---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
    Score_9, Score_8_up, Score_7_up,two young women seated on a couch in a
    well-furnished room. Both are wearing skirts and have long hair. The woman
    on the left is wearing a grey dress with a V-neck, while the woman on the
    right is dressed in a beige blouse with a V-neck. Both are wearing high
    heels. The room has a modern design with a window that offers a view of a
    cityscape. The woman on the left has brown hair and is wearing earrings,
    while the woman on the right has black hair. Both are looking directly at
    the viewer.
  parameters:
    negative_prompt: score_4,score_3,score_2,score_1,ugly,bad hands,bad foot,bad_hands,
  output:
    url: images/img1.jpeg
base_model: LyliaEngine/Pony_Diffusion_V6_XL
instance_prompt: null
license: apache-2.0
---
# white_v20

<Gallery />

## Model description 

This is a checkpoint trained on Pony Diffusion V6 XL as a base, which possesses realistic painting abilities that Pony currently does not possess. I have made specialization on semantics and images that cater to the preferences of Chinese people (because I am also) The training data consists of approximately 20000 high-quality images and provides very accurate image annotation The total number of training steps is 10000000, and currently there are checkpoints open for 5000000 steps The training equipment is 4*4090 Please control clipskip to 2 Please use Pony&#39;s exclusive quality words for optimal results For example: score_9, score_8, score_7


## Download model

Weights for this model are available in Safetensors format.

[Download](/tnlight/white_v20/tree/main) them in the Files & versions tab.