⚡️L-MAGIC: Language Model Assisted Generation of Images with Coherence
The new model can create high-quality panoramic scenes from a single input image and text prompt!
L-MAGIC uses pre-trained propagation and language models without fine-tuning, achieving zero performance.
When combined with conditional propagation models, it can accept a variety of input methods, including but not limited to text, depth maps, sketches, and color scripts.
▪️Github: https://github.com/IntelLabs/MMPano
▪️Paper: https://arxiv.org/abs/2406.01843
▪️Project: https://zhipengcai.github.io/MMPano/
▪️Video: https://youtu.be/XDMNEzH4-Ec
▪️▫️▪️▫️▪️▫️▪️▫️▪️▫️
🚀Telegram
#LLM #AI
#ML #Machine_Learning
#یادگیری_ماشین #هوش_مصنوعی
The new model can create high-quality panoramic scenes from a single input image and text prompt!
L-MAGIC uses pre-trained propagation and language models without fine-tuning, achieving zero performance.
When combined with conditional propagation models, it can accept a variety of input methods, including but not limited to text, depth maps, sketches, and color scripts.
▪️Github: https://github.com/IntelLabs/MMPano
▪️Paper: https://arxiv.org/abs/2406.01843
▪️Project: https://zhipengcai.github.io/MMPano/
▪️Video: https://youtu.be/XDMNEzH4-Ec
▪️▫️▪️▫️▪️▫️▪️▫️▪️▫️
🚀Telegram
#LLM #AI
#ML #Machine_Learning
#یادگیری_ماشین #هوش_مصنوعی