search

tencent-ailab / V-Express

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.
2.03k stars 250 forks source link

What is the Memory Requirement? Will 10gb be enough? #17

Open oisilener1982 opened 1 month ago

oisilener1982 commented 1 month ago

Will my RTX 3080 with just 10gb of memory work? Thanks in advance

tiankuan93 commented 1 month ago

In a V100 machine, the following script requires 9873M GPU memory. Please feel free to have a try. Or you can use a shorter audio. For an audio of about 2 seconds, that's roughly 9253M.

python inference.py \
    --reference_image_path "./test_samples/short_case/AOC/ref.jpg" \
    --audio_path "./test_samples/short_case/AOC/aud.mp3" \
    --kps_path "./test_samples/short_case/AOC/kps.pth" \
    --output_path "./output/short_case/talk_AOC_no_retarget.mp4" \
    --retarget_strategy "no_retarget" \
    --num_inference_steps 25
nitinmukesh commented 4 weeks ago

Will my RTX 3080 with just 10gb of memory work? Thanks in advance

I tested on 8 GB VRAM (RTX 4060), works absolutely fine