Tencent's open-weight video model for local text-to-video and image-to-video
HunyuanVideo is Tencent's open-weight video generation family for text-to-video and image-to-video work. HunyuanVideo 1.5 uses an 8.3-billion-parameter architecture designed to run on consumer GPUs with model offloading, generates coherent motion and detailed visuals, and includes a super-resolution stage for 1080p output. Tencent publishes model weights, inference and training code, LoRA tuning support, and integrations for Diffusers and ComfyUI.
It's easier when you're signed in — Altern helps you get more out of AI.
By continuing you agree to our Terms and Privacy Policy.