Bagheera
Bagheera
have you experimented with models that use non-linear noise schedules such as CosXL or DeepFloyd, both of which use cosine but with deepfloyd's differing in that it's not cosine-continuous but...
are you on 14.4? i've been using pytorch 2.2 and i get about 10 seconds per step with 1 megapixel images on a M3 Max 128G. do you observe any...
also, in my environment, i've been running with `--mixed_precision=fp16` but i'm not sure why that's erroring out for you the way it is. the code only returns an error to...
are you running the latest main branch?
#7530 might fix this one @sagargulabani
@sagargulabani i've updated that script in particular for that PR. it now uses native_amp = False in the Accelerator config. can you please re-run with that change? i will put...
was there more to the traceback before that one? that's the traceback from Accelerate, but the one from the trainer is needed to know where this error originated. i believe...
@sayakpaul i think i'm in a bit of a need of rescuing on this issue. do you have an ideas how to proceed? maybe a dummycast wrapper in train utils...
i'm able to reproduce this one locally, but it's not clear why it's happening. the text encoder hidden states are fp16, the noisy inputs are fp16. i can train locally...
it's been complicated to do in a non-invasive way for the diffusers project. for now, i've been running dreambooth via [simpletuner](https://github.com/bghira/SimpleTuner) for the last few days successfully, introducing single subjects...