Technical Specifications of `black-forest-labs/flux-kontext-pro`

Specification	Details
Model ID	`black-forest-labs/flux-kontext-pro`
Provider	Black Forest Labs
Category	Multimodal diffusion model
Input Modalities	Text prompts and optional reference images
Output Modality	Generated images
Core Capability	Context-aware image generation grounded by prompt and visual references
Reference Conditioning	Supports image-guided synthesis to preserve composition and style cues
Reproducibility	Seed control for repeatable outputs
Typical Use Cases	Brand asset creation, product visuals, visual ideation, mood-board-driven generation
Integration Type	API-based image generation workflow

What is `black-forest-labs/flux-kontext-pro`?

black-forest-labs/flux-kontext-pro is a multimodal diffusion model designed for context-aware image generation. It creates images from natural language prompts and can optionally use reference images to guide the final result. This allows developers and creative teams to generate visuals that are not only prompt-compliant but also better aligned with desired composition, framing, tone, or stylistic direction.

Because it combines text understanding with image-based conditioning, black-forest-labs/flux-kontext-pro is well suited for workflows where consistency and grounding matter. Teams can use it to produce marketing graphics, product-centric imagery, concept explorations, and other visuals that benefit from example-based steering. Seed control also helps make outputs more reproducible, which is useful when iterating on creative assets or maintaining repeatable generation pipelines.

Main features of `black-forest-labs/flux-kontext-pro`

Multimodal prompting: Accepts text prompts and optional reference images, enabling more controlled image generation than text-only workflows.
Context-aware generation: Uses prompt context and visual guidance together to synthesize outputs that better reflect the intended subject, layout, and style.
Reference-conditioned sampling: Leverages example images to preserve composition and stylistic cues for grounded creative results.
Creative consistency: Helps teams maintain more coherent visual direction across asset variations, especially in branding and product content workflows.
Seed-controlled reproducibility: Supports repeatable generations through seed parameters, which is useful for testing, refinement, and production pipelines.
Visual ideation support: Works well for mood boards, example-shot-driven exploration, and concept development where visual references accelerate iteration.
Production-friendly applications: Suitable for brand asset creation, product visuals, campaign mockups, and other commercial image-generation scenarios.

How to access and integrate `black-forest-labs/flux-kontext-pro`

To get started, create an account on CometAPI and generate your API key from the dashboard. This key is required to authenticate every request and route it to the black-forest-labs/flux-kontext-pro model.

Step 2: Send Requests to `black-forest-labs/flux-kontext-pro` API

Once you have your API key, send requests to the CometAPI endpoint with black-forest-labs/flux-kontext-pro as the model. Include your prompt and any optional reference-image inputs required by your workflow.

curl --request POST \
  --url https://api.cometapi.com/v1/responses \
  --header "Authorization: Bearer $COMETAPI_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "black-forest-labs/flux-kontext-pro",
    "input": [
      {
        "role": "user",
        "content": [
          { "type": "input_text", "text": "Create a premium studio product image of a minimalist skincare bottle with soft natural lighting." }
        ]
      }
    ]
  }'

Step 3: Retrieve and Verify Results