Hunyuan Video Family: Tencent Open Source Video Generation for ComfyUI

Tencent's open-source video generation model series. From v1.0 to v1.5, delivering high-quality text-to-video and image-to-video generation.

H

HunyuanVideo by Tencent

VideoText-to-VideoImage-to-VideoOpen Source

Open-source video generation model series from Tencent. Diffusion Transformer with 3D VAE — text-to-video and image-to-video at up to 720p (v1.0) and multi-resolution variants in v1.5.

GitHubHF OrgPaper
This Model Hub series covers HunyuanVideo only. Tencent’s earlier HunyuanDiT image models (and their ControlNets / LoRAs) are out of scope here — they are a separate image stack, not Video downloads.

Versions

VersionKey ImprovementsLicenseReleased
v1.0First open Video release — 720p T2V + I2V; Comfy-Org / Kijai / GGUF packsOpen weights2024-12
v1.5Multi-res T2V/I2V, distilled & FP8 Comfy packs, Apache 2.0Apache 2.02025-11

Select a version above for tutorials and related news. Curated ComfyUI weight downloads live in the Model Hub catalog.