WaveSpeedAI APIFlux Kontext Dev LoRA Ultra Fast

Flux Kontext Dev Lora Ultra Fast

FLUX.1 Kontext LoRA Ultra Fast [dev] is an optimized, high-performance version of the state-of-the-art image editing model that lets you edit images using text prompts and LoRA models. It maintains the same high quality while delivering significantly faster processing times.

Features

FLUX.1 Kontext LoRA Ultra Fast [dev] is an optimized, high-performance version of the state-of-the-art image editing model by Black Forest Labs. It maintains all the powerful features of the original model while delivering significantly faster processing times. You can edit images using text prompts and LoRA models with exceptional speed without compromising on quality.

Key Features

  • High Performance: Optimized processing pipeline for significantly faster image generation and editing.
  • LoRA Support: Apply custom styles and transformations using LoRA models for personalized results.
  • Context-Aware Editing: Intelligent understanding of image semantics for precise modifications that preserve natural aesthetics.
  • Precision Control: Granular control over transformations with intuitive parameters and fine-tuning capabilities.
  • SOTA Quality: State-of-the-art results surpassing existing models across all quality benchmarks.

Use Cases

  • Style Transfer: Convert photos to different art styles using LoRA models.
  • Object/Clothing Changes: Modify hairstyles, add accessories, change colors with style-specific LoRAs.
  • Text Editing: Replace text in signs, posters, and labels.
  • Background Swapping: Change environments while preserving subjects.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-kontext-dev-lora-ultra-fast" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "A restored and colorized vintage black-and-white photograph, removing scratches, dust, and tears. The image features enhanced clarity, natural skin tones, and realistic colors while preserving the original nostalgic atmosphere. The photo looks vivid and fresh, with balanced lighting and rich detail, as if carefully brought back to life from the past.",
    "image": "https://d2g64w682n9w0w.cloudfront.net/media/images/1750946150521827253_czYURNKG.jpg",
    "size": "1024*1024",
    "num_inference_steps": 28,
    "guidance_scale": 2.5,
    "num_images": 1,
    "seed": -1,
    "loras": [],
    "enable_base64_output": false,
    "enable_safety_checker": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYesA restored and colorized vintage black-and-white photograph, removing scratches, dust, and tears. The image features enhanced clarity, natural skin tones, and realistic colors while preserving the original nostalgic atmosphere. The photo looks vivid and fresh, with balanced lighting and rich detail, as if carefully brought back to life from the past.-The prompt to generate an image from.
imagestringNohttps://d2g64w682n9w0w.cloudfront.net/media/images/1750946150521827253_czYURNKG.jpg-The image to generate an image from.
sizestringNo1024*1024512 ~ 1536 per dimensionThe size of the generated image.
num_inference_stepsintegerNo281 ~ 50The number of inference steps to perform.
guidance_scalenumberNo2.50.0 ~ 20.0The 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 image to show you.
num_imagesintegerNo11 ~ 4The number of images to generate.
seedintegerNo-1-1 ~ 9999999999 The same seed and the same prompt given to the same version of the model will output the same image every time.
lorasarrayNo[]max 5 itemsList of LoRAs to apply (max 5)
loras[].pathstringYes-Path to the LoRA model
loras[].scalefloatYes-0.0 ~ 4.0Scale of the LoRA model
enable_base64_outputbooleanNofalse-If enabled, the output will be encoded into a BASE64 string instead of a URL.
enable_safety_checkerbooleanNotrue-If set to true, the safety checker will be enabled.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Query Parameters

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.