Title: spec_gurl-v1 – Realistic Woman with Glasses [Close-up Character LoRA]

Description:

spec_gurl-v1 is a realistic LoRA character trained on a carefully curated dataset of women wearing glasses. This LoRA is ideal for generating high-quality portraits and close-up shots of a female character who consistently features glasses as a defining trait.

Perfect for cinematic renders, social-style photos, and expressive character studies, this LoRA preserves facial structure, skin detail, and lens reflections across multiple angles.

📌 Details:

• Trigger word: spec_gurl

• Model Base: SD1.5 (runwayml/stable-diffusion-v1-5)

• Clip Skip: 2

• Resolution: Trained with mixed resolutions (512x512, 576x512, ??0x512)

  • Supports bucketed resolutions up to 512x768 and beyond

• Training:

  • 102 images

  • 10 batch size

  • 10 epochs

  • 110 steps

  • Trained using Kohya LoRA (networks.lora)

• File Size: 72MB

• Hash: 89ed443e37f0

🧪 Recommended Usage:

• Prompt:
  spec_gurl <lora:spec_gurl-v1:0.95>, close-up, glasses, ultra-detailed face, natural lighting, bokeh background
  Pair with <lora:add_detail:1.8> for enhanced realism.

• Recommended LoRA weight: 0.6 – 1.0

• Best With:

  • add_detail, epi_noiseoffset, clearVAE, easynegative

  • Realistic base models like CyberRealistic, RealisticVision, or your custom blends

• Notes:

  • Works best in portrait or half-body framing

  • Facial features remain consistent even at high-res

  • Character identity focuses on a realistic woman who always wears glasses

🏷️ Suggested Tags:

realistic, portrait, female, glasses, woman, photo, photorealistic, character, close-up, lora, sd1.5, cinematic, detail, kohya, clip-skip-2, curated-dataset, 512x768, multi-angle, bucket-train