v-diffusion-pytorch

v-diffusion-pytorch copied to clipboard

Hello, thank you for your great work! I have a little puzzle in sample.py `# Get the model output (v, the predicted velocity) with torch.cuda.amp.autocast(): v = model(x, ts *...

zhangquanwei962

mark down format.

eltociear

Thanks very much for your pretrained model. How long does it take to train on wikiarts-256？

Josh00-Lu

Hey @crowsonkb , This is a quick PR that adds two files so that people can use [cog](https://github.com/replicate/cog) to easily try out the CFG diffusion model. It also can then...

dashstander

add colab callback function for display, auto download model checkpoints, and colab notebook

2

- added 2 functions for cfg_sample and clip_sample, which allows calling from colab (ipython display cannot show content when using the "!" magic in notebooks) - added a callback function...

EleaZhong

split up sample() to allow backwards pass

1

This refactor takes the existing sample() call and splits it into subroutines disabling `@torch.no_grad()` to enable optimisation of `x`. Could be further cleaned up, but this version is working well...

dribnet

AlexWortega

Thanks for sharing such an amazing repo! I am testing a prompt like openAI “an astronaut riding a horse in a photorealistic style” to compare. But somehow the iterations seems...

alelordelo

[Question] Questions about `zero_embed` and `weights`

4

Thanks for this great work. I'm recently interested in using diffusion model to generate images iteratively. I found your script `cfg_sample.py` was a nice implementation and I decided to learn...

Karbo123

Hi! I wanted to thank you for your work, especially since without you DiscoDiffusion wouldn't exist ! Still, I was wondering if you had the metrics (Precision, Recall, FID and...

Maxim-Durand