HunyuanVideo
6.4#173 in ai video generatorsLinuxSelf-hosted
Visit
| Fact | HunyuanVideo | PixVerse |
|---|---|---|
| AI avatars | No | Yes |
| API access | No | Yes |
| Founded | 1998 | 2023 |
| Headquarters | Shenzhen, China | Singapore |
| Image-to-video | The project links a separate HunyuanVideo image-to-video model with inference code and checkpoints. | Yes |
| License | The repository links a license file, but the opened page does not state license terms in its displayed content. | PixVerse is listed as proprietary software; its open-source notice covers integrated Qwen-Image and Qwen-Image-Edit models under Apache License 2.0. |
| Maximum resolution | 1080p | 4k |
| Text-to-video | The released model generates videos from text prompts, with supported output settings up to 720p and 129 frames. | Yes |
No prices published.
It suits technically capable users running Linux with NVIDIA CUDA hardware who want open-source text-to-video or image-to-video generation. Commercial projects are allowed, while users needing avatars or an API should note their absence.
It suits people or teams generating videos from text or images, or using AI avatars through an API. Plan choice matters for credit volume, resolution, concurrency, and Enterprise API access.