Skip to content

Issues: NVlabs/Sana

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

23 Open 55 Closed
23 Open 55 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How much training data was used to train Sana? Answered Answered the question
#95 opened Dec 17, 2024 by omrastogi
1
Awful Image Generation Answered Answered the question
#93 opened Dec 17, 2024 by shaun-ba
8
Problem launching training with less GPUs Answered Answered the question
#92 opened Dec 15, 2024 by AfterHAL
1
Why is the flow-DPM Solver so much worse than Euler's method in my flow matching model. FID become very large when use it Answered Answered the question
#91 opened Dec 14, 2024 by lllzzz3
3
Sana models in PixArt
#89 opened Dec 13, 2024 by srikarym
1
Request for training to use jpg and jpeg dataset source format (in addition to png). Answered Answered the question
#84 opened Dec 12, 2024 by AfterHAL
10
Sana finetuned example documentation Improvements or additions to documentation
#74 opened Dec 6, 2024 by recoilme
3
Controlnet Support Answered Answered the question
#73 opened Dec 6, 2024 by Oguzhanercan
4
Wrong epoch count on training (Bug?)
#71 opened Dec 5, 2024 by AfterHAL
1
Sana checkpoint trained with SD-3 VAE
#70 opened Dec 4, 2024 by srikarym
2
官方提供的api文档里面的示例无法成功运行 Answered Answered the question
#68 opened Dec 4, 2024 by forjone
4
dc-ae and text-encoder load Answered Answered the question
#67 opened Dec 4, 2024 by wanglaofei
2
Sana Training time limit & epochs saved at every step (bug)
#62 opened Dec 3, 2024 by AfterHAL
11
lora train? Answered Answered the question
#61 opened Dec 3, 2024 by Deng-Xian-Sheng
4
Face Distortion Answered Answered the question
#52 opened Nov 27, 2024 by zrealli
11
bf16 training Answered Answered the question
#47 opened Nov 26, 2024 by Muinez
20
Runpod.io template for it so that anyone can use it no matter what computer they have documentation Improvements or additions to documentation
#35 opened Nov 24, 2024 by mp3pintyo
5
Info about other tokenizer Answered Answered the question
#26 opened Nov 22, 2024 by chri002
4
The generated 4K images appear somewhat blurry and out of focus.
#14 opened Nov 16, 2024 by i18nsite
3
Add training data documentation Improvements or additions to documentation
#13 opened Nov 7, 2024 by ashrafbay
1
Image style When you select "Anime" in , cold blue shadows are emphasized due to the influence of PAG Guidance Scale.
#9 opened Oct 25, 2024 by haruharu-1105
6
Benchmarking
#5 opened Oct 23, 2024 by TomLucidor
4
Pre-emptive Feature anticipation Answered Answered the question working working on this issue
#4 opened Oct 23, 2024 by TomLucidor
11 tasks
11
ProTip! Follow long discussions with comments:>50.