Instructions to use Alpha-VLLM/Lumina-Image-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Alpha-VLLM/Lumina-Image-2.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Alpha-VLLM/Lumina-Image-2.0", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
need 4 step solution.
#12
by pikkaa - opened
any chance of running this with 4 steps ?
We are experimenting 4-step distillation solutions same as FLUX-snell. We will share new results once experiment is done. The current model is a naive base model which requires up to 50 iterations for stable and superior performance.