HunyuanCustom | Multi-Subject Video Generator
This ComfyUI HunyuanCustom Multi-Subject workflow integrates Tencent's advanced model into the ComfyUI environment, specifically optimized for dual-subject generation. Built upon the HunyuanVideo framework and enhanced by Kijai, this workflow excels at maintaining consistent identity features of both subjects throughout generated videos. With FreSca technology and specialized nodes, it achieves superior quality for virtual demonstrations, product showcases, and natural subject interactions with approximately 30% faster processing speeds.ComfyUI HunyuanCustom Workflow

- Fully operational workflows
- No missing nodes or models
- No manual setups required
- Features stunning visuals
ComfyUI HunyuanCustom Examples
ComfyUI HunyuanCustom Description
1. What is the ComfyUI HunyuanCustom Multi-Subject Workflow?
The ComfyUI HunyuanCustom Multi-Subject workflow integrates Tencent's advanced HunyuanCustom model into the ComfyUI environment, specifically optimized for dual-subject generation. Built upon the HunyuanVideo framework, this HunyuanCustom workflow focuses on generating videos featuring interactions between two subjects (such as a person and a product) with exceptional identity preservation. The HunyuanCustom workflow, optimized by Kijai, includes several enhancements like FreSca technology and specialized nodes designed to improve HunyuanCustom generation quality, consistency, and efficiency.
2. Benefits of ComfyUI HunyuanCustom Multi-Subject Workflow:
- Superior Identity Preservation: HunyuanCustom excels at maintaining consistent identity features of both subjects throughout generated videos.
- Natural Subject Interaction: The HunyuanCustom model enables realistic interactions between a person and a product, ideal for virtual demonstrations.
- Enhanced Quality: Implementation of FreSca technology and optimized nodes significantly improves overall HunyuanCustom video quality and stability.
- Product Demonstration Focus: HunyuanCustom is specifically designed for virtual human advertisements and product showcases.
- Performance Optimization: HunyuanCustom TeaCache implementation delivers approximately 30% faster processing speeds compared to standard workflows.
3. How to Use the ComfyUI HunyuanCustom Workflow
3.1 Generation Methods with ComfyUI HunyuanCustom Multi-Subject Workflow
Example Setup for HunyuanCustom Multi-Subject:
- Prepare inputs:
- Upload a reference image of a person (preferably upper-body shot) for best HunyuanCustom identity preservation
- Upload a reference image of a product or second subject
- Enter simple and clear prompt describing the desired interaction between the person and product
- Set negative prompt to avoid unwanted elements in your HunyuanCustom output
- Configure the HunyuanCustom nodes with recommended settings (see Parameter Reference)
- Click
Run
to run the HunyuanCustom workflow - Retrieve your HunyuanCustom video from the output node

HunyuanCustom Dual-Subject Generation
- Best for: Creating videos featuring person-product interactions with strong HunyuanCustom identity preservation
- Characteristics:
- Maintains consistent identity of both the person and product throughout the HunyuanCustom video
- Enables natural interaction between the person and product in HunyuanCustom outputs
- Achieves realistic demonstrations and product presentations
HunyuanCustom Virtual Advertisement
- Best for: Creating product demonstrations and marketing videos with HunyuanCustom
- Characteristics:
- Preserves product details and branding elements in HunyuanCustom videos
- Shows natural human interaction with the product
- Ideal for virtual showrooms and HunyuanCustom demonstrations
3.2 Parameter Reference for ComfyUI HunyuanCustom
Main HunyuanCustom Node:
Resolution
: Sets HunyuanCustom output video resolution (recommended: 720×1280 for best quality)Frames
: Number of frames to generate in HunyuanCustom videos (typically 129 frames for 5-second videos)Steps
: Number of denoising steps for HunyuanCustom (30 recommended for balance of quality and speed)CFG Scale
: Controls prompt adherence strength in HunyuanCustom (higher = more prompt-aligned but potentially less natural)Flow Shift
: Adjusts motion fluidity in HunyuanCustom outputs (recommended value: 13.0)
FreSca Enhancement Node:
Enabled
: Toggle the FreSca enhancement on/off for HunyuanCustomScale
: Strength of FreSca effect (1.0 recommended for balanced enhancement)Mode
: Set to "single blocks" for optimal hand stability and detail preservation
ID Enhancement Module:
Weight
: Controls how strongly the identity features are preserved in HunyuanCustomTemporal Concat
: Enables improved identity consistency across frames
SLG (Stability-Latent-Guidance) Node:
Mode
: Set to "single blocks" for best hand detail preservation in HunyuanCustomStrength
: Controls how strongly the stability guidance is applied to the generation
3.3. Advanced Optimization with ComfyUI HunyuanCustom
Best Practices for Subject Images:
- Use upper-body or shoulder-up portraits for best face quality and consistency in HunyuanCustom
- Avoid full-body shots as they disperse attention and may result in poorer facial detail
- For unavoidable full-body requirements, consider post-processing with GPEN face enhancement
Improving Hand Rendering in HunyuanCustom:
- Enable FreSca enhancement and set to "single blocks" mode
- Use SLG nodes with appropriate strength settings in your HunyuanCustom workflow
- Include specific hand descriptions in your prompt to guide generation
Performance Enhancement for HunyuanCustom:
- Implement TeaCache for approximately 30% faster processing
- Use appropriate batch sizes based on your GPU capabilities
- Consider lower resolutions for draft generations and higher resolutions for final HunyuanCustom outputs
Quality Enhancements:
- Add Hunyuan Reward LoRA for improved overall HunyuanCustom quality
- Use the CFG Zero Star node to enhance generation quality
- Experiment with different sampling methods for optimal HunyuanCustom results
More Information about HunyuanCustom
For additional details and development references:
- Original HunyuanCustom model by
- ComfyUI integration of HunyuanCustom by
Acknowledgements
This workflow is powered by HunyuanCustom, developed by Tencent's Hunyuan team. The original paper "HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation" introduced this powerful framework that emphasizes subject consistency while supporting image, audio, video, and text conditions.
The ComfyUI integration of HunyuanCustom is provided by Kijai, including optimizations like FreSca technology, SLG nodes, and TCatch implementation that significantly improve generation quality and efficiency. Full credit goes to the original authors at Tencent for their groundbreaking work on HunyuanCustom and to Kijai for the outstanding ComfyUI implementation and enhancements.