Closed isamu-isozaki closed 10 months ago
+1
I made a blog here for my notes on how the rectified flow works and what needs to be done for this PR. I was wrong in that this will probably need to be a community example in itself so might not finish within October
The preliminary TODO list I have is
@patrickvonplaten Hi! Do you think this should be 3 separate PRs?
@isamu-isozaki Go for it 👍🏽 If you're adding to the examples folder I thinking you can make it a single PR.
I finished making the dataset part. I am currently doing reflow and for log_validation, I think I will need a new scheduler for this which just adds the output of the unet /total timesteps to the latent.
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.
Please note that issues that do not follow the contributing guidelines are likely to be ignored.
I finished making the dataset part. I am currently doing reflow and for log_validation, I think I will need a new scheduler for this which just adds the output of the unet /total timesteps to the latent.
hey, hows it going, got a model now?
@spacewalkingninja Ah I made a training colab for a lora version and training rectified flows. I did notice the loss goes down but haven't tested for that much longer training yet. Honestly, if anyone can run this for a while that'll be great. I will be running on my end too
It's really helpful, thanks.
Is your feature request related to a problem? Please describe. For hacktoberfest, I wanted to add in the Rectified Flow training objective which is what the instaflow paper, which can generate images in one forward pass, used to finetune stable diffusion.
Describe the solution you'd like I'll make a small pr and argument to examples/text_to_image based on code from here to examples/text_to_image loss. I'm thinking of testing it out with mnist to see if it works.
Additional context The links to the papers: instaflow rectified flow