Stable diffusion 3.5本地运行环境配置记录

1.环境配置

  • 创建虚环境

    bash 复制代码
    conda create -n sd3.5 python=3.10
  • Pytorch(>2.0)

    bash 复制代码
    conda install pytorch==2.2.2 torchvision==0.17.2 torchaudio==2.2.2 pytorch-cuda=12.1 -c pytorch -c nvidia
  • Jupyter能使用Anaconda虚环境

    bash 复制代码
    conda install ipykernel
    python -m ipykernel install --user --name sd3.5 --display-name "SD3.5"
  • 安装transformer和tokenizer

    bash 复制代码
    pip install transformers==4.38.2 
    pip install tokenizers==0.15.2
  • 安装最新版本的diffuser

    复制代码
    pip install -U diffusers
  • 安装量化库节约VRAM GPUs

    bash 复制代码
    pip install bitsandbytes
  • 安装sentencepiece

    bash 复制代码
    pip install sentencepiece
  • 根据项目需要安装其他库

    bash 复制代码
    pip install matplotlib
    pip install numpy==1.26.4    # 降级,否则有些时候会报错
    pip install accelerate
    pip install protobuf==3.19.0

    2.报错解决

如果报错:Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 960 column 3

降级解决

复制代码
pip install transformers==4.38.2
pip install tokenizers==0.15.2

如果报错ValueError: Cannot instantiate this tokenizer from a slow version. If it's based on sentencepiece, make sure you have sentencepiece installed.

安装sentencepiece:

bash 复制代码
pip install sentencepiece

如果报错:ValueError: The current PyTorch version does not support the scaled_dot_product_attention function.

解决:安装高于Pytorch>2.0

如果报错:T5Converter requires the protobuf library but it was not found in your environment. Checkout the instructions on the

解决:

bash 复制代码
pip install protobuf==3.19.0

3.实测

  • 官网例子:
python 复制代码
local_path = "/home/aic/diffusion_models/stable-diffusion-3.5-large/"
pipe = StableDiffusion3Pipeline.from_pretrained(local_path, torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")

image = pipe(
    "A capybara holding a sign that reads Hello World",
    num_inference_steps=28,
    guidance_scale=3.5,
).images[0]
image.save("capybara.png")
  • 自定义例子

    "一名古代风格的中国女学生坐在现代的计算机教室里面学习编程"

    prompts:"An ancient-style Chinese female student sitting in a modern computer classroom learning programming, focused eyes, traditional Hanfu attire, modern technology, code editor, keyboard, mouse, fusion of digital age and traditional aesthetics, rich in detail, high-definition quality."

python 复制代码
prompts="An ancient-style Chinese female student sitting in a modern computer classroom learning programming, focused eyes, traditional Hanfu attire, modern technology, code editor, keyboard, mouse, fusion of digital age and traditional aesthetics, rich in detail, high-definition quality."
image = pipe(
    prompt=prompt,
    num_inference_steps=28,
    guidance_scale=4.5,
    max_sequence_length=512,
).images[0]

image.save("girls.png")
plt.imshow(plt.imread("girls.png"))
plt.axis('off')  # 不显示坐标轴
display(plt.gcf())
相关推荐
爱分享的飘哥13 小时前
第三十七章:文生图的炼金术:Stable Diffusion完整工作流深度解析
人工智能·pytorch·stable diffusion·文生图·ai绘画·代码实战·cfg
EndingCoder3 天前
Three.js + AI:结合 Stable Diffusion 生成纹理贴图
开发语言·前端·javascript·人工智能·stable diffusion·ecmascript·three.js
那年一路北3 天前
Deforum Stable Diffusion,轻松实现AI视频生成自由!
人工智能·stable diffusion·音视频
全宝4 天前
🎨【AI绘画实战】从零搭建Stable Diffusion环境,手把手教你生成超可爱Q版大头照!
人工智能·python·stable diffusion
sculida9 天前
秋叶sd-webui频繁出现生成后无反应的问题
stable diffusion
HORSE RUNNING WILD13 天前
【物理与机器学习】从非平衡热力学到扩散模型
人工智能·学习·机器学习·stable diffusion
取不好名字=14 天前
【ComfyUI学习笔记01】下载安装 | 运行第一个工作流 | 学习思路
笔记·学习·ai作画·stable diffusion
qq_3988989325 天前
【简单三步】Stable diffusion Webai本地部署无法加载模型并报openai/clip-vit-large-patch14错误的解决方法
stable diffusion
ai_xiaogui25 天前
AIStarter用户与创作者模式详解:一键管理Stable Diffusion项目!
人工智能·stable diffusion·一键发布ai项目·熊哥aistarter教程·开发者必备aistarter
一禅(OneZen)1 个月前
「Windows/Mac OS」AIGC图片生成视频 ,webui + stable-diffusion环境部署教程
windows·stable diffusion