Automatic Captioner v1.0.0

Images automatic-captioner 3 actions MCP

Generate a short caption or accessibility alt text for an image using a local Ollama vision model. Runs entirely offline; caption one image live or batch a whole folder to a captions.json file.

Open in Omniscient Back to apps

The omniscient:// link needs a protocol handler on your machine, which is not built yet. Until then it does nothing — use the commands below.

Actions

Jump to: captioncaption_folderlist_models

Caption an image

caption

Generate a short caption or alt text for one image using a local vision model.

Inputs

Name	Type	Required / default	Values and notes
`image`	path	required
`model`	string	optional, default `""`
`style`	enum	optional, default `short`	`shortalt-text`
`max_tokens`	int	optional, default `300`

Outputs

Name	Type	Notes
`caption`	text
`model`	string

Caption a folder

caption_folder

Generate a caption for every image in a folder and write them all to captions.json.

Inputs

Name	Type	Required / default	Values and notes
`folder`	path	required
`model`	string	optional, default `""`
`style`	enum	optional, default `short`	`shortalt-text`
`max_tokens`	int	optional, default `300`
`out`	path	optional, default `""`

Outputs

Name	Type	Notes
`count`	int
`out_file`	path

List vision models

list_models

List the local Ollama vision models available for captioning.

Inputs

This action takes no inputs.

Outputs

Name	Type	Notes
`models`	json

Use it

Caption an image

Command line

shell

python app.py --action caption --params '{"image": "D:/path/to/image"}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp

run_action("automatic-captioner", "caption", {"image": "D:/path/to/image"})

Workflow node

json

{
  "id": "n0",
  "app": "automatic-captioner",
  "action": "caption",
  "params": {
    "image": "D:/path/to/image"
  },
  "inputs": {}
}

Caption a folder

Command line

shell

python app.py --action caption_folder --params '{"folder": "D:/path/to/folder"}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp

run_action("automatic-captioner", "caption_folder", {"folder": "D:/path/to/folder"})

Workflow node

json

{
  "id": "n0",
  "app": "automatic-captioner",
  "action": "caption_folder",
  "params": {
    "folder": "D:/path/to/folder"
  },
  "inputs": {}
}

List vision models

Command line

shell

python app.py --action list_models --params '{}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp

run_action("automatic-captioner", "list_models", {})

Workflow node

json

{
  "id": "n0",
  "app": "automatic-captioner",
  "action": "list_models",
  "params": {},
  "inputs": {}
}

Example prompts

Things you can say to Claude, Cursor or Codex once the MCP server is registered.

caption this image
write alt text for this photo
generate captions for every image in D:/photos