Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Cannot run the colab notebook for version 2.1 #10

Closed
thhung opened this issue Dec 10, 2022 · 13 comments
Closed

Cannot run the colab notebook for version 2.1 #10

thhung opened this issue Dec 10, 2022 · 13 comments

Comments

@thhung
Copy link

thhung commented Dec 10, 2022

I cannot get it run, get the following errors:

Installing requirements for Web UI
Launching Web UI with arguments: --share --force-enable-xformers
Loading config from: /content/stable-diffusion-webui/models/Stable-diffusion/v2-1_768-ema-pruned.yaml
LatentDiffusion: Running in v-prediction mode
DiffusionWrapper has 865.91 M params.
Downloading: 100% 3.94G/3.94G [00:51<00:00, 77.1MB/s]
^C
@camenduru
Copy link
Owner

Probably colab updated some library again I am not on PC I will look at later

@camenduru
Copy link
Owner

it is working now I did nothing 😋

@thhung
Copy link
Author

thhung commented Dec 13, 2022

I still have the same issue. Did you run Colab with high ram mode?

@camenduru
Copy link
Owner

are we talking about same thing right 🤔 https://github.com/camenduru/stable-diffusion-webui-colab/blob/main/stable_diffusion_v2_1_webui_colab.ipynb is working right now

@thhung
Copy link
Author

thhung commented Dec 14, 2022

Yes, we talk about the same thing. When this one loads the model, it consumes more than 12 GB RAM, and Colab supports only 12 GB. Do you have a Pro Colab account?

@camenduru
Copy link
Owner

I am testing with free account please use this command !nvidia-smi and please post here what it returns

Wed Dec 14 21:04:12 2022       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |
| N/A   49C    P0    28W /  70W |      0MiB / 15109MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

@thhung
Copy link
Author

thhung commented Dec 14, 2022

I mean RAM not GPU RAM. Please see in this picture below:
Screenshot 2022-12-14 223028

@thhung
Copy link
Author

thhung commented Dec 14, 2022

I think it is broken on the Auto1111's repo. Normally they have an option for "low ram" but it doesn't work anymore.

@camenduru
Copy link
Owner

please run this command !grep MemTotal /proc/meminfo

Screenshot 2022-12-15 004200

@thhung
Copy link
Author

thhung commented Dec 14, 2022

Interesting, I have the same size of RAM as you. Here is the output:
13297220 kB

@thhung
Copy link
Author

thhung commented Dec 14, 2022

If I run the notebook from your github, no problem. If I run the cloned version of it, it crashes. Interesting bugs right there.

@camenduru
Copy link
Owner

is everything same with this repo

@thhung
Copy link
Author

thhung commented Dec 14, 2022

I tried only with version 2.1. When I have time, I will try with the rest.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants