Viaya

↗ HN profile [ 138 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Hi HN — we just open‑sourced/released (or “publicly launched”, depending on whether it's open‑source) a new image generation & editing model called Doubao‑Seedream-4.5, by Volcano Engine. Compared with 4.0, this version…

  2. We’ve been exploring how to make AI video generation consistent. Most existing text-to-video models can create impressive short clips—but the “same person” often drifts across shots or disappears when multiple subjects…

  3. AI-generated video has made remarkable progress, but the output often caps at 480p or 720p—blurry textures, jagged edges, and lacking detail. For creators, that’s far from production-ready. FlashVSR is a…

  4. Hey HN I’ve been experimenting with different image generation tools for months — but I kept running into the same problems: slow generation, repeated outputs, and limited artistic control. That’s why I built…

  5. I built Ovi AI, an audio-video generation tool that brings static images to life with synchronized voice, motion, and ambient sound. Unlike traditional tools that require separate dubbing and editing, Ovi AI generates…

  6. Sora2 AI is a next-generation AI model for video and audio generation. It builds on the original Sora, adding advanced physics simulation, temporal consistency, synced audio, and rich style control to produce…

  7. I’ve been following both Veo3 and Wan 2.5 closely, and the differences are starting to feel interesting. Veo3 has been the benchmark for cinematic AI video, especially with its stability and audio-video sync. Wan 2.5,…

  8. Hi HN, I’m excited to share HuMo AI, an AI-driven tool that helps creators easily produce realistic, human-centric videos. HuMo AI supports text, image, and audio inputs, turning simple ideas into fully customized,…

  9. I’m excited to introduce Infinite Talk AI, a tool that creates realistic, unlimited-length AI talking videos. It transforms your audio into lifelike videos with synchronized lip movements, facial expressions, and body…

  10. I built Nano Banana AI , a fast tool to edit existing images with text prompts. I made it because current tools felt slow and mostly focus on generating new images. This one is different: Image-to-image only — edit…

  11. I built VidVeo3 – an AI-powered video creation tool based on Google’s Veo 3 model. You can type in a prompt (e.g. “a stormy lighthouse at night,” “a short sci-fi scene,” or “a person walking through neon-lit Tokyo”),…