All apps · 0 apps
immich-machine-learning-rocm
Docker app from rorar's Repository
Overview
Readme
View on GitHub
High performance self-hosted photo and video management solution
Català Español Français Italiano 日本語 한국어 Deutsch Nederlands Türkçe 简体中文 正體中文 Українська Русский Português Brasileiro Svenska العربية Tiếng Việt ภาษาไทย മലയാളം
[!WARNING] ⚠️ Always follow 3-2-1 backup plan for your precious photos and videos!
[!NOTE] You can find the main documentation, including installation guides, at https://immich.app/.
Links
Demo
Access the demo here. For the mobile app, you can use https://demo.immich.app for the Server Endpoint URL.
Login credentials
| Password | |
|---|---|
| demo@immich.app | demo |
Features
| Features | Mobile | Web |
|---|---|---|
| Upload and view videos and photos | Yes | Yes |
| Auto backup when the app is opened | Yes | N/A |
| Prevent duplication of assets | Yes | Yes |
| Selective album(s) for backup | Yes | N/A |
| Download photos and videos to local device | Yes | Yes |
| Multi-user support | Yes | Yes |
| Album and Shared albums | Yes | Yes |
| Scrubbable/draggable scrollbar | Yes | Yes |
| Support raw formats | Yes | Yes |
| Metadata view (EXIF, map) | Yes | Yes |
| Search by metadata, objects, faces, and CLIP | Yes | Yes |
| Administrative functions (user management) | No | Yes |
| Background backup | Yes | N/A |
| Virtual scroll | Yes | Yes |
| OAuth support | Yes | Yes |
| API Keys | N/A | Yes |
| LivePhoto/MotionPhoto backup and playback | Yes | Yes |
| Support 360 degree image display | No | Yes |
| User-defined storage structure | Yes | Yes |
| Public Sharing | Yes | Yes |
| Archive and Favorites | Yes | Yes |
| Global Map | Yes | Yes |
| Partner Sharing | Yes | Yes |
| Facial recognition and clustering | Yes | Yes |
| Memories (x years ago) | Yes | Yes |
| Offline support | Yes | No |
| Read-only gallery | Yes | Yes |
| Stacked Photos | Yes | Yes |
| Tags | No | Yes |
| Folder View | Yes | Yes |
Translations
Read more about translations here.
Repository activity
Star history
Contributors
Install immich-machine-learning-rocm on Unraid in a few clicks.
Find immich-machine-learning-rocm in Community Apps on your Unraid server, review the template, and click Install. Unraid handles the Docker app or plugin setup from the published template.
Requirements
Categories
Related apps
Explore more like this
Explore allDetails
ghcr.io/immich-app/immich-machine-learning:release-rocmRuntime arguments
- Network
immich_internal- Shell
bash- Privileged
- false
- Extra Params
--group-add video
Template configuration
AMD Kernel Fusion Driver. Required for ROCm.
- Target
- /dev/kfd
- Default
- /dev/kfd
- Value
- /dev/kfd
AMD GPU render device.
- Target
- /dev/dri
- Default
- /dev/dri
- Value
- /dev/dri
ML model cache directory. Models are downloaded on first use (several GB).
- Target
- /cache
- Default
- /mnt/user/appdata/immich/model-cache/
- Value
- /mnt/user/appdata/immich/model-cache/
General settings.
Timezone. See: https://en.wikipedia.org/wiki/List_of_tz_database_time_zones#List
- Target
- TZ
- Default
- Europe/Berlin
- Value
- Europe/Berlin
Advanced ML settings.
Seconds of inactivity before unloading models from VRAM. Set to 0 to keep loaded permanently.
- Default
- 300
- Value
- 300
Number of ML worker processes. For multi-GPU setups, increase workers and set MACHINE_LEARNING_DEVICE_IDS (e.g. 0,1) to distribute workers across GPUs.
- Default
- 1
- Value
- 1
Seconds before a worker is considered unresponsive. GPU inference can be slow on first run.
- Default
- 300
- Value
- 300
Log verbosity: verbose, debug, log, warn, error
- Default
- log
- Value
- log