Open neuron-party opened 1 month ago
essentially the title. i've tried the following:
transformer = diffusers.Flux2DTransformer.from_single_file(path_to_kohya_safetensors, torch.dtype=torch.bfloat16) pipeline = diffusers.FluxPipeline.from_pretrained(..., transformer=transformer, torch.dtype=torch.bfloat16)
however all generated images have weird artifacts, regardless of checkpoint number i've tried with both lr 1e-5 and 1e-4
@kohya-ss
Sorry, I seem to have overlooked the issue. Does the safetensors work with other inference environments, such as ComfyUI or flux_minimum_inference.py?
essentially the title. i've tried the following:
however all generated images have weird artifacts, regardless of checkpoint number i've tried with both lr 1e-5 and 1e-4