improved-diffusion
improved-diffusion copied to clipboard
openai
Release for Improved Denoising Diffusion Probabilistic Models
## Goal We're trying to answer the question, can diffusion models denoise beyond the original level of noise in the dataset? ## Results Extrapolating the time step past 0 doesn't...
I have set the diffusion_step=1000,but the progress has run 10000 steps not stopping. My data_dir has 30000 rgb images. There are my settings： MODEL_FLAGS="--image_size 256 --num_channels 256 --num_res_blocks 2 --learn_sigma...
Thank you so much for the great code. Do any of you know how one can see the intermediate samples in the sampling to see how it "denoises" into the...
hi, thx to your great repo. I have a question about how to train a model use **mpiexec** I searched some infos from the Internet that https://gitee.com/mindspore/docs/blob/r1.2/tutorials/training/source_zh_cn/advanced_use/distributed_training_gpu.md. mpirun -n 16...
Where to set OPENAI_LOGDIR? @longouyang @welinder @JoshuaGross @jietang @esigler
When I'm debugging the image sampler with fewer timesteps (let's say just 2 steps out of 1000), in .ddim_sample(), in the first sampling step, the variable `t` is set to...
If I understand the code correctly, it seems the implementation does not apply the the stratgey in section 4 of the original paper to improve the sampling speed.
I wanted to know how to save the model in checkpoints (.pt) while training. The authors have provided the checkpoints for reference but I want to train from scratch.
