Files
easygoing0114-ComfyUI-clipt…/README.md
T
2026-08-13 14:42:46 +09:00

2.4 KiB

ComfyUI Cliption Integrated Nodes thumbnail

ComfyUI-cliption-integrated

A streamlined fork of pharmapsychotic/comfy-cliption for ComfyUI, providing a single, integrated CLIPtion Beam Search node.

CLIPtion is a fast, lightweight image captioning model built on top of CLIP. This fork simplifies the original node pack down to the beam-search workflow only.

Node

CLIPtion Beam Search (Integrated)

mask refine node sample

Loads the CLIPtion decoder on demand at caption time (rather than at workflow-load time) and runs beam search to caption an image, ranking the resulting candidates by CLIP similarity to the input image.

Inputs

Name Type Description
clip CLIP CLIP text encoder (must include CLIP-L).
clip_vision CLIP_VISION CLIP vision encoder (must be CLIP-L).
image IMAGE Inoput Image to caption.
beam_width INT Number of beams to maintain during search (default: 4).
unload_after_run BOOLEAN Unload the CLIPtion decoder from VRAM after captioning (default: False).
device (optional) ["default", "cpu"] Inference device override.

Output

Name Type Description
STRING STRING (list) One caption per input image.

The CLIPtion decoder weights (CLIPtion_20241219_fp16.safetensors) are downloaded automatically from easygoing0114/ComfyUI-use-models on Hugging Face the first time the node runs, and are cached on disk afterwards.

Installation

cd ComfyUI/custom_nodes
git clone https://github.com/easygoing0114/ComfyUI-cliption-integrated.git

Restart ComfyUI. The node should now appear in the node search as CLIPtion Beam Search (Integrated).

Credits

License

This project is licensed under the MIT License.