Omer Bar Tal
Omer Bar Tal
> hi Adam, > > You get that warning because the current implementation of the `bubble` and `triangle` functions doesn't center the values properly when sigma is even. > >...
Hi, thank you for the answer. just to make sure I get it right - isn't sigma only relevant for the choice of neurons to update in each step?
So if sigma < 1 implies updating only the winner, then why should I expect different values in that range to lead to different results (since anyway only the winner...
Hi! any chance that you can please share the linux compatible implementation of the Gaussians? @alessiapacca
Hi, what torch version are you using? it shouldn't happen with the versions specified in the requirements file, but you can also try to comment out [this line](https://github.com/omerbt/Text2LIVE/blob/8144c003c5e74a6145a864b9a72af2358c8c2ca4/CLIP/clip_explainability/auxilary.py#L16).
Hi! indeed as @sayakpaul mentioned, even though StableDiffusion can technically process higher resolution images, we observed that many times it produces poor quality outputs (it is out-of-distribution w.r.t its training...
Please note that by default, the bootstrapping parameter is set to 20, as in the application of tight masks. The high bootstrapping parameter encourages high-fidelity to accurate segmentation masks, but...
Hi try to upgrade the `diffusers` package version
Hi, sure -- the implementation can be found [here](https://huggingface.co/spaces/weizmannscience/multidiffusion-region-based/blob/7c13d190c4677c7bcd1dd29ff5ed4540057b1a4d/region_control.py#L134)