HunyuanVideo 1.5 is an open-source lightweight video generation model by Tencent Hunyuan Team. Built on the DiT architecture with 8.3B parameters, it supports text-to-video and image-to-video, runs on consumer GPUs with 14GB VRAM, generates 5-10s HD videos, and boasts strong prompt responsiveness and cinematic quality.

LongCat Video is a unified AI model for text-to-video, image-to-video, and continuation tasks, offering efficient 720p 30fps generation with RLHF-tuned quality.

Infinite Talk AI is an audio-driven video tool for talking avatars with precise lip sync. InfiniteTalk turns images into lively, unlimited-length videos. Try free.

FlashVSR is the first real-time diffusion-based 4K video converter featuring video super-resolution (VSR). Perfect for long-video upscaling and detail recovery.

Seed3D AI is a fast image-to-3D platform powered by Seed3D 1.0, creating high-fidelity, simulation-ready 3D assets with 6K textures, PBR materials, and smart scenes.