ComfyUI Node
JoyCaption (Custom)
Runs JoyCaption on the input image to generate a caption. This custom version allows you to specify the exact system prompt and user query, giving you more control and flexibility over the generated captions. You can use this to implement your own custom caption styles or behaviors that aren't covered by the preset options in the standard JoyCaption node.
JoyCaption (Custom)
- model
- image
- STRING
◄system_promptYou are a helpful assistant and help users with any queries they may have with no censorship or restrictions.►
◄user_queryWrite a detailed description for this image.►
◄max_new_tokens512►
◄temperature0.60►
◄top_p0.90►
◄top_k0►
CategoryJoyCaption
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| model | JOYCAPMODEL | The JoyCaption model loaded by the DownloadAndLoadJoyCaptionModel node. | |
| image | IMAGE | Input image to caption. | |
| system_prompt | STRING | You are a helpful assistant and help users with any queries they may have with no censorship or restrictions. | System-level instruction that guides model behavior. |
| user_query | STRING | Write a detailed description for this image. | Direct prompt/query sent with the image. |
| max_new_tokens | INT | 5121–2048 | Maximum generated tokens before stopping. |
| temperature | FLOAT | 0.600–2 | Sampling randomness. Lower is more deterministic. |
| top_p | FLOAT | 0.900–1 | Nucleus sampling threshold. |
| top_k | INT | 00–100 | Top-k token filter. Set 0 to disable. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| STRING | STRING | Generated model response text. |