inference speed

#2
by hp47 - opened

as you report: Inference Speed: ~2-3 seconds per image (40 steps, RTX 4090)。in my test, even remove 'negative_prompt', the original qwen-edit-2509 takes ~40-50 seconds to edit an image (40steps, A100).
how could u be so fast?

We were using our own inference framework, and kuan-wang has reported the speed on H100s.

Eigen AI org

Oh, thanks for pointing out the typo, will fix.

Eigen AI org

On a standard H100 GPU running in FP16 precision with DiffSynth, inference takes approximately 1.1 seconds per step, resulting in a total runtime of about 43 seconds for 40 steps.

jinleic changed discussion status to closed

Sign up or log in to comment