Flux Kontext Dev Multi Ultra Fast

Flux Kontext Dev Multi Ultra Fast

Playground

Experimental FLUX.1 Kontext [dev] - Multi-Ultra-Fast endpoint with native multi-image handling for batch and multi-view inputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX Kontext Dev Multi Ultra Fast — wavespeed-ai/flux-kontext-dev/multi-ultra-fast

FLUX.1 Kontext Dev Multi Ultra Fast is a low-latency, multi-image editing model designed for fast, instruction-based image editing with richer context. Provide up to 4 reference images plus a text instruction, and the model performs controlled edits while using the references to improve consistency across identity, style, and scene—optimized for rapid iteration and production workflows.

Key capabilities

• Ultra-fast multi-image contextual editing with up to 4 reference images
• Stronger consistency by grounding edits in multiple references (identity, outfit, style, lighting, background)
• Supports both local edits and global transformations
• Ideal for iterative workflows: quick refinements with minimal drift

Typical use cases

• Multi-reference character consistency for portraits and creatives
• Product/branding edits using multiple references (logo + label + lighting + packaging)
• Background swaps with better subject matching (lighting, shadows, perspective)
• Text edits that must follow reference typography and layout
• Rapid A/B iteration for marketing assets and creative variations

Pricing

$0.025 per generation.

If you generate multiple outputs in one run, total cost = num_images × $0.025 Example: num_images = 4 → $0.10

Inputs and outputs

Input:

• Up to 4 reference images (upload or public URLs)
• One edit instruction (prompt)

Output:

• One or more edited images (controlled by num_images)

Parameters

• prompt: Edit instruction describing what to change and what to preserve
• images: Up to 4 reference images
• 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)

Prompting guide

Assign clear roles to references to avoid conflicts:

Template: Use reference 1 for [identity]. Use reference 2 for [outfit/material]. Use reference 3 for [style/lighting]. Use reference 4 for [background/scene]. Keep [must-preserve]. Change [edit request]. Match [lighting/shadows/perspective].

Example prompts

• Use reference 1 for face identity and reference 2 for hairstyle. Keep the pose from the base image. Replace the background with a clean studio setup and match shadow direction.
• Use reference 1 for the product shape and reference 2 for the label design. Replace the label text with “WaveSpeedAI”, keeping font style, perspective, and print texture consistent.
• Use reference 3 as the style guide (soft illustration look) and reference 4 for lighting mood (sunset). Preserve identity from reference 1 and keep composition unchanged.

Best practices

• Use high-quality references with clear subjects and minimal occlusion.
• Give each reference a purpose (identity vs. style vs. scene) for more reliable results.
• Iterate with one change per run for tighter control.
• Fix seed for stable comparisons across prompt variants.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-kontext-dev/multi-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,
    "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}"