Flux Kontext Dev LoRA Ultra Fast

Flux Kontext Dev LoRA Ultra Fast

Playground

Ultra-fast FLUX.1 Kontext [dev] endpoint with LoRA support for rapid image editing and brand/style adaptation using pre-trained LoRA. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX Kontext Dev LoRA Ultra Fast — wavespeed-ai/flux-kontext-dev-lora-ultra-fast

FLUX Kontext Dev LoRA Ultra Fast is a low-latency image-to-image editing model that supports LoRA adapters directly in the request. Provide a source image plus a natural-language edit instruction, and optionally attach up to 3 LoRAs to steer style, identity consistency, or domain aesthetics—optimized for rapid iteration and production workflows.

Key capabilities

• Ultra-fast instruction-based image editing from a single input image
• LoRA-enabled inference: apply up to 3 LoRAs via input parameters
• Strong preservation when you explicitly state what must remain unchanged
• Great for iterative editing: quick refinements across multiple passes with minimal drift

Typical use cases

• Fast retouching + consistent styling using a “house look” LoRA
• Batch product edits (color variants, background swaps) with brand LoRAs
• Text edits on packaging/signage while keeping typography/perspective consistent
• Rapid A/B testing by switching LoRAs instead of rewriting prompts

Pricing

$0.025 per image.

Cost per run = num_images × $0.025 Example: num_images = 4 → $0.10

Inputs and outputs

Input:

• One source image (upload or public URL)
• One edit instruction (prompt)
• Optional: up to 3 LoRA items

Output:

• One or more edited images (controlled by num_images)

Parameters

Core:

• prompt: Edit instruction describing what to change and what to preserve
• image: Source image
• width / height: Output resolution
• num_inference_steps: More steps can improve fidelity but increases latency
• guidance_scale: Higher values follow the prompt more strongly; too high may over-edit
• num_images: Number of variations generated per run
• seed: Fixed value for reproducibility; -1 for random
• output_format: jpeg or png
• enable_base64_output: Return BASE64 instead of a URL (API only)
• enable_sync_mode: Wait for generation and return results directly (API only)

LoRA (up to 3 items):

• loras: A list of LoRA entries (max 3)

  • path: owner/model-name or a direct .safetensors URL
  • scale: LoRA strength (start around 0.6–1.0 and adjust)

Prompting guide

Use a clear “preserve + edit + constraints” structure and let LoRAs control the look:

Template: Keep [what must stay]. Change [what to edit]. Ensure [constraints]. Apply LoRA style consistently without altering identity.

Example prompts

• Keep the person’s face, hairstyle, and pose unchanged. Replace the background with a clean studio backdrop. Match lighting direction and shadow softness.
• Keep the product shape and label layout unchanged. Replace only the label text with “WaveSpeedAI”, preserving font style, size, and perspective.
• Remove the background clutter and keep the main subject sharp. Preserve natural skin texture while reducing shine.

Best practices

• Start with one LoRA first; add a second/third only when needed.
• If the output is over-stylized, reduce LoRA scale and/or guidance_scale.
• For consistent batches, reuse the same LoRA set + scales and fix seed for comparisons.
• Match width/height to the original aspect ratio to avoid distortions.

# 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 '{
    "num_inference_steps": 28,
    "guidance_scale": 2.5,
    "num_images": 1,
    "seed": -1,
    "loras": [],
    "output_format": "jpeg",
    "enable_base64_output": false,
    "enable_sync_mode": false
}'

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