Skip to content

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.

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

50 Open 35 Closed
50 Open 35 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

support pipeline parallel
#110 opened Oct 18, 2024 by write3371
当前lumina_next_t2i是否支持batch_size大于1的推断？lumina_next_t2i/sample.py中的batch_size参数似乎没有使用？
#108 opened Aug 21, 2024 by henyilee
run Style-Consistent Generation
#107 opened Aug 15, 2024 by lllrf-xuexi
3
Slow generation on cuda
#106 opened Aug 8, 2024 by OlegRuban-ai
1
Why did you choose FSDP instead of deepseed framework for training? What are the potential problems of deepseed framework for making text graphs?
#105 opened Aug 7, 2024 by heart-du
The total iterations in 256 pretraining stage
#104 opened Aug 1, 2024 by WANGSSSSSSS
Next-DiT-ImageNet checkpoints
#103 opened Jul 29, 2024 by heart-du
2
Could the author release a training script for training LoRA or fine-tuning based on Diffusers?
#102 opened Jul 18, 2024 by wangqixun
1
Request for Guidance on Reproducing Model Architecture for Image Classification
#101 opened Jul 16, 2024 by yardenfren1996
2
This can generate video pictures and 3D models with only a single model, or it needs to be configured separately. Each model is separate and needs to integrate its own functions
#100 opened Jul 14, 2024 by libai-lab
When will the MV-Next-DiT model weights released?
#99 opened Jul 12, 2024 by runzeer
Do you have any plans to accelerate the Lumina model using TensorRT?
#97 opened Jul 9, 2024 by csdY123
1
Is it possible to replace the model's Text Encoder with other models, such as google/gemma-2-9b?
#96 opened Jul 8, 2024 by lymanzhao
it would be cool if you could implement IC-Light for this model
#95 opened Jul 6, 2024 by Manni1000
Lumina-T2X VAE problem
#94 opened Jul 3, 2024 by George0726
3
Expected timeline of T2V model/code release
#92 opened Jun 24, 2024 by kkahatapitiya
1
cutlassF: no kernel found to launch!
#89 opened Jun 22, 2024 by zhuhw19
2
你们有对比多lumina-next-2B模型跟SD3-2B模型的速度吗？我这边跑了下，慢了一倍，会是什么原因呢？
#86 opened Jun 21, 2024 by heart-du
1
有计划，讲SD3的训练配置跟论文中的对齐吗
#83 opened Jun 20, 2024 by heart-du
5
https://huggingface.co/Alpha-VLLM/Lumina-T2Audio is 404
#82 opened Jun 19, 2024 by SoftologyPro
1
ImportError: attempted relative import beyond top-level package
#81 opened Jun 19, 2024 by SoftologyPro
30
LoRA training
#80 opened Jun 19, 2024 by KreischerPanoptic
1
\Lumina-Next-T2I\config.json' is not a valid JSON file.
#74 opened Jun 18, 2024 by danieldietzel
3
What watershed do in precompute_freq_cis function
#73 opened Jun 17, 2024 by yjhong89
1
ComfyUI support?
#68 opened Jun 16, 2024 by GamingDaveUk
7
ProTip! Follow long discussions with comments:>50.