[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".
Utilize a unified image tokenizer for improved understanding and generation of images from text descriptions.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".
TokenFlow has 464 stars on GitHub. It has been forked 10 times. TokenFlow is written mainly in Python. It has been in active development since 2024. TokenFlow is available under the Apache-2.0 license. Its main topics are large-language-models, multimodal-understanding, text-to-image-generation, vector-quantization.
[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".
TokenFlow is an open-source project. It is released under the Apache-2.0 license.
Yes. TokenFlow is free and open source — you can use, modify and self-host it.
TokenFlow is available under the Apache-2.0 license.
TokenFlow is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/bytevisionlab-tokenflow.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.