ksai2324

Results 5 comments of ksai2324

> Also interested in. I tried to combine ControlNet (sd1.5 based) and stable-diffusion-inpainting, I found sd2 based inpainting is not compatible to ControlNet, some layers (to_k, to_v) and n_feature dimension...

I would be also interested in the checkpoint of the model trained only on 256x256 data. It would be nice if you can provide it!

Hello @rose-jinyang did you find a way to do it? I'm also interested in this!

Facing the same problem. @yuxu915 did you manage to solve it?

According to: [issue3367](https://github.com/huggingface/diffusers/issues/3367) `pipeline.unet.load_attn_procs()` takes the path where the **_.bin_** file is stored not the path to **_.bin_** file itself. Changing the input from` "CheapCotton.bin"` to `"/PathToWhereItsStored"` solved this error...