README.md

metadata

license: wtfpl
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
  - flux
  - flowmatch
  - stationthis
widget:
  - text: >-
      supernal, This is a digital drawing in a manga style, featuring a large,
      blue and yellow robotic creature with shark-like features, including a
      pointed snout and red eyes. The creature's body is segmented and
      mechanical, with visible gears and cables. The background showcases a
      detailed, intricate mechanical structure, filled with gears and pipes,
      resembling a futuristic spaceship or industrial complex. The left side of
      the image has a vertical black and pink text block with stylized letters,
      and a smaller black and white inset at the bottom left corner. The overall
      color palette includes shades of blue, yellow, red, and gray.
    output:
      url: samples/sample_000.jpg
instance_prompt: supernal
training_steps: 4000
network_type: lora
library_name: ai-toolkit

supernal

This LoRA model generates digital drawings in a manga style, depicting large robotic creatures with distinctive shark-like features, such as pointed snouts and red eyes. The artworks feature segmented, mechanical bodies adorned with visible gears and cables, set against intricately detailed mechanical backgrounds.

Trigger word: supernal

Sample Outputs

supernal, This is a digital drawing in a manga style, featur...	supernal, This is a digitally-created, hyper-realistic close...
supernal, This is a highly detailed, digital illustration in...	supernal, This digital artwork depicts a towering, armored w...

Usage

ComfyUI

1. Download the .safetensors file from the Files tab
2. Place in ComfyUI/models/loras/
3. Use the Load LoRA node with strength 0.8-1.0
4. Include supernal in your prompt

Diffusers

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    torch_dtype=torch.bfloat16
)
pipe.load_lora_weights("ms2stationthis/supernal")
pipe.to("cuda")

image = pipe(
    prompt="supernal portrait, soft lighting, detailed",
    guidance_scale=3.5-4.0,
    num_inference_steps=20-30,
    generator=torch.Generator("cuda").manual_seed(42)
).images[0]

image.save("output.png")

Recommended Settings

Parameter	Value
LoRA Strength	0.8-1.0
Guidance Scale	3.5-4.0
Inference Steps	20-30
Resolution	1024x1024

Example Prompts

• supernal this is a digital drawing in a manga style
• supernal featuring a large
• supernal intricate mechanical structure
• supernal filled with gears and pipes

Training Details

• Base model: black-forest-labs/FLUX.1-dev
• Training steps: 4000
• Trigger word: supernal
• Network: LoRA rank 32, alpha 32
• Optimizer: adamw8bit, lr 1e-4
• Precision: float16
• Resolution: 512, 768, 1024 (multi-res bucketed)

About

Trained using StationThis — an AI creative platform powered by $MS2. Train your own LoRAs via @stationthisbot on Telegram.

---

_{Generated by StationThis Training Pipeline}