search

TencentARC / T2I-Adapter

T2I-Adapter
3.38k stars 198 forks source link

Errors when trying the Style Adapter (and color Adapter) #32

Open trendland opened 1 year ago

trendland commented 1 year ago

Trying to do a style transfer with Model checkpoint SD 1.5 They are both loading about 50% and then these two errors :/ Any help would be great as I would really like to try these style transfers

ControlNet 0: Preprocessor: Canny -- Model: control canny ControlNet 1: Preprocessor: Clip_vision -- Model: T2iadapter_style_sd14V1

RuntimeError: !(has_different_input_dtypes && !config.promote_inputs_to_commondtype && (has_undefined_outputs || config.enforce_safe_casting_tooutput || config.cast_common_dtype_tooutputs)) INTERNAL ASSERT FAILED at "/Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/TensorIterator.cpp":407, please report a bug to PyTorch.

Error with Color Adapter

Controlnet 0: Preprocessor: Canny -- Model: control canny ControlNet 1: Preprocessor: Clip_vision -- Model: T2iadapter_color_sd14V1

RuntimeError: pixel_unshuffle expects height to be divisible by downscale_factor, but input.size(-2)=257 is not divisible by 8

Thank you!

ptppan commented 1 year ago

Yeap I'm getting a similar issue:

RuntimeError: [srcBuf length] > 0 INTERNAL ASSERT FAILED at "/Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/native/mps/OperationUtils.mm":277, please report a bug to PyTorch. Placeholder tensor is empty!

Any time I try to use the t2i style adapter on controlnet with A1111.