This repository contains the LoRA adapter for FLUX.1-Krea [dev], fine-tuned using https://fal.ai/models/fal-ai/flux-krea-trainer with curated Solarpunk-style images. This LoRA excels at creating solarpunk imagintations of real world cities in a dreamy style! I personally feel it performs better than midjourney and any other text-to-image model 👀

The dataset was assembled for the Solarpunk Art Contest 2025 by Yishan, featuring a wide range of environments, architecture, and character scenes inspired by solarpunk aesthetics.

You should use the following template (defined when annotating the images with captions) to trigger solarpunk image generation:

"Solarpunk [city or setting] with [distinctive future-tech feature], [architecture or landmark (unchanged if historic)], [greenery and fruiting trees/flowers], [people or activity], [lighting or atmosphere], [additional details]"

You should use [SLRPNK] to trigger the image generation.

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Training was done using fal.ai/models/fal-ai/flux-krea-trainer.