Artgen
Artgen
Artgen
Artgen
DocsArtgenArtgen docs
How to choose an AI image modelFLUX.1 [schnell] prompting guideFLUX.2 [klein] 4B editing guide
Models

How to choose an AI image model

Which AI image model to use on Artgen — text-to-image vs image editing, and how FLUX.1 [schnell] and FLUX.2 [klein] 4B compare.

Which AI image model should you use? On Artgen you pick the model behind each AI image. Fixed effects (pixel, ASCII and the print effects) don't use a model at all — this page is only about AI create and AI reimagine.

First question: do you start from text or from an image?

  • Text only → any model that lists Text to image.
  • You want to change an uploaded image → you need a model that lists Image to image. Text-only models won't appear as an option for edits.

Models covered in these guides

ModelDeveloperText to imageImage to imageGood starting useGuide
FLUX.1 [schnell]Black Forest LabsYesNoQuick ideas and style exploration from a promptGuide · Model page
FLUX.2 [klein] 4BBlack Forest LabsYesYesPrompts and edits of your own imageGuide · Model page

Check the model's page and the studio for its current availability and capabilities. Credit cost differs by model — the studio shows it before you generate; plans are on Pricing.

A simple workflow

  1. Explore a prompt quickly with a text-to-image model.
  2. When you have a direction, keep the same prompt and try the other model to compare.
  3. If you need to change a specific photo or reference, switch to a model with image-to-image and use Convert → AI reimagine.

Check the model's own page for what it supports. Results vary by model and prompt — download the ones you want to keep, since studio history is session-only.

Related

  • AI style tools: prompt patterns
  • Generation failed

Artgen API Reference

Authenticate with a dashboard API key and call Artgen from your server — models, styles, create, and convert.

FLUX.1 [schnell] prompting guide

How to prompt FLUX.1 [schnell] on Artgen — prompt structure, example prompts, settings and what it can't do (no image editing).

On this page

First question: do you start from text or from an image?Models covered in these guidesA simple workflowRelated