The open image model just hit commercial grade. tencent's hunyuan image 3.0, out oct 7, is the…
the open image model just hit commercial grade. tencent's hunyuan image 3.0, out oct 7, is the first open-source native multimodal image model built for products, at 8 billion parameters.
the closed-image premium just lost a reason to exist.
Context
Verified event date: Tencent open-sourced HunyuanImage 3.0 on Sep 28, 2025, with inference code and model weights public (Hugging Face and GitHub model cards). Its technical report describes a native multimodal model that unifies understanding and generation in an autoregressive framework.
The model card says it is the largest open-source image generation Mixture of Experts model to date: 64 experts and 80 billion total parameters, 13 billion activated per token.
The open-source native multimodal image model matches Tencent's model card and report. The post says 'out oct 7' and '8 billion parameters'; the release is dated Sep 28, 2025, and the card gives 80 billion total with 13 billion activated per token. 'Built for products' and the closed-image premium losing a reason to exist are not seen in the excerpts read, so unsupported here, not refuted. and the author's.
'the open image model just hit commercial grade' is the author's opinion.
Related work
- Hugging Face: tencent/HunyuanImage-3.0 ↗Model card.
- arXiv: HunyuanImage 3.0 Technical Report ↗Sep 2025.
- GitHub: Tencent-Hunyuan/HunyuanImage-3.0 ↗Sep 28, 2025 release.
Watch next
- Read the license terms on the model card for commercial use.
Sources
- Hugging Face, HunyuanImage-3.0huggingface.co
- arXiv, technical reportarxiv.org
- GitHub, HunyuanImage-3.0github.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 08:26 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →