FoundationVision / UniTok
[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding
Why this job: topics: text-to-image, image-generation
What it does
This repo implements UniTok, a unified visual tokenizer well-suited for both generation and understanding tasks. It is compatiable with autoregressive generative models (e.g. LlamaGen), multimodal understanding models (e.g. LLaVA), and unified MLLMs (e.g. Chameleon and Liquid).
Get started
git clone https://github.com/FoundationVision/UniTok.git
cd UniTok
pip install -r requirements.txt You need: Python ≥ 3.10; PyTorch ≥ 2.3.1
- Maintenance
- Inactive
- Last commit 12 months ago
- Stars
- 537
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 96% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 53% closed
- 16 still open
- Pull requests
- 0 merged
- 1 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Lakonik / LakonLab | 490 | 14 days ago | Apache-2.0 | No downloads |
| yuji-hatakeyama / opencode-gpt-imagegen | 123 | 2 days ago | MIT | No downloads |
| XingtongGe / SenseFlow | 118 | 8 months ago | Custom | No downloads |
More: languages, topics and project record
Languages
- Python 96%
- Shell 2%
- JavaScript 1%
- HTML <1%
Topics
- autoregressive-models
- generative
- generative-ai
- generative-model
- image-generation
- image-tokenizer
- large-language-models
- text-to-image
- tokenizer
Project record
- JobImage generation
- StatusListed
- Commits25
- Forks16
- Watching9
- Stars in 28 days+2
- CreatedFeb 27, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026