Tencent Cloud
The Tencent-Hunyuan GitHub organization exposes a broad open-source portfolio. Pinned repositories include Hy3-preview for reasoning and agents, HunyuanVideo for large video generation, HunyuanImage-3.0 for native multimodal image generation, Hunyuan3D-2.1 for high-fidelity 3D assets, HunyuanOCR, and HunyuanVideo-I2V for image-to-video generation.
Editorial verdict
Developers surveying Tencent's open-source model assets across LLM, video, image, 3D and OCR.
Avoid using it as a hosted product substitute without repository-by-repository license and deployment review.
The open-source organization helps show Hunyuan's model breadth beyond Tencent Cloud APIs.
Open-source repositories are free to access; deployment cost depends on model size and infrastructure
GitHub, Hugging Face where linked, Self-hosted infrastructure
Commercial use should follow the current product, API, model license and billing terms.
Review prompt, file, media upload, retention and training-use terms before sensitive workloads.
Use it to shortlist Hunyuan repositories by modality and deployment target.
Pinned projects provide entry points for HunyuanVideo, HunyuanImage-3.0 and Hunyuan3D-2.1.
Model names, quotas, release status, regional access and commercial terms can change quickly; recheck official sources before procurement or production use.
hunyuan-hy3-preview
mimo-v2-flash
qwen
other · en · verified 2026-08-04
Confirms public organization and pinned repository portfolio.
other · en · verified 2026-05-17
Open-source native multimodal image-generation repository.
Last checked: 2026-08-04