razv23andCursor
58c9ffe598
Extract actual token counts from Claude and Gemini API responses instead of discarding them. The LLM node now outputs a formatted token_usage string (input/output/total) alongside the response. Also adds a standalone text analyzer utility node for pre-flight word count and token estimation. Co-authored-by: Cursor <cursoragent@cursor.com>
ComfyUI Stillfront Custom Nodes
A consolidated collection of custom nodes for ComfyUI developed by Stillfront.
Features
This package includes nodes for:
- LLM Integration - Claude and Gemini API support for text generation with optional image input
- WaveSpeed API - Image and video generation via WaveSpeed AI (VEO, Sora, Qwen, ByteDance, etc.)
- Utility Nodes - Resolution presets, dynamic prompt lists, and more
Installation
From GitHub
cd ComfyUI/custom_nodes
git clone https://github.com/stillfront/comfyui-stillfront.git
cd comfyui-stillfront
pip install -r requirements.txt
Configuration
- Copy
config.ini.tmptoconfig.ini - Add your API keys:
- WaveSpeed API key
- Claude API key (or set
ANTHROPIC_API_KEYenvironment variable) - Gemini API key (or set
GEMINI_API_KEYenvironment variable)
Node Categories
All nodes are prefixed with "SF" for easy searching in ComfyUI.
Stillfront/LLM
- SF LLM Chat - Chat with Claude or Gemini models, supports image input
Stillfront/WaveSpeed
- SF WaveSpeed Client - API client configuration
- SF VEO 3.1 Text to Video - Google VEO video generation
- SF Sora 2 Text to Video - OpenAI Sora video generation
- SF Qwen Image - Qwen image generation and editing
- SF ByteDance Seedream - ByteDance image generation
- And many more...
Stillfront/Utils
- SF Qwen Resolution - Resolution presets with visual preview
- SF Dynamic Prompt List - Dynamic text input list
Requirements
- Python 3.10+
- ComfyUI
- See
requirements.txtfor Python dependencies
License
MIT License