FLUX.2 Pro Edit API by Black Forest Labs

FLUX.2 Pro — Edit (Image Editing)

Developer: Black Forest Labs
Model ID: black-forest-labs/flux-2-pro/edit
Release Date: November 25, 2025

Overview

FLUX.2 Pro Edit is a professional image editing model built on the same multimodal flow matching architecture as FLUX.2 Pro. It accepts a text prompt alongside one or more reference images, enabling targeted edits, subject replacement, style transfer, and multi-reference identity-consistent generation — all without fine-tuning.

FLUX.2 Pro Edit supports up to 8 reference images per request, allowing character or product identity to be locked across an entire campaign with high visual consistency.

Key Capabilities

• High-fidelity editing up to 4MP — Precise, photorealistic edits with realistic lighting, spatial logic, and fine detail.
• Multi-reference consistency — Lock character or product identity across multiple images, maintaining visual consistency from shot to shot.
• Brand-accurate results — Exact hex-color matching, reliable typography, and structured controls for brand compliance.
• Robust consistency across successive edits — Supports multiple rounds of editing with minimal visual drift.
• Strong prompt fidelity — Precise positioning, physics-aware lighting, and composition control with up to 32K token support.

Use Cases

• Image editing — Edit existing images through text instructions: change backgrounds, swap textures, alter objects, or relight scenes.
• Multi-reference generation — Maintain character, product, or style consistency across compositions using multiple reference images.
• Campaign asset creation — Generate a series of brand-consistent images from a set of reference shots.
• Product visualization — Place products in new environments or combine product elements for e-commerce and marketing.
• Iterative refinement — Refine images through successive edits while maintaining overall visual coherence.

Input Parameters

Note on images: Each item can be a publicly accessible image URL or a Base64-encoded image string (e.g., data:image/jpeg;base64,...). When only one reference image is provided, its actual resolution is used for billing. When multiple images are provided, each is billed at a flat 1 MP rate.

Output

Returns a URL to the edited image. The model supports asynchronous generation: the response first contains a polling URL, which resolves to the final image once processing is complete.

Output formats: JPEG, PNG Maximum output resolution: 4 megapixels (e.g., 2048×2048)

Pricing

Pricing covers both the generated output image and the reference input image(s), each measured in megapixels (MP). 1 MP = 1,048,576 pixels. Resolution is capped at 4 MP for billing purposes.

SKUs

Formula

cost = sku_gen_first_mp
     + max(0, min(4, ceil(width × height / 1,048,576)) - 1) × sku_gen_extra_mp
     + reference_image_cost

Where reference_image_cost is:

• Multiple images (len(images) > 1): each image is billed at 1 MP flat:

  reference_image_cost = len(images) × sku_ref_mp

• Single image (len(images) == 1): actual resolution of the image is used (capped at 4 MP):

  reference_image_cost = min(4, ceil(GetImagePixelsFromURL(images[0]) / 1,048,576)) × sku_ref_mp

Examples

When a single reference image is provided, its actual pixel count is fetched at billing time. If the image URL is inaccessible or returns an error, billing fails and the request is not charged.