All tasks / Models

HunyuanVideo 1.5

Tencent's open-weights 8.3B video model for text- and image-to-video that runs on consumer GPUs.

Tencent
Open weights
Released 20 Nov 2025

Where it ranks

C
Video generation
Models · Local · 1,169 on LMArena (Arena) Text-to-Video leaderboard (secondary benchmark)

Facts

Vendor: Tencent
Family: HunyuanVideo
Released: 20 Nov 2025
Weights: Open: download and run it yourself
License: Tencent Hunyuan Community License
Parameters: 8.3B
GPU memory to run locally: ~14 GB (Official minimum 14 GB with model offloading enabled; Wan2GP claims ~6 GB)
API price: $0.07 per second of video (hosted on Fal, $4.50/min as listed on AA (no audio))
Access: Free (open weights)
Last verified: 18 Oct 2026

Price from artificialanalysis.ai, 18 Oct 2026.

Benchmark results

Benchmark	Result	Entry on the leaderboard	As of	Source
Artificial Analysis Video Arena: Image to Video, no audio (AA-Video-I2V-Silent v1.0)	1,134	`HunyuanVideo-1.5 (Fal)` AA-Video-I2V-Silent v1.0 (no audio) board	18 Oct 2026	artificialanalysis.ai
LMArena (Arena) Image-to-Video leaderboard	1,198	`hunyuan-video-1.5` LMArena official leaderboard dataset (HF lmarena-ai/leaderboard-dataset, config image_to_video, split latest, publish date 2026-09-22); arena.ai page itself returned HTTP 403	22 Sep 2026	datasets-server.huggingface.co
LMArena (Arena) Text-to-Video leaderboard	1,169	`hunyuan-video-1.5` LMArena official leaderboard dataset (HF lmarena-ai/leaderboard-dataset, config text_to_video, split latest, publish date 2026-09-22); arena.ai page itself returned HTTP 403	22 Sep 2026	datasets-server.huggingface.co

Where you can use it

SComfyUIWorkflow platforms · Local
SSwarmUIApps · Local
SWanGP (Wan2GP)Apps · Local

Earlier versions

HunyuanVideo · 3 Dec 2024

Compare

Alternatives to HunyuanVideo 1.5

Sources