Vidthis AI

Vidthis AI is a professional, AI-powered platform built for creators who need high-quality video and image generation in a single workflow. Its flagship model, LTX-2, is an open-source and uncensored video generator designed for production-grade results, capable of creating up to 20 seconds of video at up to 50 fps, with synchronized audio that matches the on-screen action. This unified audio-visual generation helps you produce scenes that feel complete—motion, timing, and sound cues are generated together rather than stitched in later.

Vidthis AI supports both text-to-video and image-to-video creation. You can choose your generation mode, then configure resolution (480p, 720p, or 1080p), aspect ratio, and duration (5–20 seconds) to fit your project. The platform is designed for high creative freedom: prompts can include scene descriptions, character traits, camera direction, and audio cues. For more control and consistency, LTX-2 LoRA support enables director-level adjustments such as repeatable character identity, styling, and camera movement choices across multiple shots. You can also refine outputs by reusing a seed to reproduce and iterate on results.

Beyond LTX-2, Vidthis AI positions itself as an all-in-one content creation hub by offering access to additional advanced models such as Wan 2.5, Hailuo 23, and Nano Banana Pro, letting users experiment with different aesthetics or workflows from one place. LTX-2 model weights are available publicly via GitHub and Hugging Face, supporting customization and open development. For support, Vidthis AI can be contacted at [email protected].