Intent:

Provide a clean reference implementation for Flux.2 Klein text-to-image generation.

This workflow focuses on simplicity,reproducibility, and education rather than including every available feature.

----------------------------------------------------

Version 1.0

Created as a simple reference workflow for users getting started with Flux.2 Klein.

If using non-gguf models, you may need to change the model loaders accordingly. The remainder of the workflow should remain unchanged.

Some models may produce washed-out images at lower resolutions (for example, Dark Beast).

Purpose:

✓ Educational

✓ Minimal

✓ Easy to extend

Verified

✓ Text-to-Image

Verified Settings:

✓ CFG : 7.0

✓ Sampler : Euler

✓ Scheduler : Simple

These settings were used to validate this workflow and are recommended as the baseline configuration.

Recommended Resolution :

✓ 384×640 (Observation - size picker doubles the resolution automatically when combined with Flux.2 Klein model, If you want exact dimensions, use 'Empty Latent Image' node instead)

Hardware Tested:

✓ RTX 2080 (8 GB)

✓ 64 GB System RAM

✓ ComfyUI 0.27.0