Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
Overbill1683
Stable Diffusion Webui
提交
c89b1a6f
S
Stable Diffusion Webui
项目概览
Overbill1683
/
Stable Diffusion Webui
10 个月 前同步成功
通知
1744
Star
81
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
分析
仓库
DevOps
项目成员
Pages
S
Stable Diffusion Webui
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Pages
分析
分析
仓库分析
DevOps
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
提交
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
未验证
提交
c89b1a6f
编写于
9月 18, 2022
作者:
A
AUTOMATIC1111
提交者:
GitHub
9月 18, 2022
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #643 from melchiar/master
fixed typos in processing.py
上级
5e80c286
f39b2ca0
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
modules/processing.py
modules/processing.py
+1
-1
未找到文件。
modules/processing.py
浏览文件 @
c89b1a6f
...
...
@@ -124,7 +124,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
# if we have multiple seeds, this means we are working with batch size>1; this then
# enables the generation of additional tensors with noise that the sampler will use during its processing.
# Using those pre-gen
rated tensors instead of si
imple torch.randn allows a batch with seeds [100, 101] to
# Using those pre-gen
erated tensors instead of s
imple torch.randn allows a batch with seeds [100, 101] to
# produce the same images as with two batches [100], [101].
if
p
is
not
None
and
p
.
sampler
is
not
None
and
len
(
seeds
)
>
1
and
opts
.
enable_batch_seeds
:
sampler_noises
=
[[]
for
_
in
range
(
p
.
sampler
.
number_of_needed_noises
(
p
))]
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录