To those who have issues adapting it with Diffuersers version>=11.0 about prompt-to-prompt HOT 10 CLOSED

@moonnnpie in the ptp_util.py, omit extra_set_kwargs = {"offset": 1}, and change model.scheduler.set_timesteps(num_inference_steps, **extra_set_kwargs) to model.scheduler.set_timesteps(num_inference_steps). This error is because in the previous diffusers, scheduler's set_timesteps function has a param offset.

from prompt-to-prompt.

ok fixed my case by reversing the advice - renamed the stuff in register_attention_control function.
context => encoder_hidden_states, mask => attention_mask, CrossAttention => AttentionBlock

from prompt-to-prompt.

On latest 0.13.1 diffusers version I had to:
rename context => encoder_hidden_states, mask => attention_mask, self.reshape_heads_to_batch_dim -> self.head_to_batch_dim, self.reshape_batch_dim_to_heads -> self.batch_to_head_dim in register_attention_control and it started working correctly

from prompt-to-prompt.

i also use 0.13.1 diffusers version but got a problem

TypeError: PNDMScheduler.set_timesteps() got an unexpected keyword argument 'offset'

how should i fix it

from prompt-to-prompt.

@eps696 I followed your advice, but found if change CrossAttention to AttentionBlock, the attention_store would be none. So in my case, I renamed context and mask, and stay with CrossAttention.

from prompt-to-prompt.

hello, could you explain this issue a bit more?
i believe i have run into it in some "updated" form, getting the error forward() got an unexpected keyword argument 'encoder_hidden_states' when running register_attention_control on null-inversion - yet i don't quite catch what and where should be changed to avoid that. do you mean changing the original diffusers code?

from prompt-to-prompt.

@liangbingzhao @bonlime you are definitely right, i didn't notice that changing the block effectively disabled main workflow. yet the CrossAttention refactoring after 0.11.1 was quite gross, so i'm afraid more issues might appear

from prompt-to-prompt.

@liangbingzhao thanks a lot

from prompt-to-prompt.

Hi, all, I have tried to port to diffusers==0.14.0, there is no runing error, but the result is actually bad...
https://github.com/JiauZhang/prompt-to-prompt for now, I just simple replace attention map.
Could anyone give me some advice？

from prompt-to-prompt.

Hi, all, I have tried to port to diffusers==0.14.0, there is no runing error, but the result is actually bad... https://github.com/JiauZhang/prompt-to-prompt for now, I just simple replace attention map. Could anyone give me some advice？

Is it solved?

from prompt-to-prompt.