README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
    url: images/s18.JPG
  text: >-
    Smnth_v1, 1girl, woman, topless, nude, breasts, navel, stomach, slim waist,
    front view, arms raised, arms above head, standing, long dark hair, indoor,
    white wall, simple background, soft lighting, dewy skin, highres, cinematic
    lighting, sharp focus, real photo style.
  parameters:
    negative_prompt: >-
      (deformed iris, deformed pupils), text, watermark, logo, signature, low
      quality, worst quality, blurry, grainy, low resolution, (plastic skin,
      fake skin, airbrushed), (cartoon, anime, 3d, render, illustration),
      (deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong
      anatomy, extra limb, missing limb, floating limbs, (mutated hands and
      fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry,
      amputation.
base_model: Tongyi-MAI/Z-Image-Turbo
instance_prompt: Smnth_v1
license: openrail
---
# Smnth v1 - Z-Image Anatomical Detail LoRA

<Gallery />

## Model description 

This LoRA is trained on the Z-Image De-Turbo architecture to improve anatomical precision and skin textures for the character&#x2F;concept Smnth_v1.

## Trigger words

You should use `Smnth_v1` to trigger the image generation.


## Download model


[Download](/ReCodePlus/Smnth_v1_NSFW1/tree/main) them in the Files & versions tab.