Thanks for your inspiring work.

I found the implementation of FON is confusing, which may not what claimed in the paper.

Paper claims

However,

def gen_fon(img, t, t_next, model, alphas_cump, ets):
    t_list = [t, (t + t_next) / 2.0, t_next]
    if len(ets) > 2:
        noise = model(img, t)
        img_next = transfer(img, t, t-1, noise, alphas_cump)
        delta = img_next - img
        ets.append(delta)
    else:
        noise = model(img, t_list[0])
        img_ = transfer(img, t, t - 1, noise, alphas_cump)
        delta_1 = img_ - img
        ets.append(delta_1)

        img_2 = img + delta_1 * (t - t_next).view(-1, 1, 1, 1) / 2.0
        noise = model(img_2, t_list[1])
        img_ = transfer(img, t, t - 1, noise, alphas_cump)
        delta_2 = img_ - img

        img_3 = img + delta_2 * (t - t_next).view(-1, 1, 1, 1) / 2.0
        noise = model(img_3, t_list[1])
        img_ = transfer(img, t, t - 1, noise, alphas_cump)
        delta_3 = img_ - img

        img_4 = img + delta_3 * (t - t_next).view(-1, 1, 1, 1)
        noise = model(img_4, t_list[2])
        img_ = transfer(img, t, t - 1, noise, alphas_cump)
        delta_4 = img_ - img
        delta = (1 / 6.0) * (delta_1 + 2*delta_2 + 2*delta_3 + delta_4)

    img_next = img + delta * (t - t_next).view(-1, 1, 1, 1)
    return img_next

After len(ets) > 2, delta seems only use first order info?

After training a model, how do I create a .ckpt file to use with the sample runner? The training loop writes out .pth files that seem almost correct, but they are slightly mismatched. After a bit of research, it appears that the model is saved with the nn.DataParallel module, but is loaded without it. Reference: https://discuss.pytorch.org/t/solved-keyerror-unexpected-key-module-encoder-embedding-weight-in-state-dict/1686/2

Hey I am back, so i moved the program over to a google colab. Ran this command:

!python main.py --runner sample --method F-PNDM --sample_speed 50 --device cuda --config ddim_cifar10.yml --image_path results --model_path models/ddim_cifar10.ckpt Everything was going fine and then ->

any advice?

Hey :wave: from the diffusers team,

Just wanted to ask if you are interested in adding a link to the diffusers library to your README. We're actively maintaining the PNDM pipeline and also enabled use cases to use PNDM with stable diffusion which might be interesting for readers of this repo.

When integrating the PNDM we made sure to have 1-to-1 the same functionality - do you think such an addition could be useful for the readers of your repo? :-)

Thanks a mille for open-sourcing your method - it has already powered millions of image generations for stable diffusion ;-)