Pinned issues
Issues
- 0
The total iterations in 256 pretraining stage
#104 opened by WANGSSSSSSS - 2
Next-DiT-ImageNet checkpoints
#103 opened by heart-du - 1
Request for Guidance on Reproducing Model Architecture for Image Classification
#101 opened by yardenfren1996 - 1
Could the author release a training script for training LoRA or fine-tuning based on Diffusers?
#102 opened by wangqixun - 2
img2img script generates corrupted images
#98 opened by araleza - 0
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 by libai-lab - 30
- 0
When will the MV-Next-DiT model weights released?
#99 opened by runzeer - 1
- 0
Is it possible to replace the model's Text Encoder with other models, such as google/gemma-2-9b?
#96 opened by lymanzhao - 2
- 3
Any plans integrating to diffusers?
#69 opened by Luciennnnnnn - 0
- 3
Lumina-T2X VAE problem
#94 opened by George0726 - 5
- 7
Lumina Next img2img
#91 opened by thelemuet - 5
t2v timing
#52 opened by BurhanUlTayyab - 1
Expected timeline of T2V model/code release
#92 opened by kkahatapitiya - 1
Error when downloading LuminaModel
#88 opened by ninjasaid2k - 2
cutlassF: no kernel found to launch!
#89 opened by zhuhw19 - 1
Fine-tuning on a 24GB GPU?
#90 opened by araleza - 2
How is captioning labeled for Lumina-T2I models?
#85 opened by nunbuzor - 2
- 1
Image Neural Field
#72 opened by nunbuzor - 1
🍊 Jupyter Notebook
#87 opened by camenduru - 1
- 1
关于训练sd3,出现TypeError: JointTransformerBlock.forward() got an unexpected keyword argument 'offload_to_cpu'
#84 opened by jiashenggu - 5
有计划,讲SD3的训练配置跟论文中的对齐吗
#83 opened by heart-du - 0
About synthetic dataset of T2I
#61 opened by jiashenggu - 1
- 4
- 1
LoRA training
#80 opened by KreischerPanoptic - 2
- 4
Non-Stable Diffusion VAE for commercial usage?
#76 opened by araleza - 4
Gated Llama-2-7b
#79 opened by SoftologyPro - 3
- 8
- 1
- 7
ComfyUI support?
#68 opened by GamingDaveUk - 2
- 3
how to try sd3 sample_sd3.py ?
#66 opened by s9anus98a - 2
- 3
Question about lognorm
#57 opened by jiashenggu - 1
Training details about the t2v model.
#63 opened by HashimotoPatrickMu - 2
ComfyUI support
#58 opened by edwinzeng2005 - 1
conrolnet support?
#59 opened by universewill - 0
what is the funciton of learn_sigma
#56 opened by zhangyongshun - 1
I can't make it work in Colab
#55 opened by Quick-Eyed-Sky - 4
still bad compare to hunyuan dit try this complex violinist prompt, one shot no cherry picking
#53 opened by s9anus98a - 3
text to music demo not working
#51 opened by Muinez