Stable Diffusion - SDT Hair Lora 1 V1

Stable Diffusion - SDT Hair Lora 1
NOTE: THIS IS NOT AN SDT MOD. THIS IS A LORA DESIGNED TO BE USED WITH STABLE DIFFUSION.

This is a lightweight resize of the Lora I use for generating sdt reference images. For more information and directions please see this thread: https://www.undertow.club/threads/a...erated-mod-content-for-sdt.20558/#post-276610

Model trained on ponyDiffusionV6XL_v6StartWithThisOne and will work with various Pony flavors.





Basic Instructions:
Using web automatic1111
The Loras were trained with 819w and 1024h. Using this size yields best results.
Triggers: sdchan,
Recommended prompts: (white background), upper body OR full body
Put hair instructions last.

Prompt Example:
score_9, score_8_up, score_7_up, [source_anime], <lora:sdt-hair1:0.9> sdchan, 1girl, solo, from side, mouth open, nude, neutral lighting, (full body, (white background)), feet, hands on thigh, <lora:Anime_Screencap:0.35> anime coloring, [[female focus]], breasts, kneeling, (detailed hair), <lora:add-detail-xl:1.1>, long hair, hair ornament, wavy hair

NEGATIVE:
score_5, source_realistic, watermark, censored, blur, (((out of frame:1.3))), expressive lighting, closed mouth, cutoff, cropped, (teeth, tongue), (bad anatomy), huge eyes, looking up, looking down, hair out of frame, washed out, dark, low quality, close-up, deformed, horror, awkward position, [custom nose, custom mouth], (background),

Recommend Parameters:
teps: 24, Sampler: Euler a, Schedule type: Automatic, CFG scale: 7, Seed: 2504589038, Size: 819x1024, Model hash: ac006fdd7e, Model: autismmixSDXL_autismmixConfetti, VAE hash: b8821a5d58, VAE: sdxl_vae.safetensors, Denoising strength: 0.38, Clip skip: 2, Token merging ratio: 0.2, Token merging ratio hr: 0.2,
Hires: 2x, 16 steps, 0.33 to 0.5 denoise. 4x Ultrasharp

Training Information:
Trained on 819x1024 images on white background with 75 images.