wavespeed-ai/hunyuan-custom-ref2v-720p
HunyuanCustom, a multi-modal, conditional, and controllable generation model centered on subject consistency, built upon the Hunyuan Video generation framework. It enables the generation of subject-consistent videos conditioned on text, images, audio, and video inputs.
image-to-video
new
Idle
Your request will cost $0.4 per video,
For $1 you can run this model approximately 2 times.
README
hunyuan-custom-ref2v-720p is an open-source, multimodal-driven architecture for customized video generation, powered by HunyuanVideo-13B. Outperforming existing open-source models, it rivals top closed-source solutions!
Key Features
- Single-Subject Video: Upload an image + text to videos with new actions, outfits, and scenes.
- Multi-Subject Video: Generate videos with multiple subjects from separate image inputs.
- Audio-Driven Video: Sync audio with visuals for talking or singing in any scene.
- Video-Driven Video: Seamlessly insert or replace subjects into any video for creative enhancements.
ComfyUI
hunyuan-custom-ref2v-720p text + image to video is available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.
Use Cases
- Virtual advertising and try-on: By accepting multiple image inputs, HunyuanCustom enables the creation of virtual human advertisements and virtual try-on experiences with consistent character appearance.
- Singing avatar generation: With combined image and audio inputs, it supports the generation of realistic singing avatars for entertainment and digital performer use cases.
- Video editing and subject replacement: By using an image and a video as inputs, HunyuanCustom can replace subjects in the video with those from the image, supporting advanced creative editing scenarios.
Accelerated Inference
Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.