Dhruv Nair

Hi @crapthings it appears that the `cond_stage_model.transformer.text_model.embeddings.position_ids` key is missing from your checkpoint, which is what `from_single_file` in `0.28.0` uses to identify the CLIP model in the checkpoint. Did you...

@crapthings No it shouldn't affect the quality. I've opened a PR with a fix as well.

@crapthings could you try installing diffusers from main and see if the issue persists?

Closing as completed.

cc: @a-r-r-o-w Can you take a look here

Hi @hyunW3 I'm unable to reproduce this using a T4 GPU. Are you running on a machine with low RAM?

Hi @hardikdava The Flux Control Pipelines are meant to be used with Flux Control Models. Can you try changing your pipeline to the FluxFillPipeline.

Is there an example of Flux Fill working with Control LoRAs that you are trying to replicate? Off the top of my head I'm not sure how well this approach...

I don't think a Control LoRA would work here. We could look into adding a ControlNet support for Flux Fill. cc'ing: @asomoza to get his thoughts on this.

Hi @KaiWU5 I think this question would be better to ask in the Discussions section.