stablemultidiffusion_pipeline.py code is incomplete about the code that does not apply to the lcm method. Can you provide a copy?

[redredbluee]

stablemultidiffusion_pipeline.py code is incomplete about the code that does not apply to the lcm method. Can you provide a copy? there is something wrong with the scheduler

[ironjr]

Ah, yes. I do have a plan to support other types of acceleration LoRAs (I'm trying Hyper-SD right now).

If you have a list of request for other types of schedulers, please let me know. Thanks!

[redredbluee]

DDIMScheduler

Ah, yes. I do have a plan to support other types of acceleration LoRAs (I'm trying Hyper-SD right now).

If you have a list of request for other types of schedulers, please let me know. Thanks!

Ah, yes. I do have a plan to support other types of acceleration LoRAs (I'm trying Hyper-SD right now).

If you have a list of request for other types of schedulers, please let me know. Thanks!

not using any acceleration, I want to use the normal pipeline with DDIMScheduler, 20-50 step. But the code currently does not support. Does this algorithm require an acceleration solution?

[ironjr]

Ah the algorithm is originally about acceleration stuff, but I will include other standardized samplers as well.
Thanks for the feedback. The update won't take so long.

[redredbluee]

Ah the algorithm is originally about acceleration stuff, but I will include other standardized samplers as well. Thanks for the feedback. The update won't take so long.

This algorithm is great. When the mask area is small during inpainting, I wanted a more detailed and controlled generation, while the result is a bit rough. I'm wandering whether the acceleration affects.

[andupotorac]

Curious if you manage to add support to LCM-LORA. I see this is already supported in the original StreamDiffusion, so shouldn't it work here as well?

[ironjr]

LCM-LoRA's already in support, though I have found that LCM-SDXL has lower quality and relatively severe style leakage issues compared to newer acceleration modules (Lightning/Hyper-SD/etc...). It'll be nice if you suggest more acceleration methods, so I can put them into this :)
And... I am sorry for the late update of DDIMSampler. This should be my top priority.

[andupotorac]

Sure, here are a few accelerators:

• PCM (code not yet live)
• TCD
• DMD2

Also check OneDiff, FaserLCM, DeepCache, if these are useful.

[ironjr]

Copy that!