Diffusers代码学习：SDXLTextual inversion

Stable Diffusion XL（SDXL）也可以使用Textual inversion向量进行推理。与Stable Diffusion 1和2相比，SDXL有两个文本编码器，因此需要两个Textual inversion嵌入-每个文本编码器模型一个。

import os
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
rom huggingface_hub import hf_hub_download
from safetensors.torch import load_file

file = hf_hub_download("dn118/unaestheticXL", filename="unaestheticXLv31.safetensors")
state_dict = load_file(file)

from diffusers import AutoPipelineForText2Image
import torch

pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", variant="fp16", torch_dtype=torch.float16)
pipe.to("cuda")

pipe.load_textual_inversion(state_dict["clip_g"], token="unaestheticXLv31", text_encoder=pipe.text_encoder_2, tokenizer=pipe.tokenizer_2)
pipe.load_textual_inversion(state_dict["clip_l"], token="unaestheticXLv31", text_encoder=pipe.text_encoder, tokenizer=pipe.tokenizer)

# the embedding should be used as a negative embedding, so we pass it as a negative prompt
generator = torch.Generator().manual_seed(33)
image = pipe("a woman standing in front of a mountain", negative_prompt="unaestheticXLv31", generator=generator).images[0]

image.show()