Lumina-Image 2.0
An open-source AI image generation framework runs locally, supports ComfyUI and Diffusers, and includes fine-tuning and LoRA tools.
Lumina-Image 2.0 generates images from text on your own hardware. It's for developers, researchers and people who want a model they can use in visual workflows or adapt with their own image collections.
- Image generation: Generate images from text with downloadable model checkpoints, including batch generation for collections of prompts.
- Workflow integrations: Use the model through ComfyUI, integrate it into Python applications with Diffusers, or access generation through a Gradio web interface.
- Model adaptation: Fine-tune on image and text pairs or use LoRA to adapt the model.
The framework is open source under Apache 2.0 and supports generation from local checkpoint files, including .pth weights. It uses Gemma-2-2B as its text encoder and FLUX-VAE-16CH for image encoding and decoding. Access to Gemma-2-2B requires Hugging Face authentication.
Logotyper
