ComfyUI Node
DIGIT Captioner
A ComfyUI node in DIGIT with 13 inputs and 3 outputs.
DIGIT Captioner
- report
- last_caption
- captioned_count
◄dataset_path►
◄actioncaption_uncaptioned►
◄caption_preset►
◄system_promptYou are an expert image captioner for AI training datasets. Describe the image in detail, focusing on subject, composition, lighting, colors, style, and mood. Be specific and descriptive. Output only the caption, no preamble.►
◄prompt_templateDescribe this image in detail for AI training:►
◄modelgemini-2.5-flash►
◄temperature0.40►
◄max_tokens300►
◄overwritefalse►
◄caption_ext.txt►
◄single_image_path►
◄gcp_project_id►
◄gcp_region►
CategoryDIGIT
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| dataset_path | STRING | — | |
| action | COMBO | caption_uncaptioned | 5 options: caption_all, caption_uncaptioned, caption_single, recaption_all, preview |
| caption_presetopt | STRING | — | |
| system_promptopt | STRING | You are an expert image captioner for AI training datasets. Describe the image in detail, focusing on subject, composition, lighting, colors, style, and mood. Be specific and descriptive. Output only the caption, no preamble. | — |
| prompt_templateopt | STRING | Describe this image in detail for AI training: | — |
| modelopt | COMBO | gemini-2.5-flash | 4 options: gemini-2.5-flash, gemini-2.5-pro, gemini-2.0-flash, gemini-2.0-flash-lite |
| temperatureopt | FLOAT | 0.400–2 | — |
| max_tokensopt | INT | 30050–2000 | — |
| overwriteopt | BOOLEAN | false | — |
| caption_extopt | STRING | .txt | — |
| single_image_pathopt | STRING | — | |
| gcp_project_idopt | STRING | — | |
| gcp_regionopt | STRING | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| report | STRING | — |
| last_caption | STRING | — |
| captioned_count | INT | — |