---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: 7-cgifaces, portrait, woman, accurate eye proportions
  parameters:
    negative_prompt: >-
      watermark, error, blurry, jpeg artifacts, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      artist name, (worst quality, low quality:1.4), bad anatomy, watermark,
      signature, text, logo, nsfw, nipples, negativeV2,
  output:
    url: images/ComfyUI_02952_.png
- text: >-
    [7-cgifaces], woman medium close up, cloaked, medieval attire, reflection's,
    coat, portrait   
  parameters:
    negative_prompt: >-
      watermark, error, blurry, jpeg artifacts, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      artist name, (worst quality, low quality:1.4), bad anatomy, watermark,
      signature, text, logo, nsfw, nipples, negativeV2,
  output:
    url: images/ComfyUI_02985_.png
- text: '[7-cgifaces], portrait, cyberpunk, synth wave, girl, helmet'
  parameters:
    negative_prompt: >-
      watermark, error, blurry, jpeg artifacts, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      artist name, (worst quality, low quality:1.4), bad anatomy, watermark,
      signature, text, logo, nsfw, nipples, negativeV2,
  output:
    url: images/ComfyUI_02965_.png
- text: >-
    [7-cgifaces], soldier, close up on face, portrait, dirt, mud, explosions,
    embers, dramatic, god rays, reflections, lighting
  parameters:
    negative_prompt: >-
      watermark, error, blurry, jpeg artifacts, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      artist name, (worst quality, low quality:1.4), bad anatomy, watermark,
      signature, text, logo, nsfw, nipples, negativeV2,
  output:
    url: images/ComfyUI_02970_.png
- text: '-'
  output:
    url: images/face compare.jpeg
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: 7-cgifaces
license: cc-by-3.0
---
# Rendered-Face-Detailer-SDXL

<Gallery />

## Model description 

This model is trained on 150 3D modelled faces. This model aims to increase the detail on the face in a hyper realistic way. The images were retrieved from art station so big shoutout for the amazing creators on that platform.

GPT4V was used to caption the dataset, this is my first time using it and it seems to give great results.

I&#39;ve found if the strength is too high the eyes won&#39;t align very well. A strength of 0.8 seems to work effectively.

This model is quite experimental so if you have any feedback I&#39;d love to hear it.

[CivitAI Source](https:&#x2F;&#x2F;civitai.com&#x2F;models&#x2F;600119&#x2F;rendered-face-detailer-sdxl)

Author: Cooper7trooper

## Trigger words

You should use `7-cgifaces` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/Omarito2412/Rendered-Face-Detailer-SDXL/tree/main) them in the Files & versions tab.