ComfyUI Node: (Down)Load LLaVA-OneVision Model

Authored by kijai

Created

Updated

102 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

LLaVA-OneVision

Inputs

model
  • lmms-lab/llava-onevision-qwen2-7b-ov
  • lmms-lab/llava-onevision-qwen2-0.5b-ov
  • lmms-lab/llava-onevision-qwen2-7b-si
  • lmms-lab/llava-onevision-qwen2-0.5b-si
device
  • cuda
  • cpu
  • mps
precision
  • fp4
  • nf4
  • int8
  • fp16
  • bf16
  • fp32
attention
  • flash_attention_2
  • sdpa
  • eager

Outputs

LLAVAMODEL

Extension: ComfyUI Llava-OneVision

Nodes to use the OneVision LLaVA models: a/https://github.com/LLaVA-VL/LLaVA-NeXT

Authored by kijai

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more