ComfyUI-LLM-text-processor

ComfyUI LLM Text Processor

Process text and images with GGUF LLMs in ComfyUI using llama.cpp, including Qwen3-VL, Qwen3.5, Qwen3.6, Qwen3.7, Qwen3.8, Gemma 4, and gpt-oss.

This extension adds a local LLM node for prompt writing, prompt rewriting, translation, captioning, extraction, and other text processing tasks inside ComfyUI. It discovers local GGUF models from ComfyUI/models/LLM, and it can also accept a single image or a ComfyUI image batch for multimodal models that use an external mmproj.

Node UI

Features

• Text generation and text transformation with local GGUF models
• Optional image input for multimodal llama.cpp models that use mmproj, including multi-image batches
• Separate RESPONSE and REASONING outputs
• System prompt presets from text files
• Recursive model discovery from ComfyUI/models/LLM
• Automatic llama.cpp setup on supported Windows systems
• Download progress logs during automatic llama.cpp setup
• Advanced llama.cpp options for users who need them
• Optional enable_processing toggle for switching between node processing and direct passthrough

Supported Model Families

Works with local GGUF models for Qwen, Gemma 4, gpt-oss, and other llama.cpp-compatible families.

Common examples:

• Qwen text and vision families such as Qwen3-VL, Qwen3.5, Qwen3.6, Qwen3.7, and Qwen3.8
• Gemma 4 GGUF models such as gemma-4-E2B, gemma-4-E4B, gemma-4-26b-a4b, and gemma-4-31b
• OpenAI gpt-oss-20b and gpt-oss-120b

Notes:

• For image workflows, choose a matching mmproj file from the same model family when the GGUF release provides one.
• Gemma 4 text generation works well. Vision support depends on the specific GGUF and mmproj release, and can be less reliable on some Windows CUDA setups.
• In this node, gpt-oss is used as a text model through llama.cpp-compatible GGUF releases.

Installation

ComfyUI Manager

Open ComfyUI Manager, choose Install Custom Nodes, search for LLM Text Processor, install it, then restart ComfyUI.

Manual Git Clone

Open a terminal in ComfyUI/custom_nodes and run:

git clone https://github.com/KingManiya/ComfyUI-LLM-text-processor.git

Restart ComfyUI. The node appears under:

LLM Text Processor -> LLM Text Processor

No extra setup is needed for basic use.

Example workflow

Workflow

llama.cpp

The node uses official llama.cpp release binaries. Automatic setup is currently available on:

Windows x64 + CUDA 13

Other platforms require manual setup.

The extension downloads llama.cpp only. It does not download model weights.

During automatic setup, the console shows download progress, total size when available, and current download speed so slow connections do not look like a freeze.

Model Placement

Put your GGUF files anywhere under:

ComfyUI/models/LLM

Example:

ComfyUI/models/LLM/My-Model/model-q4_k_m.gguf
ComfyUI/models/LLM/My-Model/mmproj-bf16.gguf

The model dropdown shows model .gguf files. The mmproj dropdown shows vision projector files and none.

For image workflows, choose the mmproj file that belongs to the selected model. You can connect either one image or a ComfyUI image batch; batch items are sent together in the same llama.cpp request.

System Prompt Presets

Create text files in:

ComfyUI/models/LLM/prompts

Example:

ComfyUI/models/LLM/prompts/captioner.txt

Each top-level .txt file appears in the system_prompt dropdown. Choose none to run without a system prompt.

Recommended Settings

These presets are a good starting point for common models and tasks.

Qwen

Qwen starting presets:

| Model family / use case | reasoning | temperature | top_p | `to