DreamBooth - Liyulingyue/Neolle_Face_Generator
本仓库的权重是基于 Linaqruf/anything-v3.0 训练而来的,我们采用DreamBooth的技术并使用a photo of Neolle
文本进行了训练。
用于微调的图片共10张,均为原神角色诺艾尔,batch_size取1,学习率是5e-6,共训练1000步。
一些提示词示例 - Some prompt examples
- Noelle with glasses
- Noelle with sunglasses
- Noelle with dark hair, beautiful eyes
- Noelle, 20 years old
- Noelle playing basketball
- Noelle with cat ears, blue hair
生成图片展示 - Generated Images
使用方法 - How to use it
# In any Jupyter Enviroment
! git lfs install
! git clone https://huggingface.co./Liyulingyue/Neolle_Face_Generator
! pip install -U paddlepaddle paddlenlp ppdiffusers visualdl safetensors --user
from ppdiffusers import StableDiffusionPipeline
# 加载模型
model_path = "Neolle_Face_Generator"
pipe = StableDiffusionPipeline.from_pretrained(model_path)
# 提示词,生成一个带猫耳,绿色头发的诺艾尔
prompt = "Noelle with cat ears, green hair"
# 生成
image = pipe(prompt, num_inference_steps=50,guidance_scale=10).images[0]
# 保存
image.save("test.jpg")
# 展示图片
image.show()
更多示例以及一件运行+生成 - More information
Model tree for Liyulingyue/Neolle_Face_Generator
Base model
Linaqruf/anything-v3.0