FDM
FDM copied to clipboard
The official PyTorch implementation of Fast Diffusion Model
when I run : ``` torchrun --standalone --nproc_per_node=4 train.py --outdir=training-output \ --data=datasets/ffhq-64x64.zip --cond=0 --arch=ddpmpp \ --batch=256 --cres=1,2,2,2 --lr=2e-4 --dropout=0.05 --augment=0.15 \ --precond=fdm_edm --warmup_ite=800 --fdm_multiplier=1 ``` it appear: untimeError: params[127] in...
Hello, thanks to your sharing the codes. I have read some codes and I find the difference between FDM and EDM is the loss function. Have you modified any other...
Hello, thanks for your paper. I have a small question. Is your paper applicable for text2image networks? Concrete for Classifier Free Guidance. Can FDM precondition be used for conditional input...