I built a video generator

I built a video generator for game devs, comic creators & VTubers. Brief your agents, watch them work, tweak til it's perfect. Built entirely on

@Melius for the@contra x #MeliusChallenge. #Melius

Ai models used in the project workflow: seedance 2.0, Claude sonnet 4.5, and GPT Image 2.

Project Link: https://app.melius.com/projects/48bc8d2f-f2f2-4a9f-a333-25d0db6a5947/canvas/053a8b12-85eb-47d3-8f50-41d85b94bf7e

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.

Socials: https://x.com/PidiaSam/status/2056418002321494213?s=20

https://x.com/PidiaSam/status/2056440290743910861?s=20