HunyuanImage 2.1 GGUF Text-to-Image & Image-to-Image Workflow
This workflow is designed for HunyuanImage 2.1 GGUF running in ComfyUI.
It supports both Text-to-Image (T2I) and Image-to-Image (I2I) generation using a simple workflow switch, making it easy to create artwork from text prompts or transform existing images into completely new styles.
Features
Supports HunyuanImage 2.1 GGUF
Switch between Text-to-Image and Image-to-Image
Easy workflow layout
Optimized for ComfyUI
Includes positive and negative prompt setup
Supports cyberpunk, fantasy, anime, and other creative styles
Easy to customize and expand
Required Models
Please install the following models before using this workflow.
GGUF Model
HunyuanImage 2.1 GGUF UNet
GGUF Dual CLIP
Qwen2.5-VL-7B-Instruct-Vision GGUF
byt5_small GGUF
GGUF VAE
HunyuanImage VAE GGUF
Notes
This workflow requires the necessary GGUF models to be installed in the correct ComfyUI model folders.
Please make sure your GGUF model paths are configured properly before loading the workflow.
Example
The example images demonstrate how a real-world photograph can be transformed into completely different artistic styles, including fantasy and cyberpunk scenes.
Enjoy creating your own worlds!
For installation, GGUF model selection, VRAM benchmarks, and workflow demonstrations, please visit my YouTube channel.
📺 YouTube Tutorials & Benchmarks
1. HunyuanImage 2.1 Installation & Beginner Guide
Installation
Standard Version
GGUF Introduction
2. HunyuanImage 2.1 GGUF VRAM Benchmark
GGUF Models
VRAM Requirements
Performance Testing
3. HunyuanImage 2.1 GGUF RTX 5080 / RTX 5090 Test
Best GGUF Models
RTX 5080
RTX 5090
Performance Comparison
4. HunyuanImage 2.1 Complete Summary
Performance Comparison
GGUF Overview
Recommended Settings