Visit ComfyUI Online for ready-to-use ComfyUI environment
ComfyUI-Mana-Nodes enhances ComfyUI with features like font animation, speech recognition, caption generation, and text-to-speech (TTS), providing advanced multimedia capabilities for dynamic user interfaces.
Welcome to the ComfyUI-Mana-Nodes project! This extension is a collection of custom nodes designed to enhance text-based content creation within the ComfyUI environment. Whether you're working on dynamic captions, transcribing audio, or crafting engaging visual content, ComfyUI-Mana-Nodes has got you covered. This extension aims to simplify and supercharge your creative process, making it easier to produce high-quality content with minimal effort.
ComfyUI-Mana-Nodes operates by providing a set of specialized nodes that you can use within the ComfyUI framework. These nodes are like building blocks that you can connect to create complex workflows for generating text, images, and even audio. Think of it as a toolkit where each tool (node) has a specific function, and by combining them, you can achieve a wide range of creative tasks. For example, you can use one node to transcribe audio into text and another to render that text onto images, all within a seamless workflow.
This node allows you to render text onto images. You can customize the font, canvas properties, and even add highlights to specific words. It supports multiline text and frame-specific text rendering, making it versatile for various applications.
This node lets you define the font properties such as font file, size, color, and additional styling options like kerning, border, and shadow. You can also animate these properties using the Scheduled Values node.
This node allows you to set the dimensions, background color, padding, and line spacing for the canvas where the text will be rendered. You can also use images as the background instead of a solid color.
This node helps you animate various properties over time. You can set keyframes and generate intermediate values using different easing functions. This is useful for creating dynamic text animations.
This node provides predefined color animations like rainbow, sunset, and ocean. You can set the duration and reset behavior of these animations, making it easy to add colorful effects to your text.
This node converts spoken words in an audio file to text using a deep learning model. It supports various languages and can generate frame-stamped transcriptions, which are useful for synchronizing text with video.
This node extracts frames and audio from a video file. You can specify the frame range and get the extracted frames as image tensors, along with the audio file.
This node combines a sequence of images into a video file. You can also add an audio file to the video, making it easy to create video content from individual frames.
This node converts text to speech and saves the output as an audio file. It supports multiple languages and can generate non-speech sounds like laughter and music.
This node allows you to save text to a file, which can be useful for debugging or for saving intermediate results in your workflow.
The extension uses various models for different tasks. For example, the Speech Recognition node uses the Wav2Vec2 model for transcribing audio. You can find and use different models from Hugging Face to suit your specific needs.
How do I change the font color?
Use the Font Properties node and set the font_color
input. You can also animate the color using the Preset Color Animations node.
Can I use my own fonts? Yes, you can use any font file located in the system font directories or the custom_nodes\ComfyUI-Mana-Nodes\font_files directory.
How do I synchronize text with video? Use the Speech Recognition node to generate frame-stamped transcriptions and then use these transcriptions in the Text to Image Generator node.
For more information, tutorials, and community support, you can visit the following resources:
© Copyright 2024 RunComfy. All Rights Reserved.