ComfyUI Node: Molmo Vision-Language Model

Authored by gokayfem

Created

Updated

576 stars

Run Molmo Vision-Language Model without installing ComfyUI

This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.

Category

VLM Nodes/Molmo

Inputs

image IMAGE
prompt STRING
model_name
  • MolmoE-1B (Efficient)
  • Molmo-7B-D (Best 7B)
  • Molmo-7B-O (Alternative 7B)
memory_mode
  • Full Precision (45GB+ Required)
  • 8-bit Quantized (25GB+ Required)
  • 4-bit Quantized (15GB+ Required)
  • 4-bit + CPU Offload (12GB+ Required)
max_new_tokens INT
temperature FLOAT
top_p FLOAT
top_k INT
use_autocast BOOLEAN

Outputs

STRING

Extension: VLM_nodes

Custom Nodes for Vision Language Models (VLM) , Large Language Models (LLM), Image Captioning, Automatic Prompt Generation, Creative and Consistent Prompt Suggestion, Keyword Extraction

Authored by gokayfem

Looking for a different node?

Run Molmo Vision-Language Model without installing ComfyUI

This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.

Learn more