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

25 Open 19 Closed
25 Open 19 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

Actual training example config seem to train from scratch. How to fine-tune from pre-trained state of Sana ?
#55 opened Nov 27, 2024 by AfterHAL
Clarify model license
#54 opened Nov 27, 2024 by VMinB12
TypeError: DCAE_HF.__init__() missing 1 required positional argument: 'model_name'
#53 opened Nov 27, 2024 by Aziily
3
Face Distortion Answered Answered the question
#52 opened Nov 27, 2024 by zrealli
1
Metric Evaluation Answered Answered the question
#51 opened Nov 27, 2024 by LWang1016
4
OOM on train on 48GPU with batch 1 proc 1 Answered Answered the question
#49 opened Nov 26, 2024 by recoilme
16
bf16 training Answered Answered the question
#47 opened Nov 26, 2024 by Muinez
12
A training example with at least 2 images is needed. Answered Answered the question
#44 opened Nov 25, 2024 by AfterHAL
3
ImportError: cannot import name 'safety_check' from 'app'
#41 opened Nov 24, 2024 by CRCODE22
1
Too hard to run on win, lol(now available run on windows with custom ComfyUI node) documentation Improvements or additions to documentation fixed fix a bug
#36 opened Nov 24, 2024 by zmwv823
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
colab t4 fixed fix a bug
#33 opened Nov 22, 2024 by werruww
4
not run
#32 opened Nov 22, 2024 by werruww
1
Safetensors?
#28 opened Nov 22, 2024 by Xenodermus
1
Windows support?
#27 opened Nov 22, 2024 by endman100
19
Info about other tokenizer
#26 opened Nov 22, 2024 by chri002
2
Wonderful Work! Adaptation for MacOS and Mobile Devices and Text Rendering Limitations
#24 opened Nov 22, 2024 by viiika
4
The generated 4K images appear somewhat blurry and out of focus.
#14 opened Nov 16, 2024 by i18nsite
3
Add training data
#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
0.6 Billion parameters
#8 opened Oct 23, 2024 by ashrafbay
4
Inquiry about Training Data Used in the Sana Paper and Its Availability
#6 opened Oct 23, 2024 by taki0112
1
Benchmarking
#5 opened Oct 23, 2024 by TomLucidor
4
Pre-emptive Feature anticipation
#4 opened Oct 23, 2024 by TomLucidor
11 tasks
6
The quality of generated character images seems not to be very good？
#3 opened Oct 22, 2024 by wudidiandian
4
ProTip! no:milestone will show everything without a milestone.