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
When I run in comfyui
#10
by layde - opened
ERROR: Could not detect model type of: E:\ComfyUI-aki\ComfyUI-aki-v1.4 2024\models\checkpoints\lumina_2.safetensors
same Q
Hello, it seems you are not using the latest official comfyui https://github.com/comfyanonymous/ComfyUI. Please use this latest version.
same Q when using last version
Well, even my customized model with baked in different Gemma works (not well, but works). Soo.. you guys are probably doing something wrong. Using latest ComfyUI and their example workflow for Lumina.
https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/tree/main/example%20workflow
That one.