InvokeAI
InvokeAI copied to clipboard
[bug]: Killed while loading 1.5
Is there an existing issue for this?
- [X] I have searched the existing issues
OS
Linux
GPU
cpu
VRAM
No response
What happened?
It says 'Killed' when I try to run invoke.py --web as seen below
(invokeai) lunkwill@Will-of-Lunk:~/Programs/stable-invoke/invokeAI$ python scripts/invoke.py --web
- Initializing, be patient...
Initialization file /home/lunkwill/.invokeai found. Loading... InvokeAI runtime directory is "/home/lunkwill/invokeai" Patchmatch initialized GFPGAN Initialized CodeFormer Initialized ESRGAN Initialized Using device_type cuda Current VRAM usage: 0.00G Scanning Model: stable-diffusion-1.5 Model Scanned. OK!! Loading stable-diffusion-1.5 from /home/lunkwill/invokeai/models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt | LatentDiffusion: Running in eps-prediction mode | DiffusionWrapper has 859.52 M params. | Making attention of type 'vanilla' with 512 in_channels | Working with z of shape (1, 4, 32, 32) = 4096 dimensions. | Making attention of type 'vanilla' with 512 in_channels Killed
Screenshots
No response
Additional context
I have 16g normal RAM and this is my GPU: Intel Corporation CometLake-U GT2 the laptop in an ASUS ZenBook running Ubuntu 22.04
Contact Details
No response
I now have the same issue on Ubuntu 22.04, with an rtx 3060.
Using device_type cuda Current VRAM usage: 0.00G Scanning Model: stable-diffusion-1.5 Model Scanned. OK!! Loading stable-diffusion-1.5 from /media/iwoolf/BigDrive/Stable-diffusion/models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt Terminated
I'm also getting this error while loading either 1.4 or 1.5. I haven't yet tried any other models. Same console output as OP.
I am running on Ubuntu 20.04 on WSL, 16GB memory. Nvidia-smi correctly shows my rtx 3070.
There has been no activity in this issue for 14 days. If this issue is still being experienced, please reply with an updated confirmation that the issue is still being experienced with the latest release.