Aray Karjauv

@houqp any news about cuda + cudnn + opengl?

where can I find the weights?

I found the weights in a nearby [repository](https://github.com/CompVis/latent-diffusion#inpainting): ```bash wget -O models/ldm/inpainting_big/last.ckpt https://heibox.uni-heidelberg.de/f/4d9ac7ea40c64582b7c9/?dl=1 ```

> this link doesnt seem to be working anymore, anybody got an updated link? There is also a [download script](https://github.com/CompVis/stable-diffusion/blob/main/scripts/download_models.sh#L12): ```bash wget -O models/ldm/inpainting_big/model.zip https://ommer-lab.com/files/latent-diffusion/inpainting_big.zip ``` but I didn't try...

> So hold on, someone said we could use the SD model, but then that didn't work, so people started downloading the old LDM model for inpainting? SD is based...

Do I have to use the `sd-v1-4.ckpt` weights for the [inpaint.py](https://github.com/CompVis/stable-diffusion/blob/main/scripts/inpaint.py) example?

> I think this is a different model that doesn't have the weights released yet. I handled it. [Here](https://github.com/CompVis/stable-diffusion/issues/17#issuecomment-1224165074) is what I did.

Thank you for the fast reply. I tried your workaround but the resolution was set with different values: ``` $ exiftool slide.tiff ... X Resolution : 0.009999999776 Y Resolution :...

I use OpenSlide and according to the [docs](https://digitalslidearchive.github.io/HistomicsTK/examples/using_large_image.html#getMetadata()), > `mm_x, mm_y` - width and height of a pixel in millimeters at the base resolution. so I think, you are right....

Yes, I think I solved my problem. Your [comment](https://github.com/libvips/pyvips/issues/164#issuecomment-595310955) from another discussion helped me