Alpha-VLLM/Lumina-mGPT
Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"
Python
Issues
- 1
- 1
cannot generate 256*256 images?
#20 opened by zhangzheyu0 - 1
- 1
VQGAN models dont exist
#5 opened by gjnave - 1
Trainable Parameters and their precisions
#17 opened by SxJyJay - 1
- 2
problem with Image editing
#16 opened by chkmook - 3
Save ckpt error
#18 opened by SxJyJay - 2
WeChat链接更新
#12 opened by BeBuBu - 5
Training Scrip Error: AttributeError: 'ChameleonRMSNorm' object has no attribute 'reset_parameters'. Did you mean: 'get_parameter'?
#14 opened by SunzeY - 0
Code for fine-tuning Chameleon
#15 opened by Johanan528 - 6
Potential bug on z-loss calculation
#13 opened by leloykun - 5
3 x Black and White output
#11 opened by Excidos - 2
flash_attn_2_cuda error
#9 opened by abrakjamson - 2
- 1
Has the lumina-mGPT done any quantitative evaluation on generation or VLM benchmark?
#7 opened by muxizju - 1
- 2
Gradio launches public/live by default
#3 opened by throttlekitty - 3
- 0
What is the scale of the training data, training machine and training time for the 7B and 30B model
#6 opened by zhengyunqq