Comments (8)
How much RAM do you have?
from invokeai.
How much RAM do you have?
16 GB
from invokeai.
Which model is causing the crash? And to confirm, it's RAM and not VRAM that's getting maxed out?
from invokeai.
Which model is causing the crash? And to confirm, it's RAM and not VRAM that's getting maxed out?
Any sdxl model, I was only able to convert one model without this problem, the dreamshaper sdxl turbo, all the others had this problem. And Yes, the problem is the ram not vram, and if I run a sdxl model that its already in diffusers format it can generate imagens without any problems, this only happens when I try to convert from ckpt or safetensors to diffusers. Sd 1.5 can convert without any problems.
from invokeai.
Please let us know a specific model that has the problem so we can attempt to reproduce the issue exactly.
from invokeai.
Please let us know a specific model that has the problem so we can attempt to reproduce the issue exactly.
Some examples are juggernaut xl version X , the normal and the hyper version and kohaku xl episilon. I tried with other models too but these are some.
from invokeai.
Thanks. I've done a brief test with Juggernaut X and can confirm conversion uses an excessive amount of RAM.
I had 12GB free and OOM'd when attempting to convert using the convert button. However, I can generate with the safetensors model, the automatic conversion there works without issue. I suspect there is something in the conversion endpoint that isn't set up correctly. @lstein , can you please take a look?
from invokeai.
Thanks. I've done a brief test with Juggernaut X and can confirm conversion uses an excessive amount of RAM.
I had 12GB free and OOM'd when attempting to convert using the convert button. However, I can generate with the safetensors model, the automatic conversion there works without issue. I suspect there is something in the conversion endpoint that isn't set up correctly. @lstein , can you please take a look?
For me, even when I try to generate without previously converting, the automatic conversion runs out of memory. Therefore, if I use a SafeTensor or a ckpt model, I cannot use SDXL; instead, I need to use a model that is already in the Diffusers format. Every method of converting the model, whether through the model manager or through the automatic conversion, always runs out of memory. And I think there is no way to use a SafeTensor or ckpt model without converting, right? I can use a space on Hugging Face to convert to Diffusers, but this requires a lot of work.
from invokeai.
Related Issues (20)
- [enhancement]: Improve error message when encountering a disk errors
- [bug]: Invert Tensor Mask & Alpha Mask to Tensor Node Errors HOT 2
- [bug]: NOT INSTALL HOT 1
- [enhancement]: Gallery - Double click the thumbnail to open the image in new tab
- [bug]: ERROR - patchmatch failed to load or compile (not enough data: cadata does not contain a certificate (_ssl.c:4020)) HOT 4
- [bug]: Cannot consistently grab bounding box on Brave browser HOT 2
- [bug]: TypeError: a.map is not a function HOT 1
- [bug]: context.tensors.load returns an object that is modifiable in-place HOT 1
- [bug]: UnicodeDecodeError: 'charmap' codec can't decode byte 0x90 in position 7542: character maps to <undefined>
- [enhancement]: In the workflow, want to be able to skip the specified node
- [bug]: TypeError: a.map is not a function HOT 2
- [bug]: the shortcut keys '[' and ']' have dual functions HOT 5
- [bug]: I can't find a way to drag pictures from the gallery into IP-Adapter. HOT 1
- [bug]: Problem installing FLUX VAE from file HOT 2
- [bug]: Error: Minified React error #185; visit https://reactjs.org/docs/error-decoder.html?invariant=185 for the full message or use the non-minified dev environment for full errors and additional helpful warnings. HOT 1
- [bug]: PytorchStreamReader can't find file constants.pkl when trying to load an aDetailer HOT 1
- [enhancement]: Move image from assets to normal image gallery.
- [bug]: Regarding the compatibility issue of pad with stylus. HOT 2
- [enhancement]: Upload image to raster layer HOT 1
- [bug]: RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half' 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 invokeai.