Dhruv Nair

Hi @lamguy can you update to diffusers `0.28.0` and try running ```python from diffusers import StableDiffusionXLPipeline pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/Lykon/dreamshaper-xl-v2-turbo/blob/main/DreamShaperXL_Turbo_V2-SFW.safetensors") pipe.enable_model_cpu_offload() pipe("a painting of a cat", num_inference_steps=20).images[0].save("dreamshaper.png") ```

We don't have access to NPUs in our CI, so I don't think we can add it here.

Hi @huyduong7101 Cross Attention support does exist in the original AnimateDiff codebase, however it isn't actually used in the model. Here `cross_attention_dim` is set to `None` https://github.com/guoyww/AnimateDiff/blob/cf80ddeb47b69cf0b16f225800de081d486d7f21/animatediff/models/motion_module.py#L189 because the block...

Closing this for now. If you have further questions @huyduong7101 please feel free to create a post in the Discussions section.

Closing this as resolved. Feel free to reopen if needed 👍🏽

This is a good point. Ideally how would you like the inspiration button to modify an existing prompt?

Ah I see. I'll try to work on some improvements here this weekend :)

Agree to breaking up by type as well. @yiyixuxu's suggestions make sense to me.

Hi @crapthings based on the traceback, it looks like the CLIP text model weights aren't present your checkpoint?

Is it possible for you to host the `base.safetensors` checkpoint you're using on the HF Hub and share it?