ComfyUI Node: Loader Image to Text Model 🐼
Category
fofo🐼/image2prompt
Inputs
model
- moondream1
- moondream2
- bunny-llama3-8b-v
- internlm-xcomposer2-vl-7b
- uform-qwen
- wd-swinv2-tagger-v3
- deepseek-vl-1.3b-chat
- deepseek-vl-7b-chat
device
- cpu
- cuda
low_memory BOOLEAN
Outputs
IMAGE2TEXT_MODEL
Extension: Comfyui_image2prompt
Nodes:Image to Text, Loader Image to Text Model.
Authored by zhongpei
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more