ComfyUI Node
CC Llama Vision
A ComfyUI node in llama.cpp with 14 inputs and 1 output.
CC Llama Vision
- image
- image_batch
- video_frames
- advanced_options
- caption
◄llama_server_pathllama-server►
◄models_dir/root/models►
◄model_path▾►
◄mmproj_path▾►
◄system_prompt►
◄user_prompt►
◄port8080►
◄max_tokens2048►
◄max_video_frames16►
◄label_video_framestrue►
Categoryllama.cpp
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| llama_server_path | STRING | llama-server | Path to the llama-server executable. Leave as 'llama-server' to resolve automatically from PATH (recommended after `winget install llama.cpp`), or provide a full path to llama-server.exe. |
| models_dir | STRING | /root/models | Folder to scan (recursively) for .gguf model and mmproj files. Click '🔄 Refresh Models' after changing this to repopulate the dropdowns below. |
| model_path | COMBO | The GGUF vision-language model file to load (mmproj files are excluded from this list). | |
| mmproj_path | COMBO | The GGUF multimodal projector (mmproj) file matching the selected model — required for image/vision input. | |
| system_prompt | STRING | System-level instructions sent to the model before the user prompt, e.g. persona or output-format guidance. | |
| user_prompt | STRING | The instruction/question sent to the model along with the image(s). This text is appended after any images. | |
| port | INT | 80801024–65535 | Local TCP port llama-server will listen on. Must be free unless 'keep_server_alive' is reusing an existing server on this port. |
| max_tokens | INT | 204816–8192 | Maximum number of tokens the model may generate in its response. |
| max_video_frames | INT | 161–64 | Maximum number of frames to sample from 'video_frames' input; frames beyond this are evenly subsampled. |
| label_video_frames | BOOLEAN | true | If enabled, prefixes each video frame image with a text label like '[Video frame N of M]'. |
| imageopt | IMAGE | A single image to send to the model. | |
| image_batchopt | IMAGE | A batch of images; each is sent as a separate image in the same message. | |
| video_framesopt | IMAGE | A sequence of image frames (e.g. from a video) to sample and send to the model, subject to max_video_frames. | |
| advanced_optionsopt | LLAMA_VISION_OPTS | Optional settings from a 'CC Llama Vision Advanced Options' node — sampling, performance, lifecycle, and diagnostics. If not connected, sensible defaults are used. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| caption | STRING | — |