# HunyuanVideo
HunyuanVideo is a family of open-weights text-to-video and image-to-video generation models published by Tencent, beginning with a 13-billion-parameter diffusion transformer (AI model that generates video by iteratively denoising data) released in December 2024 and continuing with the 8.3-billion-parameter HunyuanVideo-1.5 in November 2025.[5](https://huggingface.co/docs/diffusers/api/pipelines/hunyuan_video) • [6](https://huggingface.co/tencent/HunyuanVideo-1.5) Tencent released both generations' code and weights publicly, stating that the original aimed to bridge the gap between closed-source and open-source video generation communities.[1](https://arxiv.org/html/2412.03603) This article covers the model family itself; Tencent, its founders, and any consumer products built on the models are treated in separate articles.
| Key fact | Value |
|---|---|
| Original model | 13B-parameter DiT, released December 2024[5](https://huggingface.co/docs/diffusers/api/pipelines/hunyuan_video) |
| HunyuanVideo-1.5 | 8.3B parameters, inference released November 20, 2025[3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file) • [6](https://huggingface.co/tencent/HunyuanVideo-1.5) |
| Output | 480p–720p at 5–10 seconds, upscalable to 1080p (1.5)[2](https://arxiv.org/html/2511.18870) |
| Minimum GPU memory | 14 GB with model offloading; 13.6 GB peak for 720p 121-frame inference[2](https://arxiv.org/html/2511.18870) • [3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file) |
| License | Tencent Hunyuan Community License, excluding the EU, UK, and South Korea[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/) |
| Vendor win rate vs Veo3 | −10.32% (vendor-reported, November 2025)[2](https://arxiv.org/html/2511.18870) |
| Independent ELO standing (May 2026) | ~996 (original) and ~1,015 (1.5), bottom fifth of ~90 tracked models[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/) |
## Release timeline and versions
The original HunyuanVideo, a 13-billion-parameter text-to-video foundation model, was released with code and weights in December 2024 alongside a technical report.[1](https://arxiv.org/html/2412.03603) • [5](https://huggingface.co/docs/diffusers/api/pipelines/hunyuan_video) Tencent followed it with HunyuanVideo-I2V, an image-to-video framework shipped with pretrained weights, inference code, and LoRA training code for customizable special effects.[4](https://github.com/Tencent/HunyuanVideo-I2V?tab=readme-ov-file) HunyuanCustom, a subject-driven generation capability producing identity-consistent video from a single image with audio and lip-sync, was released on May 9, 2025.[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/)
[The 1](https://www.edgepedia.org/the-1).5 generation arrived in late 2025 in a rapid sequence of drops: inference code and weights on November 20, 2025; cache inference support (deepcache, teacache, taylorcache) and Hugging Face Diffusers integration on November 27; a step-distilled 480p image-to-video model plus training and LoRA tuning code on December 5; and fp8 GEMM inference support on December 23, 2025.[3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file) The step-distilled model generates videos in 8 or 12 steps, which Tencent reports cuts end-to-end generation time by 75%, letting a single RTX 4090 produce a video within 75 seconds.[3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file) As of the checks available in this record, no HunyuanVideo 2.0 had appeared.[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/)
## How it works
The original HunyuanVideo is a 13-billion-parameter diffusion transformer (DiT) built on a dual-stream to single-stream design: video tokens and text tokens are processed through separate streams first, then concatenated and fed to the transformer, which fuses the multimodal information.[5](https://huggingface.co/docs/diffusers/api/pipelines/hunyuan_video) Text conditioning comes from a pretrained multimodal large language model (MLLM) rather than a conventional text encoder, chosen for better image-text alignment, richer detail description and reasoning, and the ability to act as a zero-shot learner when system instructions are added to prompts.[5](https://huggingface.co/docs/diffusers/api/pipelines/hunyuan_video) A 3D causal variational autoencoder (VAE) compresses video in space and time, processing footage at its original resolution and frame rate.[5](https://huggingface.co/docs/diffusers/api/pipelines/hunyuan_video)
HunyuanVideo-1.5 restructures this into a two-stage pipeline. A unified 8.3B DiT handles both text-to-video and image-to-video, producing 480p to 720p clips of 5 to 10 seconds; a video [super-resolution network](https://www.edgepedia.org/super-resolution-network) then upscales to 1080p.[2](https://arxiv.org/html/2511.18870) The paired 3D causal VAE compresses 16× spatially and 4× along the time axis.[2](https://arxiv.org/html/2511.18870) For speed, the model uses Selective and Sliding Tile Attention (SSTA), which prunes redundant spatiotemporal key-value blocks; Tencent reports a 1.87× end-to-end speedup in 10-second 720p synthesis compared with FlashAttention-3.[2](https://arxiv.org/html/2511.18870) • [3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file) Tencent also states that 1.5 was trained with the [Muon optimizer](https://www.edgepedia.org/muon-optimizer), and released the training code and LoRA tuning script accordingly.[3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file)
## By the numbers
The parameter counts moved in opposite directions to capability: 13B in the original, 8.3B in 1.5, with the smaller model claimed by Tencent's model card to establish a new state-of-the-art among open-source models in visual quality and motion coherence.[6](https://huggingface.co/tencent/HunyuanVideo-1.5) Output lengths run 5 to 10 seconds at 480p–720p, with 1080p available through the super-resolution stage; the original model's maximum native duration is about 5 seconds at 720p.[2](https://arxiv.org/html/2511.18870) • [7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/)
Memory requirements are the family's most practical number. With pipeline offloading, group offloading, and VAE tiling enabled, the 1.5 pipeline completes 720p 121-frame text-to-video or image-to-video inference at a peak of 13.6 GB, fitting a single consumer GPU such as an RTX 4090; the official repository lists 14 GB minimum with model offloading.[2](https://arxiv.org/html/2511.18870) • [3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file)
At launch in December 2024, an evaluation using 1,533 text prompts and more than 60 human evaluators reported the highest overall VBench 1.0 score among open-source text-to-video models.[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/) The launch technical report also claimed performance comparable to, or better than, leading closed-source models including [Runway Gen](https://www.edgepedia.org/runway-gen)-3 and Luma 1.6 plus three top Chinese video models; this is a vendor-reported claim.[1](https://arxiv.org/html/2412.03603)
## How it compares with Sora, Veo, Kling and Wan
Tencent's own human-rated table for 1.5 (November 2025) scores instruction following at 61.57, ahead of Wan2.2 (44.07), Kling2.1 Master (50.03), and Seedance Pro (53.19) but behind Veo3 (73.77); on structural stability it reports 79.75 versus Veo3's 75.62.[2](https://arxiv.org/html/2511.18870) In the same vendor head-to-head win-rate table, 1.5 posts +17.12% over Wan2.2, +12.6% over Kling2.1 Master, and +11.02% over Seedance Pro, but −10.32% against Veo3.[2](https://arxiv.org/html/2511.18870) These are the vendor's numbers; no independent evaluation in this record reproduces them.
An independent comparison against the other major open alternative frames the trade-off differently: HunyuanVideo-1.5 is smaller (8.3B vs Wan 2.2's 27B parameters), lighter on memory (14 GB minimum vs 24 GB+), and more restrictive in licensing (a custom license excluding EU/UK/KR versus Apache 2.0).[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/) Against commercial leaders, the gap is in length and resolution: roughly 10 seconds at 720p native (1080p upscaled) versus the 15–20 second ceilings of commercial systems.[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/) Direct comparisons with Sora or Veo beyond the vendor's Veo3 table are not covered by independent data in this record.
## Licensing, availability and cost
Both generations are governed by the Tencent Hunyuan Community License, which explicitly excludes the European Union, United Kingdom, and South Korea from authorized use, a restriction attributed to avoidance of EU AI Act regulatory exposure.[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/) The license permits commercial use elsewhere, but the exclusion means organizations in those three jurisdictions are outside the authorized scope. Weights and code are distributed through [Hugging Face](https://www.edgepedia.org/hugging-face) and GitHub, and 1.5 is available in Hugging Face Diffusers.[3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file) This record contains no hosted API or product pricing for the models.
## Adoption and reception
The open-source ecosystem around the family is substantial. An August 2026 audit counted more than 12,400 GitHub stars across the two repositories, over 128 LoRA entries on [Civitai](https://www.edgepedia.org/civitai), and a complete ComfyUI workflow library; Kohya-ss added LoRA training support through its musubi-tuner project, alongside Tencent's official LoRA scripts.[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/) • [3](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file) The same audit's verdict as of August 2026 was that HunyuanVideo is a solid mid-tier choice for open-source video generation: not the best available, but well-understood, well-supported, and ecosystem-backed.[7](https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/)
## References
1. HunyuanVideo: A Systematic Framework For Large Video Generative Models — https://arxiv.org/html/2412.03603
2. HunyuanVideo 1.5 Technical Report — https://arxiv.org/html/2511.18870
3. Tencent-Hunyuan/HunyuanVideo-1.5 (official GitHub repository) — https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5?tab=readme-ov-file
4. Tencent-Hunyuan/HunyuanVideo-I2V (GitHub README) — https://github.com/Tencent/HunyuanVideo-I2V?tab=readme-ov-file
5. HunyuanVideo — Hugging Face Diffusers documentation — https://huggingface.co/docs/diffusers/api/pipelines/hunyuan_video
6. tencent/HunyuanVideo-1.5 — Hugging Face model card — https://huggingface.co/tencent/HunyuanVideo-1.5
7. HunyuanVideo Review — Tencent's 13B Open-Source Video Model (ChatForest) — https://chatforest.com/reviews/hunyuanvideo-tencent-open-source-video-generation/
---
*Topic: Encyclopedia › Technology and the built world › Computing and digital systems › Modern AI: foundation models, generative AI, and the AI industry › Model families and named models › Video generation models*
*Initially written Sep 17, 2026 · Edited: Oct 11, 2026; Oct 15, 2026*
*Copyright 2026 EdgeChat AI, a subsidiary of Biostate AI.*
License: Edgepedia Community License 1.0, https://www.edgepedia.org/edgepedia/license