Details on the code used to produce and use this model are available at:
https://github.com/schrum2/MarioDiffusion
That repo has instructions to check out this model and apply it to the generation of Super Mario Bros. level scenes. There is also an interactive GUI for constructing complete levels out of model-generated scenes.
This model makes use of https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5 as a text embedding model for use with diffusion to generate Mario levels. Mario captions consist of multiple period-separated phrases, and this model creates a separate text embedding for each phrase when training the diffusion model.
To see a model using Alibaba-NLP/gte-large-en-v1.5 that embeds the whole caption as a single embedding, see https://huggingface.co/schrum2/MarioDiffusion-GTE-single-regular0. To see a model that uses a simple token-based transformer model for text embedding, see https://huggingface.co/schrum2/MarioDiffusion-MLM-regular0.
- Downloads last month
- -