img2vid can we use multi GPUs to speed up inference?

[Khayam Gondal]

Inference takes about 30 minutes for img2vid. Wondering is there a way to leverage multiple GPUs to improve speed? I have 8x 100 GPUs

Currently running using diffusers pipeline

from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained("local/path/stable-video-diffusion-img2vid-xt-1-1")
pipeline(image)

[KazusaKitakawa]

same question

[shiwl0329]

same question

[shiwl0329]

use CUDA_VISIBLE_DEVICES=3,4 python xxx, just use gpu 3