Back to Nodes
Flux 2 Dev

Flux 2 Dev

Official

Advanced 32B parameter model for photorealistic image generation and editing with multi-reference support.

Nodespell AI
AI / Image / Black Forest Labs

Advanced 32B parameter model for photorealistic image generation and editing with multi-reference support.

Overview

FLUX.2 Dev is a 32 billion parameter model developed by Black Forest Labs that unifies high-quality image generation and editing from text prompts. It supports creating new images, modifying existing ones, and combining multiple reference images (up to ten) to maintain consistent details such as characters, products, or styles. The model leverages a latent flow matching architecture integrating the Mistral-3 vision-language model and a rectified flow transformer, enabling strong real-world context understanding, accurate spatial relationships, and realistic lighting effects.

Strengths / What it does well

  • Generates photorealistic images from complex, structured text prompts with accurate text rendering.
  • Edits images up to 4 megapixels, allowing localized modifications while preserving unedited image parts.
  • Maintains consistency across multiple reference images, ideal for product branding or character continuity.
  • Produces sharper textures and stable lighting compared to previous versions.

Improvements over previous versions

  • Supports multi-reference inputs up to 10 images for improved consistency.
  • Enhanced legible typography rendering within generated images.
  • Better adherence to complex prompt instructions.
  • Increased photorealism with higher resolution editing capabilities (up to 4 MP).
  • Stronger grounding in real-world knowledge and spatial logic.

Best use cases

  • Product photography and branding mockups
  • Character design consistency across scenes
  • Infographic and user interface mockups requiring complex typography
  • Photorealistic concept art and visualization
  • Marketing materials blending multiple references

Model Examples (4)

Example Index01 / 04
Example 01

Editorial bakery campaign

Creates a warm documentary-style bakery campaign still with realistic morning light.

Open
Source Inputs01
Prompt

A warm documentary-style campaign still for an independent neighborhood bakery at 6 AM. A flour-dusted baker is setting trays of cardamom buns onto a marble counter, soft window light, quiet street outside, tactile food texture, natural skin tones, editorial food photography, realistic lens rendering, no visible brand names or readable signage.

Parameters07
Prompt
A warm documentary-style campaign still for an independent neighborhood bakery at 6 AM. A flour-dusted baker is setting trays of cardamom buns onto a marble counter, soft window light, quiet street outside, tactile food texture, natural skin tones, editorial food photography, realistic lens rendering, no visible brand names or readable signage.
Aspect Ratio
4:5
Go Fast
true
Output Format
png
Output Quality
90
Disable Safety Checker
false
Seed
-1
image-generationcommercialeditorialfood
Response
Editorial bakery campaign output
Inputs (2)

Prompt

String

Text description of the image to generate.

Multi InputMin: 0Max: 100

Input Images

String

List of input images for image-to-image generation. Maximum 4 images. Must be jpeg, png, gif, or webp.

Multi InputMin: 0Max: 100
Parameters (9)

Seed

Number

Random seed. Set for reproducible generation.

Default: -1

Width

Number

Width of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32).

Default: 256

Height

Number

Height of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32).

Default: 256

Prompt

String

Text description of the image to generate.

Default:

Go Fast

Boolean

Run faster predictions with additional optimizations.

Default: true

Aspect Ratio

String

Aspect ratio for the generated image. Use 'match_input_image' to match the first input image's aspect ratio.

Default: 1:1

Output Format

String

Format of the output images.

Default: webp

Output Quality

Number

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.

Default: 80

Disable Safety Checker

Boolean

Disable safety checker for generated images.

Default: false
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

London

Building the future. Join us!

nodespell.comnodespell.appNodespellAI
Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Image / Black Forest Labs

Input

TextImage

Output

Image

Keywords

Image GenerationImage EditAspect ControlResolution Control
Use in Workflow