【已解决】ModuleNotFoundError: No module named ‘clip‘_modulenotfounderror: no module named 'clip

问题描述

Traceback (most recent call last):
File "scripts/txt2img.py", line 344, in
main()
File "scripts/txt2img.py", line 240, in main
model = load_model_from_config(config, f"{opt.ckpt}")
File "scripts/txt2img.py", line 54, in load_model_from_config
model = instantiate_from_config(config.model)
File "/home/entre/generation/stable-diffusion/ldm/util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "/home/entre/generation/stable-diffusion/ldm/models/diffusion/ddpm.py", line 461, in init
self.instantiate_cond_stage(cond_stage_config)
File "/home/entre/generation/stable-diffusion/ldm/models/diffusion/ddpm.py", line 519, in instantiate_cond_stage
model = instantiate_from_config(config)
File "/home/entre/generation/stable-diffusion/ldm/util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "/home/entre/generation/stable-diffusion/ldm/util.py", line 93, in get_obj_from_str
return getattr(importlib.import_module(module, package=None), cls)
File "/home/entre/anaconda3/envs/ldm/lib/python3.8/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 975, in _find_and_load_unlocked
File "", line 671, in _load_unlocked
File "", line 783, in exec_module
File "", line 219, in _call_with_frames_removed
File "/home/entre/generation/stable-diffusion/ldm/modules/encoders/modules.py", line 4, in
import clip
ModuleNotFoundError: No module named 'clip'

解决办法

        这个还挺好解决的

pip install clip

pip install openai-clip

        感觉上述两个应该是差不多的，反正我是全都pip install了 

        具体关系请看

延伸阅读 

        1.遇到 AttributeError: module 'clip' has no attribute 'load' 或是类似问题，是安装的CLIP 有问题

        2.注意事项 不要直接“pip install clip ” 会出现问题

        

3.在创建的anaconda虚拟环境，包含python版本和pytorch版本 其中python>=3.6，pytorch>=1.7.1示例代码：

conda create -n clip python=3.6
 
conda install --yes -c pytorch pytorch=1.7.1 torchvision cudatoolkit=11.0

4.安装cuda=11.0或11.1版本

        官网下载相应版本的安装包

5 安装相应的依赖包

         

pip install ftfy regex tqdm

6.使用openAI提供的github安装源安装

pip install git+https://github.com/openai/CLIP.git

——————————————
版权声明：本文为CSDN博主「海柱12」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：

安装 跨模态模型CLIP 或是遇到 AttributeError: module ‘clip‘ has no attribute ‘load‘_attributeerror: module 'clip' has no attribute 'lo-CSDN博客文章浏览阅读6.9k次，点赞6次，收藏14次。安装 跨模态模型CLIP 或是遇到 AttributeError: module 'clip' has no attribute 'load'_attributeerror: module 'clip' has no attribute 'loadhttps://blog.csdn.net/qq_39454370/article/details/127587646

完结撒花 

        我们不会比今天更年轻了，这不是我们该有的样子