Comments (14)
额。。。。能讲中文啊?憋了半天的洋文。 跟新了一下插件,并且也装了ControlNet,但是使用正常的 文生图功能出不来图, 后台有报错。卸载sd-webui-segment-anything 后回复正常。
from sd-webui-segment-anything.
from sd-webui-segment-anything.
应该是gradio的bug,我之前碰到过,后来想了点办法给解决了,现在可能不知道是哪儿又出现了这个毛病。能不能麻烦你把你出现这个毛病的详细过程描述一下,最好把图片也发发,方便我复现。
from sd-webui-segment-anything.
同样的报错,辛苦了
from sd-webui-segment-anything.
@491331952 @zhongnannk 你们得把你们的图片和操作过程说明一下我才能复现,不然我没办法帮你们debug
from sd-webui-segment-anything.
I can confirm I am also having this issue.
The steps I took to produce it were:
- Install
Segment Anything
via the URL in theExtensions
tab. - Download the
SAM
models and place them into the appropriate directory. - Enter the
txt2img
tab and type in a term. In my case, I just wrotecheese
. - Hit run.
- No image generates and in the console I receive the following error:
Traceback (most recent call last):
File "/home/[user]/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 394, in run_predict
output = await app.get_blocks().process_api(
File "/home/[user]/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1073, in process_api
inputs = self.preprocess_data(fn_index, inputs, state)
File "/home/[user]/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 962, in preprocess_data
processed_input.append(block.preprocess(inputs[i]))
File "/home/[user]/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/components.py", line 1203, in preprocess
return self.choices.index(x)
ValueError: '0' is not in list
This is the only information available. If there's a way to get more information - such as the exact dropdown or field that is erroneous - then let me know and I'll give it a go. Thanks!
from sd-webui-segment-anything.
Thank you very much. It is much more helpful if you can provide information. Could I say that you actually did not use this extension, but only installed, but is unable to do ordinary txt2img without any extension enabled?
from sd-webui-segment-anything.
Yes, I did not use the extension, simply having it installed causes this issue. I actually removed all of my extensions then added them back individually, confirming that simply the presence of this extension causes the issue. I have gone through all of the configuration menus and changed whatever I can to ensure everything has a default or updated value, with no success. So the extension is not able to do ordinary txt2img unless it is completely removed from the extensions
directory.
from sd-webui-segment-anything.
It seems that gradio is having some very wierd behavior. Is your webui and the extension the most up-to-date? Please update your webui and extension and re-try. If it does no help, I will do some urgent fix to bypass some gradio bugs.
from sd-webui-segment-anything.
OK I know the problem. Did you install ControlNet? If no, the problem comes from this. I'll try to fix this problem.
from sd-webui-segment-anything.
I have fixed the problem. Please re-try and let me know if it is working.
from sd-webui-segment-anything.
Hey, yes, ControlNet is installed. I just git pull
ed your latest commit and it is now working as expected. Unless @491331952 continues to have issues after pulling the latest changes then I believe this issue to be solved. Thank you!
from sd-webui-segment-anything.
@DevJake @continue-revolution I test it,the problem has been fixed!Thanks。
点赞点赞!
from sd-webui-segment-anything.
from sd-webui-segment-anything.
Related Issues (20)
- [Feature]: Activate LOW VRAM on Segment Anything.
- 请教下sam_dummy_component这个当做前后端传值的组件,大概的原理是怎样的 HOT 1
- [Documentation]: workflow for edit anything's cross image region merge
- [Bug]: not an issue question on densepose HOT 1
- How to see all of my inpaint models? HOT 1
- [Feature]: Payload help required for sam/controlnet-seg endpoint
- [Feature]: DAAM cross-attention analysis to get an SD model's understanding of a detection prompt
- Sam model not found.
- [Feature]: 'GroundingDINO_ HOT 1
- [Bug]: What is https://star-history.com ? HOT 1
- [Feature]: SAM支持负面prompt吗 HOT 1
- How to obtain the execution progress of the current task through API
- [Feature]: Please take a look at InpaintAnything. HOT 4
- 请问如何更改分割后区域图片的颜色 HOT 2
- [Bug]: 我已经把模型放到对应目录里面了,运行的时候还是会去下载安装。 HOT 1
- [Bug]: 怎样屏蔽代码里自动下载models--bert-base-uncased? HOT 3
- [Bug]: Model not working well in COLAB
- [Feature]: sam api
- [Bug]: RuntimeError: CUDA error: an illegal memory access was encountered HOT 3
- [Feature]: Support for/Integration with Forge UI HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sd-webui-segment-anything.