Project description: Game devs. Comic creators. VTubers. You have the worlds. The characters. The stories. But turning them into video? That's always been the hard part. Not anymore. Meet a video generator built for the people who create — powered by AI agents that take your vision node by node, and bring it to life exactly how you imagined. No film crew. No weeks of editing. Just your idea — and a canvas that gets it done.
Process steps: Step 1: Register on melius.com. Step 2: Create a new project. Step 3: Brief Melius Ai agent assistance about project, the Ai assistance build the full workflow from scratch. Step 4: Edit and modify the workflow to meet target requirement. Step 5: Use stitch utility node to stitch all video output together to form the final long form video.
Screenshot of canvas is attached.
Feedback: Very user friendly, the canva is very lightwight compared to other automation canvas. My only recommendation is that the utility stitch node should be able to accept audio input such as background music or voiceover, currently stitch only accepts videos input.
This is my submission for the Video.js Skins Design Challenge!🚀
Nubi is a playful, animated video player designed for kids and family content.
Why this niche: children's video is one of the most-watched categories online today and one of the most valuable for creators and platforms.
☁️ What makes it special:
• Interactive googly eyes peek over the frame
• Day and night mode: a bright pastel sky with fluffy clouds, or a calm starry night where the eyes get sleepy.
• A friendly, easy-to-use look
• On phones it becomes a vertical 9:16 video with thumb-friendly controls.
Just made an introductory video of myself powered by Artificial Intelligence
A quick introduction to who I am, what I create, and how I bring ideas to life through AI-powered visuals, cinematic storytelling, and professional video editing.:
A 60-second fan short made entirely with AI video, with my own face as the lead. Nine shots, seven characters, built from one selfie and a set of reference images. No cameras were used.
I started from a public prompt guide by kaye_creatives on Higgsfield and treated it like a shooting script: built my own character sheet, cast the missing character, generated each shot separately, then cut, captioned, titled and mixed it myself.
What I'd pass on to anyone trying this:
Give every reference image one job. Face, room, prop or camera angle, never two at once.
Put exact counts in the prompt. Models add people and props unless you tell them how many.
Generate long, cut short. My first assembly was 67 seconds. The final is 60, and the pace is where the quality came from.