Image to text with CLIP ViT-L/14 in ComfyUI
Package profile
README
Image to text with CLIP ViT-L/14 in ComfyUI
Nodes in this pack
3 nodesSources
1 sourceSource excerpts
1 excerptSource context: Repo pharmapsychotic/comfy-cliption
CLIPtionBeamSearch
Deterministic search for caption from an image or batch of images. Less "creative" than Generate node. beamwidth - how many alternative captions are considered in parallel - higher values explore more possibilities but take longer ramble - forces generation of full 77 tokens
Pharmapsychotic · 2 inputs · 2 parameters · 1 output