HunyuanVideo v1.5: Multi Resolution Video Generation for ComfyUI

HunyuanVideo 1.5: multi-resolution T2V/I2V with Comfy-Org FP16/FP8 packs and Apache 2.0 licensing.

H

HunyuanVideo v1.5

VideoText-to-VideoImage-to-VideoApache 2.0

Major update to Tencent's open-source video model. Multiple 480p/720p T2V and I2V variants, distilled options, and Comfy-Org single-file packs. Apache 2.0.

Hugging FaceComfy-Org packGitHub
DeveloperTencent
ArchitectureDiffusion Transformer + updated VAE / text encoder stack
LicenseApache 2.0
Comfy packComfy-Org/HunyuanVideo_1.5_repackaged (split_files)
Official layouttencent/HunyuanVideo-1.5 (multi-file Diffusers-style transformers)
The official tencent/HunyuanVideo-1.5 repo is a multi-file Diffusers-style layout (per-resolution transformer/*/diffusion_pytorch_model.safetensors). For ComfyUI, use Comfy-Org/HunyuanVideo_1.5_repackaged split files unless your workflow says otherwise.

Guides and workflows related to this model series.

No articles found.