Models

Image generation models

By KrafLayer team6 min read2026-04-06

TL;DR

Compare AI image generation and image edit models by input, output controls, and workflow features.

Prompt-only vs. reference-image editing

Image generation models take a text prompt and produce a new image from scratch. Image edit models start from a reference image and apply style, composition, or content changes while keeping the original as a guide.

Use the table to compare input requirements, output controls, and workflow features across the active lineup.

How to read the table

  • Input tells you whether the model starts from prompt only or from prompt plus a reference image.
  • Output summarizes the major image controls that matter in the product.
  • Features highlight the extra capabilities that change workflow choice.
  • Use Costs by model and task when you need the current credit cost.
  • [Image editing tools](/docs/editing-tools)
  • [Nano Banana series](/docs/nano-banana-models)
  • [GPT Image 2 series](/docs/gpt-image-2-models)
  • [Costs by model and task](/docs/generation-cost)
  • [Plans and price](/docs/pricing-and-credits)

Related KrafLayer tools