ComfyUI_VLM_nodes

(★ 585)

ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video temporal reasoning, GGUF via llama.cpp, and hosted LLM/VLM APIs.

File Explorer

Download Latest Version (.zip)

- - bug_report.yml
  - config.yml
  - model_request.yml
- - ci.yml
  - publish-fleet.yml
  - publish.yml
- dependabot.yml
- PULL_REQUEST_TEMPLATE.md
- - __init__.py
  - lerobot_policy_server.py
  - README.md
  - vla_http_policy_safety_api.json
- - grounding_dino_image_api.json
  - moondream31_video_detect_api.json
  - moondream3_preview_svg_segment_api.json
  - README.md
  - sam2_video_tracking_api.json
  - sam3_core_adapter_blueprint_api.json
  - video_temporal_reasoning_api.json
  - vlm_performance_preflight_api.json
- auto_prompt_generation.json
- img2music_workflow_gokay.json
- simple_llava.json
- text_toolkit_api.json
- - Models.py
- acceleration.py
- audioldm2.py
- diagnostics.py
- florence2.py
- geometry.py
- grounding.py
- hosted_api.py
- joytag.py
- kosmos2.py
- llavaloader.py
- mcllava.py
- minicpm.py
- minimax_music.py
- modern_vlm.py
- molmo.py
- moondream2.py
- moondream31.py
- moondream31_worker.py
- moondream_script.py
- paligemma.py
- playmusic.py
- prompts.py
- qwen2vl.py
- robotics.py
- runtime.py
- sam2.py
- sam3_adapter.py
- simpletext.py
- spatial_parser.py
- suggest.py
- tracking.py
- uform.py
- video_intelligence.py
- vision_types.py
- vision_utils.py
- _bootstrap.py
- conftest.py
- manual_catalog_probe.py
- manual_llama_cpp_smoke.py
- manual_llm_node_smoke.py
- manual_model_smoke.py
- manual_robotics_smoke.py
- manual_specialized_smoke.py
- manual_video_intelligence_smoke.py
- test_acceleration.py
- test_documentation.py
- test_florence2_capabilities.py
- test_geometry.py
- test_grounding.py
- test_hosted_api.py
- test_llavaloader.py
- test_minimax_music.py
- test_moondream2.py
- test_moondream31.py
- test_nodes.py
- test_robotics.py
- test_sam2.py
- test_sam3_adapter.py
- test_simpletext.py
- test_spatial_parser.py
- test_suggest.py
- test_tracking.py
- test_video_intelligence.py
- test_vision_types.py
- test_vision_utils.py
- - apiSecurity.js
  - jsonToText.js
  - playSound.js
  - viewText.js
.gitignore
__init__.py
CHANGELOG.md
CITATION.cff
COMPATIBILITY.md
CONTRIBUTING.md
LICENSE
MODEL_VALIDATION.md
pyproject.toml
README.md
requirements-dev.txt
requirements-llama-cpp.txt
requirements-moondream31.txt
requirements-quantization.txt
requirements-robotics-client.txt
requirements.txt
SECURITY.md
vlmnodes.default.json
vlmnodes.json

# Installation Guide

1. Get the code

git clone https://github.com/gokayfem/ComfyUI_VLM_nodes

Downloads the entire project code from GitHub to your computer.

cd ComfyUI_VLM_nodes

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

python -m pip install -r ComfyUI/custom_nodes/ComfyUI_VLM_nodes/requirements.txt