Model reference · open weights
HunyuanVideo is an open-weight video model from tencent. HunyuanVideo (BF16) weighs 39.8 GB; the smallest configuration that runs it is L40S 48 GB.
Summary of the tencent/HunyuanVideo model card, 2026-10-01
What it is
| Released by | tencent |
|---|---|
| Released | 2024-12-01 |
| VRAM | 39.8 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 5090 32 GB | does not fit | |
| L40S 48 GB | tight | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This repo contains PyTorch model definitions, pre-trained weights and inference/sampling code for our paper exploring HunyuanVideo. You can find more visualizations on our project page.
HunyuanVideo: A Systematic Framework For Large Video Generation Model Training
We present HunyuanVideo, a novel open-source video foundation model that exhibits performance in video generation that is comparable to, if not superior to, leading closed-source models. In order to train HunyuanVideo model, we adopt several key technologies for model learning, including data curation, image-video joint model training, and an efficient infrastructure designed to facilitate large-scale model training and inference. Additionally, through an effective strategy for scaling model architecture and dataset, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models.
We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion diversity, text-video alignment, and generation stability. According to professional human evaluation results, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and 3 top-performing Chinese video generative models. By releasing the code and weights of the foundation model and its applications, we aim to bridge the gap between closed-source and open-source video foundation models. This initiative will empower everyone in the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem.
HunyuanVideo is trained on a spatial-temporally compressed latent space, which is compressed through a Causal 3D VAE. Text prompts are encoded using a large language model, and used as the conditions. Taking Gaussian noise and the conditions as input, our generative model produces an output latent, which is then decoded to images or videos through the 3D VAE decoder.
HunyuanVideo introduces the Transformer design and employs a Full Attention mechanism for unified image and video generation. Specifically, we use a "Dual-stream to Single-stream" hybrid model design for video generation. In the dual-stream phase, video and text tokens are processed independently through multiple Transformer blocks, enabling each modality to learn its own appropriate modulation mechanisms without interference. In the single-stream phase, we concatenate the video and text tokens and feed them into subsequent Transformer blocks for effective multimodal information fusion. This design captures complex interactions between visual and semantic information, enhancing overall model performance.
Some previous text-to-video models typically use pre-trained CLIP and T5-XXL as text encoders where CLIP uses Transformer Encoder and T5 uses an Encoder-Decoder structure. In contrast, we utilize a pre-trained Multimodal Large Language Model (MLLM) with a Decoder-Only structure as our text encoder, which has the following advantages: (i) Compared with T5, MLLM after visual
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → Hunyuan Video Text to Video: it loads ComfyUI's own build of this model, the files above.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the files of the template “Hunyuan Video Text to Video” (33.0 GB)
get comfyanonymous/flux_text_encoders clip_l.safetensors text_encoders
get Comfy-Org/HunyuanVideo_repackaged split_files/text_encoders/llava_llama3_fp8_scaled.safetensors text_encoders
get Comfy-Org/HunyuanVideo_repackaged split_files/diffusion_models/hunyuan_video_t2v_720p_bf16.safetensors diffusion_models
get Comfy-Org/HunyuanVideo_repackaged split_files/vae/hunyuan_video_vae_bf16.safetensors vae
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT