Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CLIP for Training #7

Open
pizzabug opened this issue Dec 30, 2022 · 0 comments
Open

CLIP for Training #7

pizzabug opened this issue Dec 30, 2022 · 0 comments
Labels
core-feature

Comments

@pizzabug
Copy link
Owner

pizzabug commented Dec 30, 2022 •
edited
Loading

Use CLIP with diffusion model. This helps abstract the lack of data by relying on CLIP to generate image embeds. It may be possible to approach the problem by training images on image-loss pairs generated by the CLIP model.
@pizzabug pizzabug changed the title CLIP for Adversarial Training CLIP for Training Jan 2, 2023
pizzabug added a commit that referenced this issue Jan 10, 2023
@pizzabug
feat: Begin implement CLIP model. [#7]
49082fb
pizzabug added a commit that referenced this issue Jan 11, 2023
@pizzabug
feat: Implement basic datasets for CLIP [#7]
d7b0b0b
pizzabug added a commit that referenced this issue Jan 11, 2023
@pizzabug
feat: Implemented training w/ CLIP input. [#7]
fb18abc
pizzabug added a commit that referenced this issue Jan 12, 2023
@pizzabug
feat: Add device picking, fixed encoder. [#7]
7943915
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
core-feature
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@pizzabug