-
Notifications
You must be signed in to change notification settings - Fork 80
Issues: Alpha-VLLM/Lumina-T2X
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
What dataset was used to train the video generation model?
#15
by Dibbidy
was closed May 11, 2024
updated May 11, 2024
Can you tell me the compute requirements for inference and training?
#14
by ninjasaid2k
was closed May 11, 2024
updated May 11, 2024
about alignment evaluation or prompt following study?
#16
by BruceLeeeee
was closed May 11, 2024
updated May 11, 2024
Distributed package doesn't have NCCL built in
#17
by Bigfield77
was closed May 13, 2024
updated May 13, 2024
“unexpected keyword argument 'max_seq_len'” in model initialization in train.py
#10
by BruceLeeeee
was closed May 13, 2024
updated May 13, 2024
Questions about next line / next frame token
#24
by yjhong89
was closed May 14, 2024
updated May 14, 2024
About data spec used for training Lumina-T2A
#33
by lisle-joyeux
was closed May 17, 2024
updated May 17, 2024
Showcase lumina-t2x on Huggingface Spaces with get free GPU grant(A100s)
#28
by yvrjsharma
was closed May 29, 2024
updated May 29, 2024
Training scripts hangs early at "Initializing pipeline" line with GPUs running at 100% when GPU number > 1
#47
by megatomik
was closed May 31, 2024
updated Jun 2, 2024
what is the funciton of learn_sigma
#56
by zhangyongshun
was closed Jun 12, 2024
updated Jun 12, 2024
Why are you using logit-normal sampling only for ImageNet experiment
#62
by Luciennnnnnn
was closed Jun 14, 2024
updated Jun 14, 2024
Do you think using a vae with more channels is good?
#60
by Manni1000
was closed Jun 15, 2024
updated Jun 15, 2024
Why doesn't inference time increase with pixel area?
#65
by jiashenggu
was closed Jun 18, 2024
updated Jun 18, 2024
Non-Stable Diffusion VAE for commercial usage?
#76
by araleza
was closed Jun 19, 2024
updated Jun 19, 2024
Hi , when T2A model? also T2Music? best regards
#45
by researcher48
was closed Jun 19, 2024
updated Jun 19, 2024
Are Lumina-T2Audio and Lumina-T2Music the same?
#77
by researcher48
was closed Jun 19, 2024
updated Jun 19, 2024
关于训练sd3,出现TypeError: JointTransformerBlock.forward() got an unexpected keyword argument 'offload_to_cpu'
#84
by jiashenggu
was closed Jun 20, 2024
updated Jun 20, 2024
Previous Next
ProTip!
no:milestone will show everything without a milestone.