guided-diffusion
guided-diffusion copied to clipboard
openai
Thank you so much for releasing this code! I am wondering how to train the model on images that have multiple labels? In my understanding, the formulation (2) --- pθ,φ(xt|xt+1,...
Hi, big fan of your work here, the results are amazing! Also, thank you for including the table on the compute comparison; these are rare to see :) I wondered...
I seem to keep getting enumerate errors. IndexError: list index out of range And the code with problems is in this range: **for j, sample in enumerate(samples):** cur_t -= 1...
Any suggestions for how to achieve this? Working on CLIP guided generation and would like to try with 512x512.
They don't seem to be documented either in this repo or in improved-diffusion. I'd like to match the training flags as closely as possible when fine-tuning (I'm trying to fine-tune...
Does the `**num_samples**` affects the FID? I performed the sampling operation on the model **lsun_bedroom.pt** provided in the paper and then evaluated the generated .npz against the reference file **VIRTUAL_lsun_bedroom256.npz**...
how long to train 256x256 on LSUN bedrooms dataset, 1000steps? how many days？ I use 4*3090 with microbatch 4 
Thanks a lot for your awesome work! I follow your setting to sample 50k imagenet64 images and calculate the FID results using `evaluations/evaluator.py`, but I got FID . And I...
Hi, in [script_util.py](https://github.com/openai/guided-diffusion/blob/main/guided_diffusion/script_util.py) when you create the model/classifier (line 148, 238 & 353) you support the image sizes of 512, 256, 128 and 64 by specifying the channel_mult. How have...
I want to generate samples interpolated by 2 images, is it covered by the codebase?
