Multiple Image Descriptions and Local Multi-Modal Models in Griptape Nodes for ComfyUI: Part 16

Описание к видео Multiple Image Descriptions and Local Multi-Modal Models in Griptape Nodes for ComfyUI: Part 16

We've updated the ComfyUI Griptape Nodes to Griptape Framework v0.28.1, which means Image Description nodes can take multiple image inputs and will also work with local multi-modal models, like LLava running on Ollama!

🔗 Helpful Links:
Griptape Framework on Github: https://github.com/griptape-ai/griptape
Griptape ComfyUI Nodes: https://github.com/griptape-ai/ComfyU...
Griptape Docs: https://docs.griptape.ai/stable/
Griptape Discord:   / discord  
Installing Ollama video:    • How to Use Ollama as a Configuration ...  
Llava: https://ollama.com/library/llava
ComfyUI-Inspire-Pack: https://github.com/ltdrdata/ComfyUI-I...

Part #17:    • WebSearch Node Now Allows for Driver ...  

#comfyui #griptape #ollama

Комментарии

Информация по комментариям в разработке

Похожие видео