本地搭建NovelAi (免费的色图生成器,可用colab在线运行)
-
@954386273 额,那你就手动执行一下那个命令试试呗。
git -C repositories\CodeFormer checkout c5b4593074ba6214284d6acd5f1719b6c5d739af
-
@Colter23
Downloading: 100%|███████████████████████████████████████████████████████████████| 1.59G/1.59G [1:06:18<00:00, 430kB/s]
Loading weights [e6e8e1fc] from E:\Git here\stable-diffusion-webui\models\Stable-diffusion\model.ckpt
Error verifying pickled file from E:\Git here\stable-diffusion-webui\models\Stable-diffusion\model.ckpt:
Traceback (most recent call last):
File "E:\Git here\stable-diffusion-webui\modules\safe.py", line 97, in load
check_pt(filename)
File "E:\Git here\stable-diffusion-webui\modules\safe.py", line 81, in check_pt
unpickler.load()
File "E:\Git here\stable-diffusion-webui\venv\lib\site-packages\torch_utils.py", line 138, in _rebuild_tensor_v2
tensor = _rebuild_tensor(storage, storage_offset, size, stride)
File "E:\Git here\stable-diffusion-webui\venv\lib\site-packages\torch_utils.py", line 134, in rebuild_tensor
return t.set(storage._untyped(), storage_offset, size, stride)
RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:81] data. DefaultCPUAllocator: not enough memory: you tried to allocate 3932160 bytes.The file may be malicious, so the program is not going to read it.
You can skip this check with --disable-safe-unpickle commandline argument.
现在来到这个进度了,想问下这个--disable-safe-unpickle应该加到哪个指令的后面? -
@Colter23
这个报错还有下面一截
Traceback (most recent call last):
File "E:\Git here\stable-diffusion-webui\launch.py", line 171, in <module>
start_webui()
File "E:\Git here\stable-diffusion-webui\launch.py", line 166, in start_webui
webui.webui()
File "E:\Git here\stable-diffusion-webui\webui.py", line 92, in webui
initialize()
File "E:\Git here\stable-diffusion-webui\webui.py", line 85, in initialize
shared.sd_model = modules.sd_models.load_model()
File "E:\Git here\stable-diffusion-webui\modules\sd_models.py", line 190, in load_model
load_model_weights(sd_model, checkpoint_info)
File "E:\Git here\stable-diffusion-webui\modules\sd_models.py", line 140, in load_model_weights
if "global_step" in pl_sd:
TypeError: argument of type 'NoneType' is not iterable -
@954386273
webui-user.bat
里的COMMANDLINE_ARGS=
后面 -
@loveriswmy 大佬还是这个问题,更新安装依赖也没用
-
大佬,请问这个是怎么回事啊,我git已经给了账号信息了,不过git安装在其他路径的,不知道有没有影响
-
你们要是实在不会弄,就直接去b找那种一键安装包吧(
-
@Colter23 好吧,谢谢你
-
@Colter23 大佬再麻烦你一下,请问下载的依赖还是环境什么的怎么删除啊,占了c盘大概20g
-
@braverookie C:\Users\你的用户名\.cache
-
3070 win10, 一般都可以正常使用
但是若其中一種prompt(正或負)數量大於27的話就會報錯Traceback (most recent call last):
File "E:\stable-diffusion-webui-master\modules\sd_samplers.py", line 199, in sample
samples_ddim, _ = self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)
File "E:\stable-diffusion-webui-master\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "E:\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\models\diffusion\ddim.py", line 96, in sample
samples, intermediates = self.ddim_sampling(conditioning, size,
File "E:\stable-diffusion-webui-master\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "E:\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\models\diffusion\ddim.py", line 149, in ddim_sampling
outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
File "E:\stable-diffusion-webui-master\modules\sd_samplers.py", line 149, in p_sample_ddim_hook
res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs)
File "E:\stable-diffusion-webui-master\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "E:\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\models\diffusion\ddim.py", line 176, in p_sample_ddim
c_in = torch.cat([unconditional_conditioning, c])
RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 77 but got size 82 for tensor number 1 in the list.用Euler a 或 ddim都會出現
降低steps也無解稍微查了一下都沒有遇到類似案例 請問大老有解嗎 謝謝
-
大佬,请问“No matching distribution found for transformers==4.19.2”有解决办法吗?运行了“pip install -i https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple transformers==4.19.2”后仍然报相同错误
-
@Jaskier 要用它环境自带的pip安装。
项目目录/venv/Scripts/pip.exe
-
@ArareF 解决了吗
-
@zclstc 检测不到显卡的问题,装了个win10解决了
-
@Colter23 成功了,感谢大佬!
-
請問一下大小模型的config具體來說由何區別呢?
-
pip升级问题解决了,指的是在c盘里面的pip通过系统cmd指令更新了,但是我c盘内存爆炸了,尝试安装在其他盘,但是他里面的pip如何更新,头疼,求助了~
-
@Colter23 在 本地搭建NovelAi (免费的色图生成器,可用colab在线运行) 中说:
--precision full --no-half
-
大佬,怎么不让别人使用这个功能啊