Coming from the diffusers repo about a discussion about how timesteps are chosen for img2img tasks, I was wondering about the reasons for filtering the timesteps based on strength value vs choosing an initial step based on strength and calculating the timesteps from that.
Coming from the diffusers repo about a discussion about how timesteps are chosen for img2img tasks, I was wondering about the reasons for filtering the timesteps based on strength value vs choosing an initial step based on strength and calculating the timesteps from that.
Please see discussion details here:
https://github.com/huggingface/diffusers/issues/7651