hffinal_miladyii_30

This LoRA fine-tunes FLUX.1-dev for custom image generation. Use the trigger word miladyii in your prompts to activate the trained style. Trained using the StationThis pipeline.

Trigger word: miladyii

Sample Outputs

This digital anime-style drawing features a chibi character ...	This is a digital anime-style drawing of a young girl, known...
This is a digital drawing of a chibi-style anime character w...	This is a digital drawing in a chibi anime style featuring a...

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 miladyii 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/hffinal_miladyii_30")
pipe.to("cuda")

image = pipe(
    prompt="miladyii 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

• miladyii teary black eyes
• miladyii pale skin
• miladyii and long
• miladyii gentle smile. at the bottom of the image

Training Details

• Base model: black-forest-labs/FLUX.1-dev
• Training steps: 30
• Trigger word: miladyii
• Resolution: 512, 768, 1024 (multi-res)
• Network: LoRA rank 16

About

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

---

_{Generated by StationThis Training Pipeline}