 720*1280	The size of the generated image in pixels
num_inference_steps	`number`	No	28	1 – 50	Number of inference steps (higher = better quality, slower)
guidance_scale	`number`	No	3.5	1 – 20 (step 0.5)	How closely to follow the prompt (higher = more faithful)
num_images	`number`	No	1	1 – 4	How many images to generate (1-4)
seed	`number`	No	-1	-1 – 2147483647	Random seed for reproducibility (-1 for random)
output_format	`string`	No	jpeg	jpeg, png, webp	The format of the output image

Example request

{
    "prompt": "A beautiful sunset over mountains with golden light",
    "image": "https://example.com/your-image.jpg",
    "mask_image": "https://example.com/your-mask_image.jpg",
    "strength": 0.8,
    "size": "1024*1024",
    "num_inference_steps": 28,
    "guidance_scale": 3.5,
    "num_images": 1,
    "seed": -1,
    "output_format": "jpeg"
}

Output

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "modelId": "flux-dev",
  "modelName": "FLUX.1 Dev",
  "status": "completed",
  "outputs": [
    "https://assets.vibedream.ai/outputs/550e8400-e29b-41d4-a716-446655440000/1736942400000-0.png"
  ],
  "error": null,
  "createdAt": "2025-01-15T12:00:00.000Z",
  "completedAt": "2025-01-15T12:00:30.000Z"
}