A tool for adding captions to PhotoPrism photos
Project description
TLDR
The simplest way to run: using uvx (you need to pip install uv first):
For local model (will install torch and transformers, can be slow):
uvx --from 'photoprism_captioner[local]' photoprism_captioner --backend local --auth-token MY_PHOTOPRISM_AUTH_TOKEN --model Salesforce/blip-image-captioning-large --photoprism-url="https://my.photoprism.qwe.org"
For Ollama model (self-hosted LLM models provider):
uvx --from 'photoprism_captioner[remote]' photoprism_captioner --backend remote --auth-token MY_PHOTOPRISM_AUTH_TOKEN --model ollama/gemma3 --api-base http://my-ollama-instance:11434 --photoprism-url="https://my.photoprism.qwe.org"
For OpenAI model (Don't forget to set OPENAI_API_KEY environment variable):
uvx --from 'photoprism_captioner[remote]' photoprism_captioner --backend remote --auth-token MY_PHOTOPRISM_AUTH_TOKEN --model gpt-4o-2024-08-06 --api-base https://api.openai.com/v1/chat/completions --photoprism-url="https://my.photoprism.qwe.org"
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file photoprism_captioner-0.1.2.tar.gz.
File metadata
- Download URL: photoprism_captioner-0.1.2.tar.gz
- Upload date:
- Size: 5.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.5.27
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
30dc890082fb39331e88e4101fbaeaf948d0e3b6153af0f60b7041f1705719d5
|
|
| MD5 |
e419faeaa535e5845399d644af811ad8
|
|
| BLAKE2b-256 |
417610a668112602e70918018262522bb73ebc4ae102bd0dc95f12dba788bccd
|
File details
Details for the file photoprism_captioner-0.1.2-py3-none-any.whl.
File metadata
- Download URL: photoprism_captioner-0.1.2-py3-none-any.whl
- Upload date:
- Size: 7.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.5.27
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
47bc92555d8c0c2c5de7269fb976d9e27009b56797b18c62ff5b59ab314566b4
|
|
| MD5 |
c25215168a2bcc220a44f008fa1b4d14
|
|
| BLAKE2b-256 |
cf1683759b936275f8717411805a214c89f1b048eb0c9b4a5793a349f9d22c02
|