this post was submitted on 06 Mar 2025
5 points (100.0% liked)

Stable Diffusion

4547 readers
15 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 2 years ago
MODERATORS
[email protected]
5
tencent/HunyuanVideo-I2V (huggingface.co)
submitted 2 weeks ago by [email protected] to c/[email protected]
3 comments fedilink hide all child comments
 

FP8 Model: https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main

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

Example ComfyUI workflow: https://github.com/kijai/ComfyUI-HunyuanVideoWrapper/blob/main/example_workflows/hyvideo_i2v_example_01.json

Discord Server: https://discord.com/invite/7tsKMCbNFC

you are viewing a single comment's thread
view the rest of the comments
[โ€“] [email protected] 1 points 2 weeks ago (1 children)

It looks like you need a minimum of 8GB of VRAM for lower resolutions.

[โ€“] [email protected] 2 points 2 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.