Image to text with CLIP ViT-L/14 in ComfyUI
Perfil do pacote
README
Image to text with CLIP ViT-L/14 in ComfyUI
Nós neste pacote
Nós 3Fontes
1 fonteTrechos de fonte
1 trechoSource 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 · entradas 2 · parâmetros 2 · saída 1