Spaces:
Running on Zero
Apply for a GPU community grant: Academic project
Project: SoulX-FlashHead — Oracle-guided Generation of Infinite Real-time Streaming Talking Heads
SoulX-FlashHead can get 96 FPS, or 3-concurrent real-time(25+ FPS) streaming video-generation on single RTX4090.
We are releasing:
• model weights
• inference pipeline
• web demo
• documentation
The Space will allow researchers, and creators to get experiment with fast and streaming video-generation.
The ZeroGPU resource will only be used for inference in the public demo Space. We will optimize generation latency and queue requests to avoid resource abuse.
Our model is very popular in the community, and we believe that having this live demo will help more people understand and experience this project.
Repository:
https://huggingface.co/Soul-AILab/SoulX-FlashHead-1_3B
Hi @JokerZhou , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.
If you can, we ask that you upgrade to Enterprise to enjoy higher ZeroGPU quota and other features like Dev Mode, Private Storage, and more: hf.co/enterprise