aleksa-codes/flux-ghibsky-illustration

Flux Ghibsky Illustration: Create Serene and Enchanting Landscapes

Prompt

GHIBSKY style, a cat on a windowsill gazing out at a starry night sky and distant city lights

Prompt

GHIBSKY style, a fisherman casting a line into a peaceful village lake surrounded by quaint cottages

Prompt

GHIBSKY style, cozy mountain cabin covered in snow, with smoke curling from the chimney and a warm, inviting light spilling through the windows

Prompt

GHIBSKY style, Mykonos

Prompt

GHIBSKY style, an orange Lamborghini driving down a hill road at night with a beautiful ocean view in the background, side view, no text

Prompt

GHIBSKY style, a small Yorkie on a windowsill during a snowy winter night, with a warm, cozy glow from inside and soft snowflakes drifting outside

Prompt

GHIBSKY style, serene Japanese garden with a koi pond and a traditional tea house, nestled under a canopy of cherry blossoms in full bloom

Prompt

GHIBSKY style, the most beautiful place in the universe

Prompt

GHIBSKY style painting, sign saying "Flux Ghibsky"

Model 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. You can also run the model on Replicate. Feedback is welcome!

Replicate Model Page

Trigger Words

Use GHIBSKY style to invoke the model’s unique aesthetic. It’s best to start your prompt with the trigger word, followed by descriptions of your scene, 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

• Trained Using: Flux LoRA Fast Training on fal.ai and Flux LoRA Trainer on Replicate
• 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

Download Model

Download the *.safetensors LoRA in the Files & versions tab.

Related Tools

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.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('aleksa-codes/flux-ghibsky-illustration', weight_name='lora.safetensors')
image = pipeline('GHIBSKY style, a serene lakeside village with colorful houses and towering mountains under a dreamy sky').images[0]

For more details, including weighting, merging, and fusing LoRAs, check the documentation on loading LoRAs in diffusers.

License

Please adhere to the licensing terms as described here.