tencent/HunyuanVideo-I2V

⁨4⁩ ⁨likes⁩

Submitted ⁨⁨3⁩ ⁨weeks⁩ ago⁩ by ⁨Even_Adder@lemmy.dbzer0.com⁩ to ⁨stable_diffusion@lemmy.dbzer0.com⁩

https://huggingface.co/tencent/HunyuanVideo-I2V

FP8 Model: huggingface.co/Kijai/HunyuanVideo_comfy/…/main

ComfyUI nodes (updated wrapper): github.com/kijai/ComfyUI-HunyuanVideoWrapper

Example ComfyUI workflow: github.com/kijai/…/hyvideo_i2v_example_01.json

Discord Server: discord.com/invite/7tsKMCbNFC

Comments

Sort:hotnew top

antipiratgruppen@lemmy.dbzer0.com ⁨3⁩ ⁨weeks⁩ ago
This looks great! Any idea of realistic hardware requirements?

source
- Even_Adder@lemmy.dbzer0.com ⁨3⁩ ⁨weeks⁩ ago
  It looks like you need a minimum of 8GB of VRAM for lower resolutions.
  
  source
  - antipiratgruppen@lemmy.dbzer0.com ⁨3⁩ ⁨weeks⁩ ago
    Thank you. I just found this additional info on huggingface:
    
    An NVIDIA GPU with CUDA support is required.
    
    The model is tested on a single 80G GPU.
    
    Minimum: The minimum GPU memory required is 60GB for 720p.
    
    Recommended: We recommend using a GPU with 80GB of memory for better generation quality.
    
    source