Node packVerificadoExterno

ComfyUI-ThinkingLLM

A multimodal ComfyUI AI node with Qwen3.5, Qwen3-VL, Qwen2.5-VL, Qwen3, and Gemma 4 integrations. Features live thinking in the terminal to see what the LLM is doing in real time. Prompt enhancing, I2T, V2T, A2T....

Fontegithub.com/goodguy1963/ComfyUI-ThinkingLLM

Mantenedor@goodguy1963Bnota

Perfil do pacote

Status: Verificado
Publicador: @goodguy1963
Fonte: GitHub
Estrelas: 27

README

ComfyUI-ThinkingLLM

ThinkingLLM is a multimodal local-LLM node pack for ComfyUI. It provides clean workflows for Qwen, Gemma 4, GGUF, Whisper ASR, prompt enhancement, image/video understanding, audio analysis, and secure OpenAI-compatible providers.

Watch the demo on YouTube

GPL-3.0 fork of Deaquay/ComfyUI-Qwen3.5-Uncensored, itself derived from huchukato/ComfyUI-QwenVL-Mod and 1038lab/ComfyUI-QwenVL. See LICENSE.

ThinkingLLM Demo Node screenshot

Highlights

Local Transformers/Hugging Face and GGUF inference
Image and video understanding with optional mask-focused analysis
Gemma 4 audio understanding and Whisper speech-to-text
Prompt enhancers for image and video generation workflows
Thinking-mode control, live terminal streaming, and a separate RAW_TRACE output
Curated model recommendations and preset-specific generation guidance
Secure OpenAI-compatible API node for approved remote providers
Existing compatible models are discovered instead of downloaded twice

Quick install

ComfyUI Manager (recommended)

Open ComfyUI Manager → Install via Registry.
Search for ThinkingLLM.
Click Install and restart ComfyUI.

Manual install

cd ComfyUI/custom_nodes
git clone https://github.com/goodguy1963/ComfyUI-ThinkingLLM.git
cd ComfyUI-ThinkingLLM
pip install -r requirements.txt

For GGUF vision or Gemma 4 audio, also follow the llama.cpp backend installation guide.

Nodes at a glance

Node	Backend	Purpose
`ThinkingLLM`	Transformers / HF	Image and video understanding
`ThinkingLLM (Advanced)`	Transformers / HF	Full controls and `MASK_PREVIEW`
`ThinkingLLM Prompt Enhancer`	Transformers / HF	Text prompt enhancement
`ThinkingLLM (GGUF)`	llama.cpp	GGUF image and video understanding
`ThinkingLLM (GGUF Advanced)`	llama.cpp	GGUF advanced controls and `MASK_PREVIEW`
`ThinkingLLM Gemma 4 Audio (GGUF)`	llama.cpp	Gemma 4 audio understanding
`ThinkingLLM Whisper ASR`	faster-whisper	Speech-to-text transcription
`ThinkingLLM Prompt Enhancer (GGUF)`	llama.cpp	GGUF prompt enhancement
`ThinkingLLM System Prompt Preset`	Utility	Reusable system prompts as `STRING`
`ThinkingLLM API (OpenAI Compatible)`	Remote API	Approved OpenAI-compatible providers

The Transformers/HF nodes are the recommended default when you want the simplest installation. Choose GGUF when you specifically need quantized llama.cpp models or Gemma 4 audio.

Start a workflow

Add the ThinkingLLM node that matches your backend and task.
Select a model or an already installed local model.
Connect image, video, audio, mask, or text inputs as needed.
Connect RESPONSE or ENHANCED_OUTPUT to a text display or downstream prompt input.
Connect RAW_TRACE when you want generation diagnostics.

Useful defaults:

Start with enable_thinking=false for transcription and short direct answers.
Enable stream_tokens_to_terminal when diagnosing a slow or unhelpful generation.
Resize very large images before inference to reduce context and memory pressure.
Use the dedicated Gemma 4 Audio or Whisper node instead of assuming every multimodal model supports audio.

For explanations of thinking mode, model guidance, raw traces, audio, masks, and object-removal prompting, see Features and workflows.