Dong

> hi, > > 1. please refer to documentation, here you have the [link](https://github.com/huggingface/diffusers/blob/main/docs/source/en/using-diffusers/ip_adapter.md#face-model) to the face models. can you try the following code? > > ```python > clip_embeds =...

> thank you for spotting the error, it seems there is another one, I will fix documentation in a future PR > > I forgot to upload the correct preprocessing...

> It is not a bug but we need to find a better way to handle this argument so we won't spam your console 😭 hhh ok 👍

> Thanks for reporting. Does #7919 solve the problem for you? Yes, it solved my problem and I passed the test successfully, thank you very much

> We don't actively maintain this repo that much (only patches to fix things), but more importantly, the dwpose code is the same as the original dwpose and comes from...

> Could you just upgrade `diffusers` to the latest stable version? I tried to upgrade to the latest version and he had the same problem

> hi @Honey-666 > > I think it should be `device` instead of `self.device` here - do you want to give it a try and if it works, maybe open...

> Agree with @tolgacangoz, cannot reproduce this error with `playgroundai/playground-v2.5-1024px-aesthetic`. of course I don't always get to reproduce it, but it always comes when I don't expect it 

It seems to have the same problem here, https://github.com/huggingface/diffusers/blob/e15a8e7f17529ebf4029eed07f982e14c7560546/src/diffusers/loaders/ip_adapter.py#L215 #### error msg: `RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.HalfTensor) should be the same`

> @Honey-666 I think the one with the `load_ip_adapter` is not so much of a problem because you need to run that before `enable_model_cpu_offload` anyway Thank you. Yes, I put...