Repository · GitHub

lucidrains/transfusion-pytorch

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

View on GitHubReport an issue

Owner	lucidrains
License (as declared)	MIT
Stars	1,405
Forks	76
Main language	Python
Created	23 August 2024
Last updated at source	4 September 2026

pythonartificial-intelligenceattentiondeep-learningflow-matchingmulti-modaltransformers

Embed this entry

<iframe src="https://silytics.si/embed/item/14e5cc5f-07d4-424a-b3cb-e10af3d2cc69" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from lucidrains

vit-pytorchRepository
DALLE2-pytorchRepository
denoising-diffusion-pytorchRepository
imagen-pytorchRepository
PaLM-rlhf-pytorchRepository
x-transformersRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.