Preview for Basic VLM
Basic VLM workflow diagram

Run this workflow on InstaSD

Get started in minutes! Run this ComfyUI workflow online - no setup required.

Description

Use VLM models in your ComfyUI workflows, here is a basic example on how to use vision Vision Language models for simple image to text.

Models

FileDestinationSource
mmproj-model-f16.gguf/ComfyUI/models/LLavacheckpointsDownload
ggml-model-q4_k.gguf/ComfyUI/models/LLavacheckpointsDownload

Nodes

LLavaSamplerSimpleSimpleTextLlavaClipLoaderLLava Loader SimpleViewTextLoadImage