Flux 2 Image to Image

FLUX.2 [dev] - Image Editing

Lightweight multi-reference editing optimized for speed without sacrificing transformation quality. FLUX.2 [dev] combines multiple input images through an efficient architecture that delivers professional edits at rapid pace. Whether compositing references, style transfers, or context-aware modifications, dev handles natural language editing instructions with the same speed-quality balance that makes it ideal for high-throughput workflows and custom training foundations.

Built for: Rapid editing iterations | High-volume image processing | Cost-efficient transformation workflows | Foundation for specialized editing fine-tuning | Production pipelines prioritizing speed

Efficient Multi-Reference Editing

FLUX.2 [dev] extends its lightweight architecture to image editing, understanding relationships between input images while maintaining the speed advantages that make dev ideal for teams moving quickly through creative development and production workflows.

What this means for you:

• Multi-image composition: Combine multiple reference images in a single edit through natural language instructions. Reference specific images by index or describe elements naturally
• Fast transformation cycles: Lightweight architecture processes edits significantly faster than heavier variants, enabling rapid iteration through creative refinements
• Natural language editing: Describe complex changes without masks or layers—"replace the background with image 2 while maintaining the lighting from the original"
• Explicit image indexing: Reference specific inputs by number for precise control—"the jacket from image 3 on the person from image 1"
• LoRA training foundation: Base editing model for custom fine-tuning via flux trainer, enabling specialized editing behaviors for brand-specific transformations or domain requirements
• Efficient resource usage: Lower computational overhead supports high-volume editing operations where speed and cost matter

Advanced Prompting Techniques

JSON Structured Prompts

For precise control over complex generations, use structured JSON prompts instead of natural language. JSON prompting enables granular specification of scene elements, subjects, camera settings, and composition.

Basic JSON structure:

json
{
  "scene": "Overall setting description",
  "subjects": [
    {
      "type": "Subject category",
      "description": "Physical attributes and details",
      "pose": "Action or stance",
      "position": "foreground/midground/background"
    }
  ],
  "style": "Artistic rendering approach",
  "color_palette": ["color1", "color2", "color3"],
  "lighting": "Lighting conditions and direction",
  "mood": "Emotional atmosphere",
  "composition": "rule of thirds/centered/dynamic diagonal",
  "camera": {
    "angle": "eye level/low angle/high angle",
    "distance": "close-up/medium shot/wide shot",
    "lens": "35mm/50mm/85mm"
  }
}

JSON prompts excel at controlling multiple subjects, precise positioning, and maintaining specific attributes across complex compositions.

HEX Color Code Control

Specify exact colors using HEX codes for precise color matching and brand consistency. Include the keyword "color" or "hex" before the code for best results.

Examples:

• `"a wall painted in color #2ECC71"`
• `"gradient from hex #FF6B6B to hex #4ECDC4"`
• `"the car in color #1A1A1A with accents in #FFD700"`

For enhanced accuracy, reference a color swatch image alongside the HEX code in your prompt.

Image Referencing with @

Reference uploaded images directly in prompts using the `@` symbol for intuitive multi-image workflows.

Usage patterns:

• `"@image1 wearing the outfit from @image2"`
• `"combine the style of @image1 with the composition of @image2"`
• `"the person from @image1 in the setting from @image3"`

The `@` syntax provides a natural way to reference multiple images without explicit index notation, while maintaining support for traditional "image 1", "image 2" indexing.