Flux Kontext Pro Multi

Flux Kontext Pro Multi

Playground

Experimental FLUX.1 Kontext [pro] with multi-image handling to combine context from multiple images for richer output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX Kontext Pro Multi — wavespeed-ai/flux-kontext-pro/multi

FLUX Kontext Pro Multi is a fast, reliable multi-image model for context-guided generation and editing. Provide a text prompt plus up to 5 reference images, and the model uses them to improve identity consistency, style alignment, and scene coherence—ideal for practical production workflows that need strong control at a lower cost.

Key capabilities

• Multi-image contextual generation with up to 5 reference images
• Strong identity and style consistency by grounding outputs in references
• Reliable composition control for everyday creative and marketing use
• Efficient for iterative workflows and rapid A/B exploration

Typical use cases

• Character consistency using multiple portraits, outfits, or angles
• Product and branding consistency (packaging + logo + lighting references)
• Style steering with multiple exemplars (art style + texture + mood)
• Scene creation guided by reference frames
• Marketing creatives that need predictable, repeatable visual direction

Pricing

$0.04 per image.

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

Inputs and outputs

Input:

• prompt (required): Instruction describing what to generate and how to use the references
• images (required): Up to 5 reference images (upload or public URLs)

Output:

• One or more generated images (based on your num_images setting, if available in your interface)

Parameters

• prompt (required): The instruction for generation or editing
• images (required): Up to 5 reference images
• seed: Fixed value for reproducibility; leave empty/random for variation
• guidance_scale: Prompt adherence strength (higher = stricter; too high may over-constrain)
• aspect_ratio: Output aspect ratio (e.g., 16:9, 1:1, 9:16)

Prompting guide (multi-reference)

Assign roles to references to reduce ambiguity:

Template: Use image 1 for identity. Use image 2 for outfit/material. Use image 3 for style. Use image 4 for lighting. Use image 5 for background/scene. Generate the shot described below. Keep the key traits unchanged.

Example prompts

• Use image 1 for the person’s identity and image 2 for outfit details. Use image 3 for visual style. Create a 16:9 cinematic medium shot in a rainy city street at night. Match lighting and reflections. Keep face structure and expression consistent.
• Use image 1 for the product shape and image 2 for label layout. Use image 3 for lighting mood. Generate a clean studio product shot with realistic shadows and crisp edges. Keep branding placement consistent.
• Use images 1–2 as identity references from different angles. Create a neutral-background portrait with softbox lighting and natural skin texture. Keep proportions realistic and avoid exaggerated stylization.

Best practices

• Use high-quality references (sharp, well-lit, minimal occlusion)
• Avoid conflicting references unless you explicitly state which reference dominates (identity vs. style vs. scene)
• Keep guidance_scale moderate and let references do most of the steering
• Fix seed when you need stable iteration and consistent comparisons
• Choose aspect_ratio intentionally to avoid awkward cropping or stretched composition

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