Flux Kontext Pro Text To Image

Flux Kontext Pro Text To Image

Playground

FLUX.1 Kontext [pro] is a premium text-to-image model with maximum performance and greatly improved prompt adherence for accurate outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX Kontext Pro (Text-to-Image) — wavespeed-ai/flux-kontext-pro/text-to-image

FLUX Kontext Pro is a fast, high-quality text-to-image model designed for reliable everyday generation. It delivers strong prompt adherence and clean composition with efficient latency—great for marketing creatives, story frames, concept art, and general-purpose visual production.

Key capabilities

• Prompt-faithful text-to-image generation with consistent visual quality
• Strong composition control via scene + camera + lighting language
• Produces clean, usable outputs quickly for iterative workflows
• Includes a configurable safety_tolerance setting for content filtering control

Pricing

$0.04 per image.

Total cost = num_images × $0.04 Example: num_images = 4 → $0.16

How to use

1. Write a prompt describing the subject, scene, action, and style.
2. Choose an aspect ratio that matches your layout (e.g., 16:9, 1:1, 9:16).
3. Set guidance_scale for how strictly the image should follow your prompt.
4. Optionally set seed for reproducible results, then generate.

Parameters

• prompt (required): Text description of what to generate
• aspect_ratio: Output aspect ratio (e.g., 16:9, 1:1, 9:16)
• seed: Fixed value for reproducibility; leave empty/random for variation
• guidance_scale: Prompt adherence strength (higher = stricter; too high may look rigid)
• safety_tolerance: Safety filtering level (higher typically allows more; use responsibly)

Prompting guide

A stable prompt structure:

• Subject: who/what is in frame
• Action: what is happening
• Scene: location + time + atmosphere
• Camera: framing, angle, lens vibe
• Lighting: softbox, sunset, neon, rim light, etc.
• Style: realistic, illustration, film still, etc.

Example pattern: A [shot type] of [subject] [action] in [scene]. [Lighting + mood]. [Camera/framing]. [Style cues].

Example prompts

• A close-up portrait of a child in a yellow raincoat hugging a golden retriever after the rain, wet grass and a faint rainbow behind, soft natural light, warm mood, shallow depth of field.
• Wide shot of a cozy café interior at night, warm tungsten lighting, rain on the windows, cinematic composition, film still look.
• Studio product photo of a minimal sneaker on a clean background, softbox lighting, crisp shadows, premium advertising style.

Best practices

• Keep the first sentence concrete, then add camera and lighting constraints.
• Use guidance_scale sparingly; moderate values often look more natural.
• For consistent iteration, fix seed and adjust only one variable at a time.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-kontext-pro/text-to-image" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "1:1",
    "guidance_scale": 3.5,
    "safety_tolerance": "2",
    "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}"