CLIPtion is a fast and small captioning extension to OpenAI CLIP ViT-L/14. You already have ViT-L loaded when using using Stable Diffusion, SDXL, SD3, FLUX, etc and with just an extra 100MB memory you can include caption/prompt generation in your workflows!

I made this for fun and am sure bigger dedicated caption models and VLM's will give you more accurate captioning, but this guy is tiny, fast, reuses what you already have loaded, and has options to give better CLIP alignment so give it a try if you like!

Big thanks to Ben Egan, SilentAntagonist, Alex Redden, XWAVE, and Jacky-hate whose synthetic caption datasets I included in the training.

Example workflow

CLIPtion-example.json

Installation

Clone this repo to your ComfyUI/custom_nodes directory.

cd custom_nodes
git clone https://github.com/pharmapsychotic/comfy-cliption.git
pip install -r comfy-cliption/requirements.txt

Download CLIPtion_20241219_fp16.safetensors and put in your ComfyUI/custom_nodes/comfy-cliption directory. You can skip this step to let it auto-download on first use to your HF_HOME cache.
Restart ComfyUI

Nodes

CLIPtion Loader

If CLIPtion_20241219_fp16.safetensors is not already downloaded (as in step 2 of Installation) then the loader will automatically download the CLIPtion model for you the first time it is run from the HuggingFace CLIPtion repo. It gets stored in the HuggingFace cache dir (controlled by HF_HOME environment variable).

CLIPtion Generate

Create caption from an image or batch of images.

temperature - controls randomness in generation - higher values produce more diverse outputs, lower values are more focused and predictable
best_of - generates this many captions in parallel and picks the one with best CLIP similarity to the image
ramble - forces generation of full 77 tokens

CLIPtion Beam Search

beam_width - how many alternative captions are considered in parallel - higher values explore more possibilities but take longer
ramble - forces generation of full 77 tokens