Is there a more comprehensive guide on what CLIP models to choose and the recommended HW?
I know that there's some kind of table in https://immich.app/docs/features/searching but I wondered if anyone knows of some other resource that explains the process of changing the model, the pros and cons, wether it's highly recommended tring to enable GPU acceleration (e.g. Cuda or they can run fine on pure CPU), and also wether we should backup something specifically before starting the process.
Seems that
XLM-Roberta-Base-ViT-B-32__laion5b_s13b_b90k outclasses the default ViT-B-32__openia by a fair margin with similar processing time and only more memory consumption.4 Replies
:wave: Hey @cibernox,
Thanks for reaching out to us. Please carefully read this message and follow the recommended actions. This will help us be more effective in our support effort and leave more time for building Immich :immich:.
References
- Container Logs:
docker compose logs docs
- Container Status: docker ps -a docs
- Reverse Proxy: https://immich.app/docs/administration/reverse-proxy
- Code Formatting https://support.discord.com/hc/en-us/articles/210298617-Markdown-Text-101-Chat-Formatting-Bold-Italic-Underline#h_01GY0DAKGXDEHE263BCAYEGFJA
Checklist
I have...
1. :blue_square: verified I'm on the latest release(note that mobile app releases may take some time).
2. :blue_square: read applicable release notes.
3. :blue_square: reviewed the FAQs for known issues.
4. :blue_square: reviewed Github for known issues.
5. :blue_square: tried accessing Immich via local ip (without a custom reverse proxy).
6. :blue_square: uploaded the relevant information (see below).
7. :blue_square: tried an incognito window, disabled extensions, cleared mobile app cache, logged out and back in, different browsers, etc. as applicable
(an item can be marked as "complete" by reacting with the appropriate number)
Information
In order to be able to effectively help you, we need you to provide clear information to show what the problem is. The exact details needed vary per case, but here is a list of things to consider:
- Your docker-compose.yml and .env files.
- Logs from all the containers and their status (see above).
- All the troubleshooting steps you've tried so far.
- Any recent changes you've made to Immich or your system.
- Details about your system (both software/OS and hardware).
- Details about your storage (filesystems, type of disks, output of commands like fdisk -l and df -h).
- The version of the Immich server, mobile app, and other relevant pieces.
- Any other information that you think might be relevant.
Please paste files and logs with proper code formatting, and especially avoid blurry screenshots.
Without the right information we can't work out what the problem is. Help us help you ;)
If this ticket can be closed you can use the /close command, and re-open it later if needed.It's very system specific, so something like what you ask isn't really possible. You kind of need to determine how your system operates and go from there - and what search detail you want available and what an acceptable wait time is
but maybe there was some general guidance like "Don't even try to run
ViT-SO400M unless you have an nvidia RTX card"
to clarify btw, the "Execution Time" in the table on https://immich.app/docs/features/searching is how log it takes to index a photo or how long it takes to find a photo?It’s the time to index a photo + the time to generate an embedding for search on a CPU. It’s mainly intended as a relative comparison between models
There is no model in the catalog that’s too slow for CPU at the moment. A GPU of course makes a big difference in processing time for the larger models, but it’s a nice-to-have rather than a necessity