TokenFlow-t2i

Open weights ByteDance December 2024

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
ByteDance
Organisation type
Industry
Country
China
Published
4 December 2024
Authors
Liao Qu, Huichao Zhang, Yiheng Liu, Xu Wang, Yi Jiang, Yiming Gao, Hu Ye, Daniel K. Du, Zehuan Yuan, Xinglong Wu

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Image generation
Task
Image generation, Text-to-image

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Open — downloadable
Model access
Open weights (unrestricted)
Training code
Open source

Apache 2.0 https://github.com/ByteFlow-AI/TokenFlow/tree/main Apache 2.0 https://huggingface.co/ByteFlow-AI/TokenFlow-t2i

Hugging Face
ByteFlow-AI

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Unknown

Sources

Where this record came from and when it was last checked.

Reference
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
Last updated
28 November 2025

What the numbers mean

Where it came from

TokenFlow-t2i was published by ByteDance, in China, in December 2024. The organisation is categorised as industry.

It works in Image generation, and is recorded as doing image generation, Text-to-image.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the ByteFlow-AI organisation on Hugging Face.

Answers

TokenFlow-t2i — common questions

01

Where can I download TokenFlow-t2i?

Its weights are published under the ByteFlow-AI organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

02

What GPU do I need to run TokenFlow-t2i?

We cannot say. TokenFlow-t2i has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

03

Is TokenFlow-t2i open source?

Its weights are published, so TokenFlow-t2i can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

04

How many parameters does TokenFlow-t2i have?

No parameter count has been published for TokenFlow-t2i, which is why no memory or speed figure appears on this page.

05

Who created TokenFlow-t2i?

TokenFlow-t2i was published by ByteDance, based in China, categorised as industry.

06

When was TokenFlow-t2i released?

TokenFlow-t2i was published in December 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

What is TokenFlow-t2i used for?

TokenFlow-t2i works in Image generation, and is recorded as handling image generation, Text-to-image. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.