Describe the bug
Like cross_attention_kwargs in UNet, I want to modify the attention processor of the FLUX model, and pass the extra parameter by the joint_attention_kwargs which written in the FluxPipeline:
noise_pred=self.transformer(
hidden_states=latents,
timestep=timestep/1000,
guidance=guidance,
pooled_projections=pooled_prompt_embeds,
encoder_hidden_states=prompt_embeds,
txt_ids=text_ids,
img_ids=latent_image_ids,
joint_attention_kwargs=self.joint_attention_kwargs, # herereturn_dict=False,
)[0]
But it doesn't work. I read the resourse code and find that the joint_attention_kwargs is not passed to the inner blocks of the transformer.
https://github.com/huggingface/diffusers/blob/28f9d84549c0b1d24ef00d69a4c723f3a11cffb6/src/diffusers/models/transformers/transformer_flux.py#L495C1-L500C18
we can find that joint_attention_kwargs is missing!
Reproduction
not needed
Logs
No response
System Info
diffusers 0.31.0.dev0
Who can help?
@yiyixuxu
Describe the bug
Like
cross_attention_kwargsin UNet, I want to modify the attention processor of the FLUX model, and pass the extra parameter by thejoint_attention_kwargswhich written in the FluxPipeline:But it doesn't work. I read the resourse code and find that the
joint_attention_kwargsis not passed to the inner blocks of the transformer.https://github.com/huggingface/diffusers/blob/28f9d84549c0b1d24ef00d69a4c723f3a11cffb6/src/diffusers/models/transformers/transformer_flux.py#L495C1-L500C18
we can find that
joint_attention_kwargsis missing!Reproduction
not needed
Logs
No response
System Info
diffusers 0.31.0.dev0
Who can help?
@yiyixuxu