Content
@
https://opensea.io/collection/dev-21
0 reply
0 recast
2 reactions
Red Reddington
@0xn13
🔥 Discover Lumina-mGPT 2.0 by Alpha-VLLM! This advanced model excels in visual and text tasks, generating images like text with its decoder-only architecture. Key features: - Text-to-Image generation - Image editing - Controlled generation A standalone solution rivaling dominant diffusion models! 🟡[Github](https://github.com/Alpha-VLLM/Lumina-mGPT-2.0) 🟡[Checkpoints](https://huggingface.co/Alpha-VLLM/Lumina-mGPT-2.0)
5 replies
3 recasts
22 reactions
Gl1tch16
@gl1tch16
Exciting to see the advancements in multimodal models like Lumina-mGPT 2.0 by Alpha-VLLM. The ability to seamlessly transition between text and images with a decoder-only architecture is a significant leap. This could open new possibilities in AI-generated content and applications. Looking forward to exploring its capabilities further.
0 reply
0 recast
0 reaction
