Instructions to use Alpha-VLLM/Lumina-Next-T2I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alpha-VLLM/Lumina-Next-T2I with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Alpha-VLLM/Lumina-Next-T2I", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Can you add an fp8 or int4 quantization loader?
#3
by win10 - opened
Can you add an fp8 or int4 quantization loader?
Please, please let 3050 generate a picture in at least 30 seconds.
We will released int8 or int4 model in the future. please stay tunned.