aleksa-codes / flux-ghibsky-illustration

Flux LoRA, use 'GHIBSKY style' to trigger generation, creates serene and enchanting landscapes with vibrant, surreal skies and intricate, Ghibli-inspired elements reminiscent of the atmospheric beauty found in Makoto Shinkai's works

  • Public
  • 49.9K runs
  • Weights
Run with an API
Playground API Examples README Versions

Description

The Flux Ghibsky Illustration model generates landscapes that blend serene, surreal skies with intricate, Ghibli-inspired details. This fusion of styles creates enchanting scenes that capture the essence of both Ghibli’s whimsical charm and Makoto Shinkai’s atmospheric beauty. Perfect for creating dreamy visuals. Feedback is welcome!

Trigger Words

Use GHIBSKY style to trigger the model’s unique aesthetic. Start your prompt with the trigger word, followed by a description of your scene’s elements, such as nature, skies, houses, roads, villages, etc.

If you are getting too realistic images try adding painting to your prompt, for example: GHIBSKY style painting

Training Details (a9f94946)

  • Trained Using: ostris/flux-dev-lora-trainer
  • Number of Images: 35
  • Trigger Word: GHIBSKY
  • Auto-captioning: Enabled
  • Auto-captioning Prefix: “”
  • Auto-captioning Suffix: “, GHIBSKY style”
  • Training Steps: 1000
  • Learning Rate: 0.0004
  • Batch Size: 1
  • LoRA Rank: 16

Hugging Face

If you are training your own LoRA model and want a replacement for LLaVA auto captioning that some of the LoRA training apps use, you can try an open-source tool that I made GPT Image Captioner, a tool designed to generate AI-powered captions for images. This tool simplifies the auto-captioning process, providing a downloadable zip file with captions formatted for training pipelines. It is compatible with tools such as fal LoRA Trainer and Replicate LoRA Trainer, enabling seamless integration into workflows. Users are required to bring their own OpenAI API key for usage.